Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592/special_tokens_map.json +51 -0
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592/tokenizer.json +0 -0
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592/trainer_state.json +830 -0
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/special_tokens_map.json +51 -0
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/tokenizer.json +0 -0
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/tokenizer_config.json +55 -0
- ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/trainer_state.json +1227 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/special_tokens_map.json +51 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/tokenizer.json +0 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/tokenizer_config.json +55 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/trainer_state.json +616 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/special_tokens_map.json +51 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/tokenizer.json +0 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/tokenizer_config.json +55 -0
- ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/trainer_state.json +957 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/trainer_state.json +210 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/trainer_state.json +306 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/trainer_state.json +210 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/trainer_state.json +306 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/trainer_state.json +171 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/trainer_state.json +267 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/trainer_state.json +299 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/tokenizer_config.json +55 -0
- ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/trainer_state.json +395 -0
- ood-viclickbait2025-bamibert-source-source-02-s42-20260827T171930Z-ee19aa8e/trainer/checkpoint-380/special_tokens_map.json +51 -0
- ood-viclickbait2025-bamibert-source-source-02-s42-20260827T171930Z-ee19aa8e/trainer/checkpoint-380/tokenizer.json +0 -0
- ood-viclickbait2025-bamibert-source-source-02-s42-20260827T171930Z-ee19aa8e/trainer/checkpoint-380/tokenizer_config.json +55 -0
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592/trainer_state.json
ADDED
|
@@ -0,0 +1,830 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2592,
|
| 3 |
+
"best_metric": 0.826900458402438,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592",
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2592,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.05787037037037037,
|
| 14 |
+
"grad_norm": 30.672374725341797,
|
| 15 |
+
"learning_rate": 5.555555555555555e-07,
|
| 16 |
+
"loss": 4.2569,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.11574074074074074,
|
| 21 |
+
"grad_norm": 28.60749053955078,
|
| 22 |
+
"learning_rate": 1.1342592592592594e-06,
|
| 23 |
+
"loss": 4.0786,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1736111111111111,
|
| 28 |
+
"grad_norm": 34.10677719116211,
|
| 29 |
+
"learning_rate": 1.7129629629629632e-06,
|
| 30 |
+
"loss": 3.7466,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.23148148148148148,
|
| 35 |
+
"grad_norm": 16.774616241455078,
|
| 36 |
+
"learning_rate": 2.2916666666666666e-06,
|
| 37 |
+
"loss": 3.4551,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.28935185185185186,
|
| 42 |
+
"grad_norm": 19.944089889526367,
|
| 43 |
+
"learning_rate": 2.8703703703703706e-06,
|
| 44 |
+
"loss": 3.2359,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3472222222222222,
|
| 49 |
+
"grad_norm": 20.603628158569336,
|
| 50 |
+
"learning_rate": 3.449074074074074e-06,
|
| 51 |
+
"loss": 3.1431,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4050925925925926,
|
| 56 |
+
"grad_norm": 28.288143157958984,
|
| 57 |
+
"learning_rate": 4.027777777777779e-06,
|
| 58 |
+
"loss": 3.0682,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.46296296296296297,
|
| 63 |
+
"grad_norm": 42.422584533691406,
|
| 64 |
+
"learning_rate": 4.606481481481481e-06,
|
| 65 |
+
"loss": 2.4462,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5208333333333334,
|
| 70 |
+
"grad_norm": 65.8946762084961,
|
| 71 |
+
"learning_rate": 5.185185185185185e-06,
|
| 72 |
+
"loss": 1.9385,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5787037037037037,
|
| 77 |
+
"grad_norm": 93.30895233154297,
|
| 78 |
+
"learning_rate": 5.7638888888888886e-06,
|
| 79 |
+
"loss": 1.6113,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6365740740740741,
|
| 84 |
+
"grad_norm": 66.67131042480469,
|
| 85 |
+
"learning_rate": 6.342592592592594e-06,
|
| 86 |
+
"loss": 1.3487,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6944444444444444,
|
| 91 |
+
"grad_norm": 25.705554962158203,
|
| 92 |
+
"learning_rate": 6.9212962962962974e-06,
|
| 93 |
+
"loss": 1.357,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.7523148148148148,
|
| 98 |
+
"grad_norm": 80.34606170654297,
|
| 99 |
+
"learning_rate": 7.500000000000001e-06,
|
| 100 |
+
"loss": 1.198,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8101851851851852,
|
| 105 |
+
"grad_norm": 46.074378967285156,
|
| 106 |
+
"learning_rate": 8.078703703703705e-06,
|
| 107 |
+
"loss": 1.0508,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.8680555555555556,
|
| 112 |
+
"grad_norm": 23.091442108154297,
|
| 113 |
+
"learning_rate": 8.657407407407408e-06,
|
| 114 |
+
"loss": 1.1129,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.9259259259259259,
|
| 119 |
+
"grad_norm": 24.728858947753906,
|
| 120 |
+
"learning_rate": 9.236111111111112e-06,
|
| 121 |
+
"loss": 1.3786,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.9837962962962963,
|
| 126 |
+
"grad_norm": 7.195851802825928,
|
| 127 |
+
"learning_rate": 9.814814814814815e-06,
|
| 128 |
+
"loss": 1.0689,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_accuracy": 0.9283854166666666,
|
| 134 |
+
"eval_loss": 0.255921870470047,
|
| 135 |
+
"eval_macro_f1": 0.6285352413936267,
|
| 136 |
+
"eval_runtime": 0.9269,
|
| 137 |
+
"eval_samples_per_second": 1657.096,
|
| 138 |
+
"eval_steps_per_second": 103.569,
|
| 139 |
+
"eval_weighted_f1": 0.9139611830188414,
|
| 140 |
+
"step": 432
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0416666666666667,
|
| 144 |
+
"grad_norm": 24.38639259338379,
|
| 145 |
+
"learning_rate": 1.0393518518518519e-05,
|
| 146 |
+
"loss": 0.9738,
|
| 147 |
+
"step": 450
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.099537037037037,
|
| 151 |
+
"grad_norm": 22.60640525817871,
|
| 152 |
+
"learning_rate": 1.0972222222222224e-05,
|
| 153 |
+
"loss": 1.1063,
|
| 154 |
+
"step": 475
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.1574074074074074,
|
| 158 |
+
"grad_norm": 48.40523147583008,
|
| 159 |
+
"learning_rate": 1.1550925925925926e-05,
|
| 160 |
+
"loss": 0.8008,
|
| 161 |
+
"step": 500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.2152777777777777,
|
| 165 |
+
"grad_norm": 66.28334045410156,
|
| 166 |
+
"learning_rate": 1.2129629629629631e-05,
|
| 167 |
+
"loss": 0.9174,
|
| 168 |
+
"step": 525
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.2731481481481481,
|
| 172 |
+
"grad_norm": 77.04571533203125,
|
| 173 |
+
"learning_rate": 1.2708333333333333e-05,
|
| 174 |
+
"loss": 1.1044,
|
| 175 |
+
"step": 550
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.3310185185185186,
|
| 179 |
+
"grad_norm": 13.086089134216309,
|
| 180 |
+
"learning_rate": 1.3287037037037039e-05,
|
| 181 |
+
"loss": 1.0311,
|
| 182 |
+
"step": 575
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.3888888888888888,
|
| 186 |
+
"grad_norm": 124.03707885742188,
|
| 187 |
+
"learning_rate": 1.3865740740740742e-05,
|
| 188 |
+
"loss": 0.9336,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.4467592592592593,
|
| 193 |
+
"grad_norm": 27.15654945373535,
|
| 194 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 195 |
+
"loss": 1.0349,
|
| 196 |
+
"step": 625
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.5046296296296298,
|
| 200 |
+
"grad_norm": 6.650602340698242,
|
| 201 |
+
"learning_rate": 1.502314814814815e-05,
|
| 202 |
+
"loss": 0.8483,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.5625,
|
| 207 |
+
"grad_norm": 7.203736782073975,
|
| 208 |
+
"learning_rate": 1.5601851851851853e-05,
|
| 209 |
+
"loss": 0.9895,
|
| 210 |
+
"step": 675
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.6203703703703702,
|
| 214 |
+
"grad_norm": 38.05658721923828,
|
| 215 |
+
"learning_rate": 1.6180555555555557e-05,
|
| 216 |
+
"loss": 0.8598,
|
| 217 |
+
"step": 700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.6782407407407407,
|
| 221 |
+
"grad_norm": 264.2079772949219,
|
| 222 |
+
"learning_rate": 1.675925925925926e-05,
|
| 223 |
+
"loss": 0.8142,
|
| 224 |
+
"step": 725
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.7361111111111112,
|
| 228 |
+
"grad_norm": 30.365806579589844,
|
| 229 |
+
"learning_rate": 1.7337962962962964e-05,
|
| 230 |
+
"loss": 1.0979,
|
| 231 |
+
"step": 750
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.7939814814814814,
|
| 235 |
+
"grad_norm": 1.4746909141540527,
|
| 236 |
+
"learning_rate": 1.7916666666666667e-05,
|
| 237 |
+
"loss": 0.7108,
|
| 238 |
+
"step": 775
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.8518518518518519,
|
| 242 |
+
"grad_norm": 103.497314453125,
|
| 243 |
+
"learning_rate": 1.849537037037037e-05,
|
| 244 |
+
"loss": 1.0016,
|
| 245 |
+
"step": 800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.9097222222222223,
|
| 249 |
+
"grad_norm": 68.68548583984375,
|
| 250 |
+
"learning_rate": 1.9074074074074075e-05,
|
| 251 |
+
"loss": 1.0385,
|
| 252 |
+
"step": 825
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.9675925925925926,
|
| 256 |
+
"grad_norm": 16.53839683532715,
|
| 257 |
+
"learning_rate": 1.9652777777777778e-05,
|
| 258 |
+
"loss": 0.7777,
|
| 259 |
+
"step": 850
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.0,
|
| 263 |
+
"eval_accuracy": 0.935546875,
|
| 264 |
+
"eval_loss": 0.2495259791612625,
|
| 265 |
+
"eval_macro_f1": 0.7821479216103883,
|
| 266 |
+
"eval_runtime": 0.9236,
|
| 267 |
+
"eval_samples_per_second": 1663.107,
|
| 268 |
+
"eval_steps_per_second": 103.944,
|
| 269 |
+
"eval_weighted_f1": 0.9310146728313726,
|
| 270 |
+
"step": 864
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.025462962962963,
|
| 274 |
+
"grad_norm": 27.388080596923828,
|
| 275 |
+
"learning_rate": 1.997427983539095e-05,
|
| 276 |
+
"loss": 0.7046,
|
| 277 |
+
"step": 875
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.0833333333333335,
|
| 281 |
+
"grad_norm": 5.5007004737854,
|
| 282 |
+
"learning_rate": 1.9909979423868314e-05,
|
| 283 |
+
"loss": 0.7542,
|
| 284 |
+
"step": 900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.1412037037037037,
|
| 288 |
+
"grad_norm": 28.260902404785156,
|
| 289 |
+
"learning_rate": 1.984567901234568e-05,
|
| 290 |
+
"loss": 0.9262,
|
| 291 |
+
"step": 925
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.199074074074074,
|
| 295 |
+
"grad_norm": 23.344812393188477,
|
| 296 |
+
"learning_rate": 1.9781378600823048e-05,
|
| 297 |
+
"loss": 0.5786,
|
| 298 |
+
"step": 950
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.2569444444444446,
|
| 302 |
+
"grad_norm": 6.03977632522583,
|
| 303 |
+
"learning_rate": 1.9717078189300413e-05,
|
| 304 |
+
"loss": 0.696,
|
| 305 |
+
"step": 975
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.314814814814815,
|
| 309 |
+
"grad_norm": 34.911014556884766,
|
| 310 |
+
"learning_rate": 1.9652777777777778e-05,
|
| 311 |
+
"loss": 0.7489,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.372685185185185,
|
| 316 |
+
"grad_norm": 65.21478271484375,
|
| 317 |
+
"learning_rate": 1.9588477366255147e-05,
|
| 318 |
+
"loss": 0.7699,
|
| 319 |
+
"step": 1025
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.4305555555555554,
|
| 323 |
+
"grad_norm": 8.82874870300293,
|
| 324 |
+
"learning_rate": 1.9524176954732512e-05,
|
| 325 |
+
"loss": 0.7235,
|
| 326 |
+
"step": 1050
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.488425925925926,
|
| 330 |
+
"grad_norm": 33.981224060058594,
|
| 331 |
+
"learning_rate": 1.945987654320988e-05,
|
| 332 |
+
"loss": 0.7552,
|
| 333 |
+
"step": 1075
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.5462962962962963,
|
| 337 |
+
"grad_norm": 8.756223678588867,
|
| 338 |
+
"learning_rate": 1.9395576131687242e-05,
|
| 339 |
+
"loss": 0.6889,
|
| 340 |
+
"step": 1100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.6041666666666665,
|
| 344 |
+
"grad_norm": 19.163267135620117,
|
| 345 |
+
"learning_rate": 1.933127572016461e-05,
|
| 346 |
+
"loss": 0.6557,
|
| 347 |
+
"step": 1125
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.662037037037037,
|
| 351 |
+
"grad_norm": 28.43830108642578,
|
| 352 |
+
"learning_rate": 1.926697530864198e-05,
|
| 353 |
+
"loss": 0.7351,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.7199074074074074,
|
| 358 |
+
"grad_norm": 62.78884506225586,
|
| 359 |
+
"learning_rate": 1.920267489711934e-05,
|
| 360 |
+
"loss": 0.7455,
|
| 361 |
+
"step": 1175
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.7777777777777777,
|
| 365 |
+
"grad_norm": 62.24296569824219,
|
| 366 |
+
"learning_rate": 1.913837448559671e-05,
|
| 367 |
+
"loss": 0.8906,
|
| 368 |
+
"step": 1200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.835648148148148,
|
| 372 |
+
"grad_norm": 13.739839553833008,
|
| 373 |
+
"learning_rate": 1.9074074074074075e-05,
|
| 374 |
+
"loss": 0.5964,
|
| 375 |
+
"step": 1225
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.8935185185185186,
|
| 379 |
+
"grad_norm": 14.087162971496582,
|
| 380 |
+
"learning_rate": 1.9009773662551443e-05,
|
| 381 |
+
"loss": 0.8638,
|
| 382 |
+
"step": 1250
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.951388888888889,
|
| 386 |
+
"grad_norm": 39.41259002685547,
|
| 387 |
+
"learning_rate": 1.8945473251028808e-05,
|
| 388 |
+
"loss": 0.6795,
|
| 389 |
+
"step": 1275
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.0,
|
| 393 |
+
"eval_accuracy": 0.9466145833333334,
|
| 394 |
+
"eval_loss": 0.20291924476623535,
|
| 395 |
+
"eval_macro_f1": 0.8094894985910427,
|
| 396 |
+
"eval_runtime": 0.9276,
|
| 397 |
+
"eval_samples_per_second": 1655.957,
|
| 398 |
+
"eval_steps_per_second": 103.497,
|
| 399 |
+
"eval_weighted_f1": 0.944308993601631,
|
| 400 |
+
"step": 1296
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.009259259259259,
|
| 404 |
+
"grad_norm": 12.844809532165527,
|
| 405 |
+
"learning_rate": 1.8881172839506173e-05,
|
| 406 |
+
"loss": 0.6876,
|
| 407 |
+
"step": 1300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.0671296296296298,
|
| 411 |
+
"grad_norm": 98.31945037841797,
|
| 412 |
+
"learning_rate": 1.8816872427983542e-05,
|
| 413 |
+
"loss": 0.5382,
|
| 414 |
+
"step": 1325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.125,
|
| 418 |
+
"grad_norm": 49.334259033203125,
|
| 419 |
+
"learning_rate": 1.8752572016460907e-05,
|
| 420 |
+
"loss": 0.7285,
|
| 421 |
+
"step": 1350
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.1828703703703702,
|
| 425 |
+
"grad_norm": 4.6014862060546875,
|
| 426 |
+
"learning_rate": 1.8688271604938272e-05,
|
| 427 |
+
"loss": 0.4937,
|
| 428 |
+
"step": 1375
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.240740740740741,
|
| 432 |
+
"grad_norm": 12.539897918701172,
|
| 433 |
+
"learning_rate": 1.862397119341564e-05,
|
| 434 |
+
"loss": 0.8402,
|
| 435 |
+
"step": 1400
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.298611111111111,
|
| 439 |
+
"grad_norm": 2.0339972972869873,
|
| 440 |
+
"learning_rate": 1.8559670781893006e-05,
|
| 441 |
+
"loss": 0.5483,
|
| 442 |
+
"step": 1425
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.3564814814814814,
|
| 446 |
+
"grad_norm": 41.038936614990234,
|
| 447 |
+
"learning_rate": 1.849537037037037e-05,
|
| 448 |
+
"loss": 0.8069,
|
| 449 |
+
"step": 1450
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.414351851851852,
|
| 453 |
+
"grad_norm": 41.195003509521484,
|
| 454 |
+
"learning_rate": 1.843106995884774e-05,
|
| 455 |
+
"loss": 0.6507,
|
| 456 |
+
"step": 1475
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.4722222222222223,
|
| 460 |
+
"grad_norm": 48.448001861572266,
|
| 461 |
+
"learning_rate": 1.8366769547325105e-05,
|
| 462 |
+
"loss": 0.6874,
|
| 463 |
+
"step": 1500
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.5300925925925926,
|
| 467 |
+
"grad_norm": 5.450769424438477,
|
| 468 |
+
"learning_rate": 1.830246913580247e-05,
|
| 469 |
+
"loss": 0.5881,
|
| 470 |
+
"step": 1525
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.587962962962963,
|
| 474 |
+
"grad_norm": 25.71689796447754,
|
| 475 |
+
"learning_rate": 1.8238168724279838e-05,
|
| 476 |
+
"loss": 0.6909,
|
| 477 |
+
"step": 1550
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.6458333333333335,
|
| 481 |
+
"grad_norm": 31.79206657409668,
|
| 482 |
+
"learning_rate": 1.8173868312757203e-05,
|
| 483 |
+
"loss": 0.6237,
|
| 484 |
+
"step": 1575
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.7037037037037037,
|
| 488 |
+
"grad_norm": 1.6047478914260864,
|
| 489 |
+
"learning_rate": 1.8109567901234572e-05,
|
| 490 |
+
"loss": 0.5917,
|
| 491 |
+
"step": 1600
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.761574074074074,
|
| 495 |
+
"grad_norm": 7.936718940734863,
|
| 496 |
+
"learning_rate": 1.8045267489711934e-05,
|
| 497 |
+
"loss": 0.5632,
|
| 498 |
+
"step": 1625
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.8194444444444446,
|
| 502 |
+
"grad_norm": 4.4144721031188965,
|
| 503 |
+
"learning_rate": 1.7980967078189302e-05,
|
| 504 |
+
"loss": 0.6438,
|
| 505 |
+
"step": 1650
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.877314814814815,
|
| 509 |
+
"grad_norm": 49.435665130615234,
|
| 510 |
+
"learning_rate": 1.7916666666666667e-05,
|
| 511 |
+
"loss": 0.653,
|
| 512 |
+
"step": 1675
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.935185185185185,
|
| 516 |
+
"grad_norm": 18.015880584716797,
|
| 517 |
+
"learning_rate": 1.7852366255144032e-05,
|
| 518 |
+
"loss": 0.5673,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.9930555555555554,
|
| 523 |
+
"grad_norm": 35.0489387512207,
|
| 524 |
+
"learning_rate": 1.77880658436214e-05,
|
| 525 |
+
"loss": 0.6615,
|
| 526 |
+
"step": 1725
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 4.0,
|
| 530 |
+
"eval_accuracy": 0.9466145833333334,
|
| 531 |
+
"eval_loss": 0.1876983791589737,
|
| 532 |
+
"eval_macro_f1": 0.8155416138247494,
|
| 533 |
+
"eval_runtime": 0.8888,
|
| 534 |
+
"eval_samples_per_second": 1728.101,
|
| 535 |
+
"eval_steps_per_second": 108.006,
|
| 536 |
+
"eval_weighted_f1": 0.9445463115930769,
|
| 537 |
+
"step": 1728
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.050925925925926,
|
| 541 |
+
"grad_norm": 100.41817474365234,
|
| 542 |
+
"learning_rate": 1.7723765432098766e-05,
|
| 543 |
+
"loss": 0.4836,
|
| 544 |
+
"step": 1750
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.108796296296297,
|
| 548 |
+
"grad_norm": 55.09341049194336,
|
| 549 |
+
"learning_rate": 1.7659465020576135e-05,
|
| 550 |
+
"loss": 0.5459,
|
| 551 |
+
"step": 1775
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.166666666666667,
|
| 555 |
+
"grad_norm": 128.3369903564453,
|
| 556 |
+
"learning_rate": 1.75951646090535e-05,
|
| 557 |
+
"loss": 0.4034,
|
| 558 |
+
"step": 1800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.224537037037037,
|
| 562 |
+
"grad_norm": 14.89205551147461,
|
| 563 |
+
"learning_rate": 1.7530864197530865e-05,
|
| 564 |
+
"loss": 0.4371,
|
| 565 |
+
"step": 1825
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 4.282407407407407,
|
| 569 |
+
"grad_norm": 50.4736213684082,
|
| 570 |
+
"learning_rate": 1.7466563786008233e-05,
|
| 571 |
+
"loss": 0.5345,
|
| 572 |
+
"step": 1850
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.340277777777778,
|
| 576 |
+
"grad_norm": 38.82111740112305,
|
| 577 |
+
"learning_rate": 1.74022633744856e-05,
|
| 578 |
+
"loss": 0.6473,
|
| 579 |
+
"step": 1875
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.398148148148148,
|
| 583 |
+
"grad_norm": 24.182580947875977,
|
| 584 |
+
"learning_rate": 1.7337962962962964e-05,
|
| 585 |
+
"loss": 0.6654,
|
| 586 |
+
"step": 1900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 4.456018518518518,
|
| 590 |
+
"grad_norm": 97.2868881225586,
|
| 591 |
+
"learning_rate": 1.7273662551440332e-05,
|
| 592 |
+
"loss": 0.584,
|
| 593 |
+
"step": 1925
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.513888888888889,
|
| 597 |
+
"grad_norm": 8.808185577392578,
|
| 598 |
+
"learning_rate": 1.7209362139917697e-05,
|
| 599 |
+
"loss": 0.5251,
|
| 600 |
+
"step": 1950
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.5717592592592595,
|
| 604 |
+
"grad_norm": 27.569793701171875,
|
| 605 |
+
"learning_rate": 1.7145061728395063e-05,
|
| 606 |
+
"loss": 0.3564,
|
| 607 |
+
"step": 1975
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 4.62962962962963,
|
| 611 |
+
"grad_norm": 27.74687957763672,
|
| 612 |
+
"learning_rate": 1.708076131687243e-05,
|
| 613 |
+
"loss": 0.4905,
|
| 614 |
+
"step": 2000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.6875,
|
| 618 |
+
"grad_norm": 35.00214385986328,
|
| 619 |
+
"learning_rate": 1.7016460905349796e-05,
|
| 620 |
+
"loss": 0.5122,
|
| 621 |
+
"step": 2025
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.74537037037037,
|
| 625 |
+
"grad_norm": 53.33663558959961,
|
| 626 |
+
"learning_rate": 1.695216049382716e-05,
|
| 627 |
+
"loss": 0.622,
|
| 628 |
+
"step": 2050
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.8032407407407405,
|
| 632 |
+
"grad_norm": 9.86314582824707,
|
| 633 |
+
"learning_rate": 1.6887860082304527e-05,
|
| 634 |
+
"loss": 0.6322,
|
| 635 |
+
"step": 2075
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.861111111111111,
|
| 639 |
+
"grad_norm": 67.70832061767578,
|
| 640 |
+
"learning_rate": 1.6823559670781895e-05,
|
| 641 |
+
"loss": 0.5603,
|
| 642 |
+
"step": 2100
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.918981481481482,
|
| 646 |
+
"grad_norm": 0.4869685173034668,
|
| 647 |
+
"learning_rate": 1.675925925925926e-05,
|
| 648 |
+
"loss": 0.4237,
|
| 649 |
+
"step": 2125
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.976851851851852,
|
| 653 |
+
"grad_norm": 174.91839599609375,
|
| 654 |
+
"learning_rate": 1.6694958847736625e-05,
|
| 655 |
+
"loss": 0.4862,
|
| 656 |
+
"step": 2150
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 5.0,
|
| 660 |
+
"eval_accuracy": 0.9466145833333334,
|
| 661 |
+
"eval_loss": 0.26453375816345215,
|
| 662 |
+
"eval_macro_f1": 0.8115004204033994,
|
| 663 |
+
"eval_runtime": 0.9254,
|
| 664 |
+
"eval_samples_per_second": 1659.871,
|
| 665 |
+
"eval_steps_per_second": 103.742,
|
| 666 |
+
"eval_weighted_f1": 0.9430780024122196,
|
| 667 |
+
"step": 2160
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 5.034722222222222,
|
| 671 |
+
"grad_norm": 3.088663101196289,
|
| 672 |
+
"learning_rate": 1.6630658436213994e-05,
|
| 673 |
+
"loss": 0.4728,
|
| 674 |
+
"step": 2175
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.092592592592593,
|
| 678 |
+
"grad_norm": 81.90543365478516,
|
| 679 |
+
"learning_rate": 1.656635802469136e-05,
|
| 680 |
+
"loss": 0.3981,
|
| 681 |
+
"step": 2200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 5.150462962962963,
|
| 685 |
+
"grad_norm": 1.5800690650939941,
|
| 686 |
+
"learning_rate": 1.6502057613168724e-05,
|
| 687 |
+
"loss": 0.1689,
|
| 688 |
+
"step": 2225
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 5.208333333333333,
|
| 692 |
+
"grad_norm": 2.941277503967285,
|
| 693 |
+
"learning_rate": 1.6437757201646093e-05,
|
| 694 |
+
"loss": 0.4084,
|
| 695 |
+
"step": 2250
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 5.266203703703704,
|
| 699 |
+
"grad_norm": 33.7673454284668,
|
| 700 |
+
"learning_rate": 1.6373456790123458e-05,
|
| 701 |
+
"loss": 0.4078,
|
| 702 |
+
"step": 2275
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 5.324074074074074,
|
| 706 |
+
"grad_norm": 2.803130626678467,
|
| 707 |
+
"learning_rate": 1.6309156378600823e-05,
|
| 708 |
+
"loss": 0.3334,
|
| 709 |
+
"step": 2300
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 5.381944444444445,
|
| 713 |
+
"grad_norm": 144.31961059570312,
|
| 714 |
+
"learning_rate": 1.624485596707819e-05,
|
| 715 |
+
"loss": 0.2874,
|
| 716 |
+
"step": 2325
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 5.439814814814815,
|
| 720 |
+
"grad_norm": 3.18941330909729,
|
| 721 |
+
"learning_rate": 1.6180555555555557e-05,
|
| 722 |
+
"loss": 0.6188,
|
| 723 |
+
"step": 2350
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.497685185185185,
|
| 727 |
+
"grad_norm": 26.587751388549805,
|
| 728 |
+
"learning_rate": 1.6116255144032925e-05,
|
| 729 |
+
"loss": 0.5596,
|
| 730 |
+
"step": 2375
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 5.555555555555555,
|
| 734 |
+
"grad_norm": 101.47644805908203,
|
| 735 |
+
"learning_rate": 1.605195473251029e-05,
|
| 736 |
+
"loss": 0.4598,
|
| 737 |
+
"step": 2400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 5.613425925925926,
|
| 741 |
+
"grad_norm": 49.117889404296875,
|
| 742 |
+
"learning_rate": 1.5987654320987655e-05,
|
| 743 |
+
"loss": 0.5003,
|
| 744 |
+
"step": 2425
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.671296296296296,
|
| 748 |
+
"grad_norm": 40.722389221191406,
|
| 749 |
+
"learning_rate": 1.5923353909465024e-05,
|
| 750 |
+
"loss": 0.5783,
|
| 751 |
+
"step": 2450
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 5.729166666666667,
|
| 755 |
+
"grad_norm": 1.4265937805175781,
|
| 756 |
+
"learning_rate": 1.5859053497942386e-05,
|
| 757 |
+
"loss": 0.5613,
|
| 758 |
+
"step": 2475
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 5.787037037037037,
|
| 762 |
+
"grad_norm": 25.484758377075195,
|
| 763 |
+
"learning_rate": 1.5794753086419754e-05,
|
| 764 |
+
"loss": 0.4909,
|
| 765 |
+
"step": 2500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 5.844907407407407,
|
| 769 |
+
"grad_norm": 29.874347686767578,
|
| 770 |
+
"learning_rate": 1.573045267489712e-05,
|
| 771 |
+
"loss": 0.4401,
|
| 772 |
+
"step": 2525
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 5.902777777777778,
|
| 776 |
+
"grad_norm": 8.134950637817383,
|
| 777 |
+
"learning_rate": 1.5666152263374488e-05,
|
| 778 |
+
"loss": 0.506,
|
| 779 |
+
"step": 2550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 5.960648148148148,
|
| 783 |
+
"grad_norm": 38.01759338378906,
|
| 784 |
+
"learning_rate": 1.5601851851851853e-05,
|
| 785 |
+
"loss": 0.4226,
|
| 786 |
+
"step": 2575
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.0,
|
| 790 |
+
"eval_accuracy": 0.9453125,
|
| 791 |
+
"eval_loss": 0.2655061185359955,
|
| 792 |
+
"eval_macro_f1": 0.826900458402438,
|
| 793 |
+
"eval_runtime": 0.9139,
|
| 794 |
+
"eval_samples_per_second": 1680.704,
|
| 795 |
+
"eval_steps_per_second": 105.044,
|
| 796 |
+
"eval_weighted_f1": 0.9445571039922019,
|
| 797 |
+
"step": 2592
|
| 798 |
+
}
|
| 799 |
+
],
|
| 800 |
+
"logging_steps": 25,
|
| 801 |
+
"max_steps": 8640,
|
| 802 |
+
"num_input_tokens_seen": 0,
|
| 803 |
+
"num_train_epochs": 20,
|
| 804 |
+
"save_steps": 500,
|
| 805 |
+
"stateful_callbacks": {
|
| 806 |
+
"EarlyStoppingCallback": {
|
| 807 |
+
"args": {
|
| 808 |
+
"early_stopping_patience": 3,
|
| 809 |
+
"early_stopping_threshold": 0.0
|
| 810 |
+
},
|
| 811 |
+
"attributes": {
|
| 812 |
+
"early_stopping_patience_counter": 0
|
| 813 |
+
}
|
| 814 |
+
},
|
| 815 |
+
"TrainerControl": {
|
| 816 |
+
"args": {
|
| 817 |
+
"should_epoch_stop": false,
|
| 818 |
+
"should_evaluate": false,
|
| 819 |
+
"should_log": false,
|
| 820 |
+
"should_save": true,
|
| 821 |
+
"should_training_stop": false
|
| 822 |
+
},
|
| 823 |
+
"attributes": {}
|
| 824 |
+
}
|
| 825 |
+
},
|
| 826 |
+
"total_flos": 0.0,
|
| 827 |
+
"train_batch_size": 8,
|
| 828 |
+
"trial_name": null,
|
| 829 |
+
"trial_params": null
|
| 830 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-3888/trainer_state.json
ADDED
|
@@ -0,0 +1,1227 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2592,
|
| 3 |
+
"best_metric": 0.826900458402438,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-uit_vsfc-bamibert-topic-domain-02-s44-20260827T163745Z-b6645c77/trainer/checkpoint-2592",
|
| 5 |
+
"epoch": 9.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3888,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.05787037037037037,
|
| 14 |
+
"grad_norm": 30.672374725341797,
|
| 15 |
+
"learning_rate": 5.555555555555555e-07,
|
| 16 |
+
"loss": 4.2569,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.11574074074074074,
|
| 21 |
+
"grad_norm": 28.60749053955078,
|
| 22 |
+
"learning_rate": 1.1342592592592594e-06,
|
| 23 |
+
"loss": 4.0786,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1736111111111111,
|
| 28 |
+
"grad_norm": 34.10677719116211,
|
| 29 |
+
"learning_rate": 1.7129629629629632e-06,
|
| 30 |
+
"loss": 3.7466,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.23148148148148148,
|
| 35 |
+
"grad_norm": 16.774616241455078,
|
| 36 |
+
"learning_rate": 2.2916666666666666e-06,
|
| 37 |
+
"loss": 3.4551,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.28935185185185186,
|
| 42 |
+
"grad_norm": 19.944089889526367,
|
| 43 |
+
"learning_rate": 2.8703703703703706e-06,
|
| 44 |
+
"loss": 3.2359,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3472222222222222,
|
| 49 |
+
"grad_norm": 20.603628158569336,
|
| 50 |
+
"learning_rate": 3.449074074074074e-06,
|
| 51 |
+
"loss": 3.1431,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4050925925925926,
|
| 56 |
+
"grad_norm": 28.288143157958984,
|
| 57 |
+
"learning_rate": 4.027777777777779e-06,
|
| 58 |
+
"loss": 3.0682,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.46296296296296297,
|
| 63 |
+
"grad_norm": 42.422584533691406,
|
| 64 |
+
"learning_rate": 4.606481481481481e-06,
|
| 65 |
+
"loss": 2.4462,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5208333333333334,
|
| 70 |
+
"grad_norm": 65.8946762084961,
|
| 71 |
+
"learning_rate": 5.185185185185185e-06,
|
| 72 |
+
"loss": 1.9385,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5787037037037037,
|
| 77 |
+
"grad_norm": 93.30895233154297,
|
| 78 |
+
"learning_rate": 5.7638888888888886e-06,
|
| 79 |
+
"loss": 1.6113,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6365740740740741,
|
| 84 |
+
"grad_norm": 66.67131042480469,
|
| 85 |
+
"learning_rate": 6.342592592592594e-06,
|
| 86 |
+
"loss": 1.3487,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6944444444444444,
|
| 91 |
+
"grad_norm": 25.705554962158203,
|
| 92 |
+
"learning_rate": 6.9212962962962974e-06,
|
| 93 |
+
"loss": 1.357,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.7523148148148148,
|
| 98 |
+
"grad_norm": 80.34606170654297,
|
| 99 |
+
"learning_rate": 7.500000000000001e-06,
|
| 100 |
+
"loss": 1.198,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8101851851851852,
|
| 105 |
+
"grad_norm": 46.074378967285156,
|
| 106 |
+
"learning_rate": 8.078703703703705e-06,
|
| 107 |
+
"loss": 1.0508,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.8680555555555556,
|
| 112 |
+
"grad_norm": 23.091442108154297,
|
| 113 |
+
"learning_rate": 8.657407407407408e-06,
|
| 114 |
+
"loss": 1.1129,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.9259259259259259,
|
| 119 |
+
"grad_norm": 24.728858947753906,
|
| 120 |
+
"learning_rate": 9.236111111111112e-06,
|
| 121 |
+
"loss": 1.3786,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.9837962962962963,
|
| 126 |
+
"grad_norm": 7.195851802825928,
|
| 127 |
+
"learning_rate": 9.814814814814815e-06,
|
| 128 |
+
"loss": 1.0689,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_accuracy": 0.9283854166666666,
|
| 134 |
+
"eval_loss": 0.255921870470047,
|
| 135 |
+
"eval_macro_f1": 0.6285352413936267,
|
| 136 |
+
"eval_runtime": 0.9269,
|
| 137 |
+
"eval_samples_per_second": 1657.096,
|
| 138 |
+
"eval_steps_per_second": 103.569,
|
| 139 |
+
"eval_weighted_f1": 0.9139611830188414,
|
| 140 |
+
"step": 432
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0416666666666667,
|
| 144 |
+
"grad_norm": 24.38639259338379,
|
| 145 |
+
"learning_rate": 1.0393518518518519e-05,
|
| 146 |
+
"loss": 0.9738,
|
| 147 |
+
"step": 450
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.099537037037037,
|
| 151 |
+
"grad_norm": 22.60640525817871,
|
| 152 |
+
"learning_rate": 1.0972222222222224e-05,
|
| 153 |
+
"loss": 1.1063,
|
| 154 |
+
"step": 475
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.1574074074074074,
|
| 158 |
+
"grad_norm": 48.40523147583008,
|
| 159 |
+
"learning_rate": 1.1550925925925926e-05,
|
| 160 |
+
"loss": 0.8008,
|
| 161 |
+
"step": 500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.2152777777777777,
|
| 165 |
+
"grad_norm": 66.28334045410156,
|
| 166 |
+
"learning_rate": 1.2129629629629631e-05,
|
| 167 |
+
"loss": 0.9174,
|
| 168 |
+
"step": 525
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.2731481481481481,
|
| 172 |
+
"grad_norm": 77.04571533203125,
|
| 173 |
+
"learning_rate": 1.2708333333333333e-05,
|
| 174 |
+
"loss": 1.1044,
|
| 175 |
+
"step": 550
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.3310185185185186,
|
| 179 |
+
"grad_norm": 13.086089134216309,
|
| 180 |
+
"learning_rate": 1.3287037037037039e-05,
|
| 181 |
+
"loss": 1.0311,
|
| 182 |
+
"step": 575
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.3888888888888888,
|
| 186 |
+
"grad_norm": 124.03707885742188,
|
| 187 |
+
"learning_rate": 1.3865740740740742e-05,
|
| 188 |
+
"loss": 0.9336,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.4467592592592593,
|
| 193 |
+
"grad_norm": 27.15654945373535,
|
| 194 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 195 |
+
"loss": 1.0349,
|
| 196 |
+
"step": 625
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.5046296296296298,
|
| 200 |
+
"grad_norm": 6.650602340698242,
|
| 201 |
+
"learning_rate": 1.502314814814815e-05,
|
| 202 |
+
"loss": 0.8483,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.5625,
|
| 207 |
+
"grad_norm": 7.203736782073975,
|
| 208 |
+
"learning_rate": 1.5601851851851853e-05,
|
| 209 |
+
"loss": 0.9895,
|
| 210 |
+
"step": 675
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.6203703703703702,
|
| 214 |
+
"grad_norm": 38.05658721923828,
|
| 215 |
+
"learning_rate": 1.6180555555555557e-05,
|
| 216 |
+
"loss": 0.8598,
|
| 217 |
+
"step": 700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.6782407407407407,
|
| 221 |
+
"grad_norm": 264.2079772949219,
|
| 222 |
+
"learning_rate": 1.675925925925926e-05,
|
| 223 |
+
"loss": 0.8142,
|
| 224 |
+
"step": 725
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.7361111111111112,
|
| 228 |
+
"grad_norm": 30.365806579589844,
|
| 229 |
+
"learning_rate": 1.7337962962962964e-05,
|
| 230 |
+
"loss": 1.0979,
|
| 231 |
+
"step": 750
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.7939814814814814,
|
| 235 |
+
"grad_norm": 1.4746909141540527,
|
| 236 |
+
"learning_rate": 1.7916666666666667e-05,
|
| 237 |
+
"loss": 0.7108,
|
| 238 |
+
"step": 775
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.8518518518518519,
|
| 242 |
+
"grad_norm": 103.497314453125,
|
| 243 |
+
"learning_rate": 1.849537037037037e-05,
|
| 244 |
+
"loss": 1.0016,
|
| 245 |
+
"step": 800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.9097222222222223,
|
| 249 |
+
"grad_norm": 68.68548583984375,
|
| 250 |
+
"learning_rate": 1.9074074074074075e-05,
|
| 251 |
+
"loss": 1.0385,
|
| 252 |
+
"step": 825
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.9675925925925926,
|
| 256 |
+
"grad_norm": 16.53839683532715,
|
| 257 |
+
"learning_rate": 1.9652777777777778e-05,
|
| 258 |
+
"loss": 0.7777,
|
| 259 |
+
"step": 850
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.0,
|
| 263 |
+
"eval_accuracy": 0.935546875,
|
| 264 |
+
"eval_loss": 0.2495259791612625,
|
| 265 |
+
"eval_macro_f1": 0.7821479216103883,
|
| 266 |
+
"eval_runtime": 0.9236,
|
| 267 |
+
"eval_samples_per_second": 1663.107,
|
| 268 |
+
"eval_steps_per_second": 103.944,
|
| 269 |
+
"eval_weighted_f1": 0.9310146728313726,
|
| 270 |
+
"step": 864
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.025462962962963,
|
| 274 |
+
"grad_norm": 27.388080596923828,
|
| 275 |
+
"learning_rate": 1.997427983539095e-05,
|
| 276 |
+
"loss": 0.7046,
|
| 277 |
+
"step": 875
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.0833333333333335,
|
| 281 |
+
"grad_norm": 5.5007004737854,
|
| 282 |
+
"learning_rate": 1.9909979423868314e-05,
|
| 283 |
+
"loss": 0.7542,
|
| 284 |
+
"step": 900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.1412037037037037,
|
| 288 |
+
"grad_norm": 28.260902404785156,
|
| 289 |
+
"learning_rate": 1.984567901234568e-05,
|
| 290 |
+
"loss": 0.9262,
|
| 291 |
+
"step": 925
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.199074074074074,
|
| 295 |
+
"grad_norm": 23.344812393188477,
|
| 296 |
+
"learning_rate": 1.9781378600823048e-05,
|
| 297 |
+
"loss": 0.5786,
|
| 298 |
+
"step": 950
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.2569444444444446,
|
| 302 |
+
"grad_norm": 6.03977632522583,
|
| 303 |
+
"learning_rate": 1.9717078189300413e-05,
|
| 304 |
+
"loss": 0.696,
|
| 305 |
+
"step": 975
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.314814814814815,
|
| 309 |
+
"grad_norm": 34.911014556884766,
|
| 310 |
+
"learning_rate": 1.9652777777777778e-05,
|
| 311 |
+
"loss": 0.7489,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.372685185185185,
|
| 316 |
+
"grad_norm": 65.21478271484375,
|
| 317 |
+
"learning_rate": 1.9588477366255147e-05,
|
| 318 |
+
"loss": 0.7699,
|
| 319 |
+
"step": 1025
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.4305555555555554,
|
| 323 |
+
"grad_norm": 8.82874870300293,
|
| 324 |
+
"learning_rate": 1.9524176954732512e-05,
|
| 325 |
+
"loss": 0.7235,
|
| 326 |
+
"step": 1050
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.488425925925926,
|
| 330 |
+
"grad_norm": 33.981224060058594,
|
| 331 |
+
"learning_rate": 1.945987654320988e-05,
|
| 332 |
+
"loss": 0.7552,
|
| 333 |
+
"step": 1075
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.5462962962962963,
|
| 337 |
+
"grad_norm": 8.756223678588867,
|
| 338 |
+
"learning_rate": 1.9395576131687242e-05,
|
| 339 |
+
"loss": 0.6889,
|
| 340 |
+
"step": 1100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.6041666666666665,
|
| 344 |
+
"grad_norm": 19.163267135620117,
|
| 345 |
+
"learning_rate": 1.933127572016461e-05,
|
| 346 |
+
"loss": 0.6557,
|
| 347 |
+
"step": 1125
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.662037037037037,
|
| 351 |
+
"grad_norm": 28.43830108642578,
|
| 352 |
+
"learning_rate": 1.926697530864198e-05,
|
| 353 |
+
"loss": 0.7351,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.7199074074074074,
|
| 358 |
+
"grad_norm": 62.78884506225586,
|
| 359 |
+
"learning_rate": 1.920267489711934e-05,
|
| 360 |
+
"loss": 0.7455,
|
| 361 |
+
"step": 1175
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.7777777777777777,
|
| 365 |
+
"grad_norm": 62.24296569824219,
|
| 366 |
+
"learning_rate": 1.913837448559671e-05,
|
| 367 |
+
"loss": 0.8906,
|
| 368 |
+
"step": 1200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.835648148148148,
|
| 372 |
+
"grad_norm": 13.739839553833008,
|
| 373 |
+
"learning_rate": 1.9074074074074075e-05,
|
| 374 |
+
"loss": 0.5964,
|
| 375 |
+
"step": 1225
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.8935185185185186,
|
| 379 |
+
"grad_norm": 14.087162971496582,
|
| 380 |
+
"learning_rate": 1.9009773662551443e-05,
|
| 381 |
+
"loss": 0.8638,
|
| 382 |
+
"step": 1250
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.951388888888889,
|
| 386 |
+
"grad_norm": 39.41259002685547,
|
| 387 |
+
"learning_rate": 1.8945473251028808e-05,
|
| 388 |
+
"loss": 0.6795,
|
| 389 |
+
"step": 1275
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.0,
|
| 393 |
+
"eval_accuracy": 0.9466145833333334,
|
| 394 |
+
"eval_loss": 0.20291924476623535,
|
| 395 |
+
"eval_macro_f1": 0.8094894985910427,
|
| 396 |
+
"eval_runtime": 0.9276,
|
| 397 |
+
"eval_samples_per_second": 1655.957,
|
| 398 |
+
"eval_steps_per_second": 103.497,
|
| 399 |
+
"eval_weighted_f1": 0.944308993601631,
|
| 400 |
+
"step": 1296
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.009259259259259,
|
| 404 |
+
"grad_norm": 12.844809532165527,
|
| 405 |
+
"learning_rate": 1.8881172839506173e-05,
|
| 406 |
+
"loss": 0.6876,
|
| 407 |
+
"step": 1300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.0671296296296298,
|
| 411 |
+
"grad_norm": 98.31945037841797,
|
| 412 |
+
"learning_rate": 1.8816872427983542e-05,
|
| 413 |
+
"loss": 0.5382,
|
| 414 |
+
"step": 1325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.125,
|
| 418 |
+
"grad_norm": 49.334259033203125,
|
| 419 |
+
"learning_rate": 1.8752572016460907e-05,
|
| 420 |
+
"loss": 0.7285,
|
| 421 |
+
"step": 1350
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.1828703703703702,
|
| 425 |
+
"grad_norm": 4.6014862060546875,
|
| 426 |
+
"learning_rate": 1.8688271604938272e-05,
|
| 427 |
+
"loss": 0.4937,
|
| 428 |
+
"step": 1375
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.240740740740741,
|
| 432 |
+
"grad_norm": 12.539897918701172,
|
| 433 |
+
"learning_rate": 1.862397119341564e-05,
|
| 434 |
+
"loss": 0.8402,
|
| 435 |
+
"step": 1400
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.298611111111111,
|
| 439 |
+
"grad_norm": 2.0339972972869873,
|
| 440 |
+
"learning_rate": 1.8559670781893006e-05,
|
| 441 |
+
"loss": 0.5483,
|
| 442 |
+
"step": 1425
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.3564814814814814,
|
| 446 |
+
"grad_norm": 41.038936614990234,
|
| 447 |
+
"learning_rate": 1.849537037037037e-05,
|
| 448 |
+
"loss": 0.8069,
|
| 449 |
+
"step": 1450
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.414351851851852,
|
| 453 |
+
"grad_norm": 41.195003509521484,
|
| 454 |
+
"learning_rate": 1.843106995884774e-05,
|
| 455 |
+
"loss": 0.6507,
|
| 456 |
+
"step": 1475
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.4722222222222223,
|
| 460 |
+
"grad_norm": 48.448001861572266,
|
| 461 |
+
"learning_rate": 1.8366769547325105e-05,
|
| 462 |
+
"loss": 0.6874,
|
| 463 |
+
"step": 1500
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.5300925925925926,
|
| 467 |
+
"grad_norm": 5.450769424438477,
|
| 468 |
+
"learning_rate": 1.830246913580247e-05,
|
| 469 |
+
"loss": 0.5881,
|
| 470 |
+
"step": 1525
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.587962962962963,
|
| 474 |
+
"grad_norm": 25.71689796447754,
|
| 475 |
+
"learning_rate": 1.8238168724279838e-05,
|
| 476 |
+
"loss": 0.6909,
|
| 477 |
+
"step": 1550
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.6458333333333335,
|
| 481 |
+
"grad_norm": 31.79206657409668,
|
| 482 |
+
"learning_rate": 1.8173868312757203e-05,
|
| 483 |
+
"loss": 0.6237,
|
| 484 |
+
"step": 1575
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.7037037037037037,
|
| 488 |
+
"grad_norm": 1.6047478914260864,
|
| 489 |
+
"learning_rate": 1.8109567901234572e-05,
|
| 490 |
+
"loss": 0.5917,
|
| 491 |
+
"step": 1600
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.761574074074074,
|
| 495 |
+
"grad_norm": 7.936718940734863,
|
| 496 |
+
"learning_rate": 1.8045267489711934e-05,
|
| 497 |
+
"loss": 0.5632,
|
| 498 |
+
"step": 1625
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.8194444444444446,
|
| 502 |
+
"grad_norm": 4.4144721031188965,
|
| 503 |
+
"learning_rate": 1.7980967078189302e-05,
|
| 504 |
+
"loss": 0.6438,
|
| 505 |
+
"step": 1650
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.877314814814815,
|
| 509 |
+
"grad_norm": 49.435665130615234,
|
| 510 |
+
"learning_rate": 1.7916666666666667e-05,
|
| 511 |
+
"loss": 0.653,
|
| 512 |
+
"step": 1675
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.935185185185185,
|
| 516 |
+
"grad_norm": 18.015880584716797,
|
| 517 |
+
"learning_rate": 1.7852366255144032e-05,
|
| 518 |
+
"loss": 0.5673,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.9930555555555554,
|
| 523 |
+
"grad_norm": 35.0489387512207,
|
| 524 |
+
"learning_rate": 1.77880658436214e-05,
|
| 525 |
+
"loss": 0.6615,
|
| 526 |
+
"step": 1725
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 4.0,
|
| 530 |
+
"eval_accuracy": 0.9466145833333334,
|
| 531 |
+
"eval_loss": 0.1876983791589737,
|
| 532 |
+
"eval_macro_f1": 0.8155416138247494,
|
| 533 |
+
"eval_runtime": 0.8888,
|
| 534 |
+
"eval_samples_per_second": 1728.101,
|
| 535 |
+
"eval_steps_per_second": 108.006,
|
| 536 |
+
"eval_weighted_f1": 0.9445463115930769,
|
| 537 |
+
"step": 1728
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.050925925925926,
|
| 541 |
+
"grad_norm": 100.41817474365234,
|
| 542 |
+
"learning_rate": 1.7723765432098766e-05,
|
| 543 |
+
"loss": 0.4836,
|
| 544 |
+
"step": 1750
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.108796296296297,
|
| 548 |
+
"grad_norm": 55.09341049194336,
|
| 549 |
+
"learning_rate": 1.7659465020576135e-05,
|
| 550 |
+
"loss": 0.5459,
|
| 551 |
+
"step": 1775
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.166666666666667,
|
| 555 |
+
"grad_norm": 128.3369903564453,
|
| 556 |
+
"learning_rate": 1.75951646090535e-05,
|
| 557 |
+
"loss": 0.4034,
|
| 558 |
+
"step": 1800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.224537037037037,
|
| 562 |
+
"grad_norm": 14.89205551147461,
|
| 563 |
+
"learning_rate": 1.7530864197530865e-05,
|
| 564 |
+
"loss": 0.4371,
|
| 565 |
+
"step": 1825
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 4.282407407407407,
|
| 569 |
+
"grad_norm": 50.4736213684082,
|
| 570 |
+
"learning_rate": 1.7466563786008233e-05,
|
| 571 |
+
"loss": 0.5345,
|
| 572 |
+
"step": 1850
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.340277777777778,
|
| 576 |
+
"grad_norm": 38.82111740112305,
|
| 577 |
+
"learning_rate": 1.74022633744856e-05,
|
| 578 |
+
"loss": 0.6473,
|
| 579 |
+
"step": 1875
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.398148148148148,
|
| 583 |
+
"grad_norm": 24.182580947875977,
|
| 584 |
+
"learning_rate": 1.7337962962962964e-05,
|
| 585 |
+
"loss": 0.6654,
|
| 586 |
+
"step": 1900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 4.456018518518518,
|
| 590 |
+
"grad_norm": 97.2868881225586,
|
| 591 |
+
"learning_rate": 1.7273662551440332e-05,
|
| 592 |
+
"loss": 0.584,
|
| 593 |
+
"step": 1925
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.513888888888889,
|
| 597 |
+
"grad_norm": 8.808185577392578,
|
| 598 |
+
"learning_rate": 1.7209362139917697e-05,
|
| 599 |
+
"loss": 0.5251,
|
| 600 |
+
"step": 1950
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.5717592592592595,
|
| 604 |
+
"grad_norm": 27.569793701171875,
|
| 605 |
+
"learning_rate": 1.7145061728395063e-05,
|
| 606 |
+
"loss": 0.3564,
|
| 607 |
+
"step": 1975
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 4.62962962962963,
|
| 611 |
+
"grad_norm": 27.74687957763672,
|
| 612 |
+
"learning_rate": 1.708076131687243e-05,
|
| 613 |
+
"loss": 0.4905,
|
| 614 |
+
"step": 2000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.6875,
|
| 618 |
+
"grad_norm": 35.00214385986328,
|
| 619 |
+
"learning_rate": 1.7016460905349796e-05,
|
| 620 |
+
"loss": 0.5122,
|
| 621 |
+
"step": 2025
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.74537037037037,
|
| 625 |
+
"grad_norm": 53.33663558959961,
|
| 626 |
+
"learning_rate": 1.695216049382716e-05,
|
| 627 |
+
"loss": 0.622,
|
| 628 |
+
"step": 2050
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.8032407407407405,
|
| 632 |
+
"grad_norm": 9.86314582824707,
|
| 633 |
+
"learning_rate": 1.6887860082304527e-05,
|
| 634 |
+
"loss": 0.6322,
|
| 635 |
+
"step": 2075
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.861111111111111,
|
| 639 |
+
"grad_norm": 67.70832061767578,
|
| 640 |
+
"learning_rate": 1.6823559670781895e-05,
|
| 641 |
+
"loss": 0.5603,
|
| 642 |
+
"step": 2100
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.918981481481482,
|
| 646 |
+
"grad_norm": 0.4869685173034668,
|
| 647 |
+
"learning_rate": 1.675925925925926e-05,
|
| 648 |
+
"loss": 0.4237,
|
| 649 |
+
"step": 2125
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.976851851851852,
|
| 653 |
+
"grad_norm": 174.91839599609375,
|
| 654 |
+
"learning_rate": 1.6694958847736625e-05,
|
| 655 |
+
"loss": 0.4862,
|
| 656 |
+
"step": 2150
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 5.0,
|
| 660 |
+
"eval_accuracy": 0.9466145833333334,
|
| 661 |
+
"eval_loss": 0.26453375816345215,
|
| 662 |
+
"eval_macro_f1": 0.8115004204033994,
|
| 663 |
+
"eval_runtime": 0.9254,
|
| 664 |
+
"eval_samples_per_second": 1659.871,
|
| 665 |
+
"eval_steps_per_second": 103.742,
|
| 666 |
+
"eval_weighted_f1": 0.9430780024122196,
|
| 667 |
+
"step": 2160
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 5.034722222222222,
|
| 671 |
+
"grad_norm": 3.088663101196289,
|
| 672 |
+
"learning_rate": 1.6630658436213994e-05,
|
| 673 |
+
"loss": 0.4728,
|
| 674 |
+
"step": 2175
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.092592592592593,
|
| 678 |
+
"grad_norm": 81.90543365478516,
|
| 679 |
+
"learning_rate": 1.656635802469136e-05,
|
| 680 |
+
"loss": 0.3981,
|
| 681 |
+
"step": 2200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 5.150462962962963,
|
| 685 |
+
"grad_norm": 1.5800690650939941,
|
| 686 |
+
"learning_rate": 1.6502057613168724e-05,
|
| 687 |
+
"loss": 0.1689,
|
| 688 |
+
"step": 2225
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 5.208333333333333,
|
| 692 |
+
"grad_norm": 2.941277503967285,
|
| 693 |
+
"learning_rate": 1.6437757201646093e-05,
|
| 694 |
+
"loss": 0.4084,
|
| 695 |
+
"step": 2250
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 5.266203703703704,
|
| 699 |
+
"grad_norm": 33.7673454284668,
|
| 700 |
+
"learning_rate": 1.6373456790123458e-05,
|
| 701 |
+
"loss": 0.4078,
|
| 702 |
+
"step": 2275
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 5.324074074074074,
|
| 706 |
+
"grad_norm": 2.803130626678467,
|
| 707 |
+
"learning_rate": 1.6309156378600823e-05,
|
| 708 |
+
"loss": 0.3334,
|
| 709 |
+
"step": 2300
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 5.381944444444445,
|
| 713 |
+
"grad_norm": 144.31961059570312,
|
| 714 |
+
"learning_rate": 1.624485596707819e-05,
|
| 715 |
+
"loss": 0.2874,
|
| 716 |
+
"step": 2325
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 5.439814814814815,
|
| 720 |
+
"grad_norm": 3.18941330909729,
|
| 721 |
+
"learning_rate": 1.6180555555555557e-05,
|
| 722 |
+
"loss": 0.6188,
|
| 723 |
+
"step": 2350
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.497685185185185,
|
| 727 |
+
"grad_norm": 26.587751388549805,
|
| 728 |
+
"learning_rate": 1.6116255144032925e-05,
|
| 729 |
+
"loss": 0.5596,
|
| 730 |
+
"step": 2375
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 5.555555555555555,
|
| 734 |
+
"grad_norm": 101.47644805908203,
|
| 735 |
+
"learning_rate": 1.605195473251029e-05,
|
| 736 |
+
"loss": 0.4598,
|
| 737 |
+
"step": 2400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 5.613425925925926,
|
| 741 |
+
"grad_norm": 49.117889404296875,
|
| 742 |
+
"learning_rate": 1.5987654320987655e-05,
|
| 743 |
+
"loss": 0.5003,
|
| 744 |
+
"step": 2425
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.671296296296296,
|
| 748 |
+
"grad_norm": 40.722389221191406,
|
| 749 |
+
"learning_rate": 1.5923353909465024e-05,
|
| 750 |
+
"loss": 0.5783,
|
| 751 |
+
"step": 2450
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 5.729166666666667,
|
| 755 |
+
"grad_norm": 1.4265937805175781,
|
| 756 |
+
"learning_rate": 1.5859053497942386e-05,
|
| 757 |
+
"loss": 0.5613,
|
| 758 |
+
"step": 2475
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 5.787037037037037,
|
| 762 |
+
"grad_norm": 25.484758377075195,
|
| 763 |
+
"learning_rate": 1.5794753086419754e-05,
|
| 764 |
+
"loss": 0.4909,
|
| 765 |
+
"step": 2500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 5.844907407407407,
|
| 769 |
+
"grad_norm": 29.874347686767578,
|
| 770 |
+
"learning_rate": 1.573045267489712e-05,
|
| 771 |
+
"loss": 0.4401,
|
| 772 |
+
"step": 2525
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 5.902777777777778,
|
| 776 |
+
"grad_norm": 8.134950637817383,
|
| 777 |
+
"learning_rate": 1.5666152263374488e-05,
|
| 778 |
+
"loss": 0.506,
|
| 779 |
+
"step": 2550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 5.960648148148148,
|
| 783 |
+
"grad_norm": 38.01759338378906,
|
| 784 |
+
"learning_rate": 1.5601851851851853e-05,
|
| 785 |
+
"loss": 0.4226,
|
| 786 |
+
"step": 2575
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.0,
|
| 790 |
+
"eval_accuracy": 0.9453125,
|
| 791 |
+
"eval_loss": 0.2655061185359955,
|
| 792 |
+
"eval_macro_f1": 0.826900458402438,
|
| 793 |
+
"eval_runtime": 0.9139,
|
| 794 |
+
"eval_samples_per_second": 1680.704,
|
| 795 |
+
"eval_steps_per_second": 105.044,
|
| 796 |
+
"eval_weighted_f1": 0.9445571039922019,
|
| 797 |
+
"step": 2592
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 6.018518518518518,
|
| 801 |
+
"grad_norm": 17.778188705444336,
|
| 802 |
+
"learning_rate": 1.5537551440329218e-05,
|
| 803 |
+
"loss": 0.5286,
|
| 804 |
+
"step": 2600
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 6.076388888888889,
|
| 808 |
+
"grad_norm": 93.97927856445312,
|
| 809 |
+
"learning_rate": 1.5473251028806587e-05,
|
| 810 |
+
"loss": 0.4149,
|
| 811 |
+
"step": 2625
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 6.1342592592592595,
|
| 815 |
+
"grad_norm": 0.2383577972650528,
|
| 816 |
+
"learning_rate": 1.5408950617283952e-05,
|
| 817 |
+
"loss": 0.4216,
|
| 818 |
+
"step": 2650
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 6.19212962962963,
|
| 822 |
+
"grad_norm": 129.9449920654297,
|
| 823 |
+
"learning_rate": 1.5344650205761317e-05,
|
| 824 |
+
"loss": 0.4641,
|
| 825 |
+
"step": 2675
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 6.25,
|
| 829 |
+
"grad_norm": 2.701225519180298,
|
| 830 |
+
"learning_rate": 1.5280349794238685e-05,
|
| 831 |
+
"loss": 0.3053,
|
| 832 |
+
"step": 2700
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 6.30787037037037,
|
| 836 |
+
"grad_norm": 4.475930213928223,
|
| 837 |
+
"learning_rate": 1.5216049382716052e-05,
|
| 838 |
+
"loss": 0.2456,
|
| 839 |
+
"step": 2725
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 6.3657407407407405,
|
| 843 |
+
"grad_norm": 0.39514395594596863,
|
| 844 |
+
"learning_rate": 1.5151748971193416e-05,
|
| 845 |
+
"loss": 0.2389,
|
| 846 |
+
"step": 2750
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 6.423611111111111,
|
| 850 |
+
"grad_norm": 64.64535522460938,
|
| 851 |
+
"learning_rate": 1.5087448559670783e-05,
|
| 852 |
+
"loss": 0.4791,
|
| 853 |
+
"step": 2775
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 6.481481481481482,
|
| 857 |
+
"grad_norm": 0.13686713576316833,
|
| 858 |
+
"learning_rate": 1.502314814814815e-05,
|
| 859 |
+
"loss": 0.3597,
|
| 860 |
+
"step": 2800
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 6.539351851851852,
|
| 864 |
+
"grad_norm": 66.75579833984375,
|
| 865 |
+
"learning_rate": 1.4958847736625515e-05,
|
| 866 |
+
"loss": 0.2795,
|
| 867 |
+
"step": 2825
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 6.597222222222222,
|
| 871 |
+
"grad_norm": 16.12794303894043,
|
| 872 |
+
"learning_rate": 1.4894547325102881e-05,
|
| 873 |
+
"loss": 0.4614,
|
| 874 |
+
"step": 2850
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 6.655092592592593,
|
| 878 |
+
"grad_norm": 16.306272506713867,
|
| 879 |
+
"learning_rate": 1.4830246913580248e-05,
|
| 880 |
+
"loss": 0.4043,
|
| 881 |
+
"step": 2875
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 6.712962962962963,
|
| 885 |
+
"grad_norm": 0.3289198875427246,
|
| 886 |
+
"learning_rate": 1.4765946502057615e-05,
|
| 887 |
+
"loss": 0.4885,
|
| 888 |
+
"step": 2900
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 6.770833333333333,
|
| 892 |
+
"grad_norm": 0.8487572073936462,
|
| 893 |
+
"learning_rate": 1.470164609053498e-05,
|
| 894 |
+
"loss": 0.4968,
|
| 895 |
+
"step": 2925
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 6.828703703703704,
|
| 899 |
+
"grad_norm": 0.2003978192806244,
|
| 900 |
+
"learning_rate": 1.4637345679012347e-05,
|
| 901 |
+
"loss": 0.5091,
|
| 902 |
+
"step": 2950
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 6.886574074074074,
|
| 906 |
+
"grad_norm": 0.16362027823925018,
|
| 907 |
+
"learning_rate": 1.4573045267489714e-05,
|
| 908 |
+
"loss": 0.3433,
|
| 909 |
+
"step": 2975
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 6.944444444444445,
|
| 913 |
+
"grad_norm": 218.46780395507812,
|
| 914 |
+
"learning_rate": 1.4508744855967079e-05,
|
| 915 |
+
"loss": 0.4131,
|
| 916 |
+
"step": 3000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 7.0,
|
| 920 |
+
"eval_accuracy": 0.9505208333333334,
|
| 921 |
+
"eval_loss": 0.2528908848762512,
|
| 922 |
+
"eval_macro_f1": 0.8252686381899087,
|
| 923 |
+
"eval_runtime": 0.9024,
|
| 924 |
+
"eval_samples_per_second": 1702.075,
|
| 925 |
+
"eval_steps_per_second": 106.38,
|
| 926 |
+
"eval_weighted_f1": 0.9495795577413876,
|
| 927 |
+
"step": 3024
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 7.002314814814815,
|
| 931 |
+
"grad_norm": 0.24196836352348328,
|
| 932 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 933 |
+
"loss": 0.524,
|
| 934 |
+
"step": 3025
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 7.060185185185185,
|
| 938 |
+
"grad_norm": 2.4255270957946777,
|
| 939 |
+
"learning_rate": 1.4380144032921813e-05,
|
| 940 |
+
"loss": 0.2824,
|
| 941 |
+
"step": 3050
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 7.118055555555555,
|
| 945 |
+
"grad_norm": 2.3567252159118652,
|
| 946 |
+
"learning_rate": 1.431584362139918e-05,
|
| 947 |
+
"loss": 0.2641,
|
| 948 |
+
"step": 3075
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 7.175925925925926,
|
| 952 |
+
"grad_norm": 3.121429443359375,
|
| 953 |
+
"learning_rate": 1.4251543209876545e-05,
|
| 954 |
+
"loss": 0.4793,
|
| 955 |
+
"step": 3100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 7.233796296296297,
|
| 959 |
+
"grad_norm": 0.1446550488471985,
|
| 960 |
+
"learning_rate": 1.4187242798353911e-05,
|
| 961 |
+
"loss": 0.2315,
|
| 962 |
+
"step": 3125
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 7.291666666666667,
|
| 966 |
+
"grad_norm": 1.926067590713501,
|
| 967 |
+
"learning_rate": 1.4122942386831278e-05,
|
| 968 |
+
"loss": 0.3161,
|
| 969 |
+
"step": 3150
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 7.349537037037037,
|
| 973 |
+
"grad_norm": 61.44171142578125,
|
| 974 |
+
"learning_rate": 1.4058641975308642e-05,
|
| 975 |
+
"loss": 0.1749,
|
| 976 |
+
"step": 3175
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 7.407407407407407,
|
| 980 |
+
"grad_norm": 0.07814063876867294,
|
| 981 |
+
"learning_rate": 1.3994341563786009e-05,
|
| 982 |
+
"loss": 0.2719,
|
| 983 |
+
"step": 3200
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 7.465277777777778,
|
| 987 |
+
"grad_norm": 0.08427251875400543,
|
| 988 |
+
"learning_rate": 1.3930041152263375e-05,
|
| 989 |
+
"loss": 0.2349,
|
| 990 |
+
"step": 3225
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 7.523148148148148,
|
| 994 |
+
"grad_norm": 0.132528617978096,
|
| 995 |
+
"learning_rate": 1.3865740740740742e-05,
|
| 996 |
+
"loss": 0.5286,
|
| 997 |
+
"step": 3250
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 7.581018518518518,
|
| 1001 |
+
"grad_norm": 0.19050949811935425,
|
| 1002 |
+
"learning_rate": 1.3801440329218107e-05,
|
| 1003 |
+
"loss": 0.3042,
|
| 1004 |
+
"step": 3275
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 7.638888888888889,
|
| 1008 |
+
"grad_norm": 33.442047119140625,
|
| 1009 |
+
"learning_rate": 1.3737139917695474e-05,
|
| 1010 |
+
"loss": 0.5667,
|
| 1011 |
+
"step": 3300
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 7.6967592592592595,
|
| 1015 |
+
"grad_norm": 0.3001527488231659,
|
| 1016 |
+
"learning_rate": 1.3672839506172841e-05,
|
| 1017 |
+
"loss": 0.3558,
|
| 1018 |
+
"step": 3325
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 7.75462962962963,
|
| 1022 |
+
"grad_norm": 0.10103724151849747,
|
| 1023 |
+
"learning_rate": 1.3608539094650206e-05,
|
| 1024 |
+
"loss": 0.4449,
|
| 1025 |
+
"step": 3350
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 7.8125,
|
| 1029 |
+
"grad_norm": 62.654327392578125,
|
| 1030 |
+
"learning_rate": 1.3544238683127573e-05,
|
| 1031 |
+
"loss": 0.2908,
|
| 1032 |
+
"step": 3375
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 7.87037037037037,
|
| 1036 |
+
"grad_norm": 0.11524419486522675,
|
| 1037 |
+
"learning_rate": 1.347993827160494e-05,
|
| 1038 |
+
"loss": 0.3451,
|
| 1039 |
+
"step": 3400
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 7.9282407407407405,
|
| 1043 |
+
"grad_norm": 0.069953054189682,
|
| 1044 |
+
"learning_rate": 1.3415637860082307e-05,
|
| 1045 |
+
"loss": 0.3791,
|
| 1046 |
+
"step": 3425
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 7.986111111111111,
|
| 1050 |
+
"grad_norm": 0.11564886569976807,
|
| 1051 |
+
"learning_rate": 1.3351337448559672e-05,
|
| 1052 |
+
"loss": 0.3311,
|
| 1053 |
+
"step": 3450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 8.0,
|
| 1057 |
+
"eval_accuracy": 0.9479166666666666,
|
| 1058 |
+
"eval_loss": 0.2920614778995514,
|
| 1059 |
+
"eval_macro_f1": 0.8200530692795899,
|
| 1060 |
+
"eval_runtime": 0.9054,
|
| 1061 |
+
"eval_samples_per_second": 1696.564,
|
| 1062 |
+
"eval_steps_per_second": 106.035,
|
| 1063 |
+
"eval_weighted_f1": 0.9466911138342452,
|
| 1064 |
+
"step": 3456
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 8.043981481481481,
|
| 1068 |
+
"grad_norm": 0.17939063906669617,
|
| 1069 |
+
"learning_rate": 1.3287037037037039e-05,
|
| 1070 |
+
"loss": 0.1105,
|
| 1071 |
+
"step": 3475
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 8.101851851851851,
|
| 1075 |
+
"grad_norm": 0.18473269045352936,
|
| 1076 |
+
"learning_rate": 1.3222736625514405e-05,
|
| 1077 |
+
"loss": 0.3775,
|
| 1078 |
+
"step": 3500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 8.159722222222221,
|
| 1082 |
+
"grad_norm": 98.61026763916016,
|
| 1083 |
+
"learning_rate": 1.315843621399177e-05,
|
| 1084 |
+
"loss": 0.2719,
|
| 1085 |
+
"step": 3525
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 8.217592592592593,
|
| 1089 |
+
"grad_norm": 0.9702001214027405,
|
| 1090 |
+
"learning_rate": 1.3094135802469137e-05,
|
| 1091 |
+
"loss": 0.2812,
|
| 1092 |
+
"step": 3550
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 8.275462962962964,
|
| 1096 |
+
"grad_norm": 23.601049423217773,
|
| 1097 |
+
"learning_rate": 1.3029835390946504e-05,
|
| 1098 |
+
"loss": 0.2446,
|
| 1099 |
+
"step": 3575
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 8.333333333333334,
|
| 1103 |
+
"grad_norm": 0.12345338612794876,
|
| 1104 |
+
"learning_rate": 1.2965534979423868e-05,
|
| 1105 |
+
"loss": 0.3504,
|
| 1106 |
+
"step": 3600
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 8.391203703703704,
|
| 1110 |
+
"grad_norm": 38.49873352050781,
|
| 1111 |
+
"learning_rate": 1.2901234567901235e-05,
|
| 1112 |
+
"loss": 0.1863,
|
| 1113 |
+
"step": 3625
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 8.449074074074074,
|
| 1117 |
+
"grad_norm": 74.69483947753906,
|
| 1118 |
+
"learning_rate": 1.2836934156378601e-05,
|
| 1119 |
+
"loss": 0.3509,
|
| 1120 |
+
"step": 3650
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 8.506944444444445,
|
| 1124 |
+
"grad_norm": 45.72534942626953,
|
| 1125 |
+
"learning_rate": 1.2772633744855968e-05,
|
| 1126 |
+
"loss": 0.3924,
|
| 1127 |
+
"step": 3675
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 8.564814814814815,
|
| 1131 |
+
"grad_norm": 2.6912403106689453,
|
| 1132 |
+
"learning_rate": 1.2708333333333333e-05,
|
| 1133 |
+
"loss": 0.3361,
|
| 1134 |
+
"step": 3700
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 8.622685185185185,
|
| 1138 |
+
"grad_norm": 0.14529313147068024,
|
| 1139 |
+
"learning_rate": 1.26440329218107e-05,
|
| 1140 |
+
"loss": 0.3644,
|
| 1141 |
+
"step": 3725
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 8.680555555555555,
|
| 1145 |
+
"grad_norm": 7.866279125213623,
|
| 1146 |
+
"learning_rate": 1.2579732510288067e-05,
|
| 1147 |
+
"loss": 0.3003,
|
| 1148 |
+
"step": 3750
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 8.738425925925926,
|
| 1152 |
+
"grad_norm": 0.358195424079895,
|
| 1153 |
+
"learning_rate": 1.2515432098765432e-05,
|
| 1154 |
+
"loss": 0.2302,
|
| 1155 |
+
"step": 3775
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 8.796296296296296,
|
| 1159 |
+
"grad_norm": 0.10957163572311401,
|
| 1160 |
+
"learning_rate": 1.2451131687242799e-05,
|
| 1161 |
+
"loss": 0.1901,
|
| 1162 |
+
"step": 3800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 8.854166666666666,
|
| 1166 |
+
"grad_norm": 2.35083270072937,
|
| 1167 |
+
"learning_rate": 1.2386831275720166e-05,
|
| 1168 |
+
"loss": 0.3523,
|
| 1169 |
+
"step": 3825
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 8.912037037037036,
|
| 1173 |
+
"grad_norm": 7.252814769744873,
|
| 1174 |
+
"learning_rate": 1.2322530864197533e-05,
|
| 1175 |
+
"loss": 0.2823,
|
| 1176 |
+
"step": 3850
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 8.969907407407408,
|
| 1180 |
+
"grad_norm": 4.921802997589111,
|
| 1181 |
+
"learning_rate": 1.2258230452674898e-05,
|
| 1182 |
+
"loss": 0.4327,
|
| 1183 |
+
"step": 3875
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 9.0,
|
| 1187 |
+
"eval_accuracy": 0.9498697916666666,
|
| 1188 |
+
"eval_loss": 0.26774439215660095,
|
| 1189 |
+
"eval_macro_f1": 0.8263756605172182,
|
| 1190 |
+
"eval_runtime": 0.9167,
|
| 1191 |
+
"eval_samples_per_second": 1675.549,
|
| 1192 |
+
"eval_steps_per_second": 104.722,
|
| 1193 |
+
"eval_weighted_f1": 0.9493403954664693,
|
| 1194 |
+
"step": 3888
|
| 1195 |
+
}
|
| 1196 |
+
],
|
| 1197 |
+
"logging_steps": 25,
|
| 1198 |
+
"max_steps": 8640,
|
| 1199 |
+
"num_input_tokens_seen": 0,
|
| 1200 |
+
"num_train_epochs": 20,
|
| 1201 |
+
"save_steps": 500,
|
| 1202 |
+
"stateful_callbacks": {
|
| 1203 |
+
"EarlyStoppingCallback": {
|
| 1204 |
+
"args": {
|
| 1205 |
+
"early_stopping_patience": 3,
|
| 1206 |
+
"early_stopping_threshold": 0.0
|
| 1207 |
+
},
|
| 1208 |
+
"attributes": {
|
| 1209 |
+
"early_stopping_patience_counter": 3
|
| 1210 |
+
}
|
| 1211 |
+
},
|
| 1212 |
+
"TrainerControl": {
|
| 1213 |
+
"args": {
|
| 1214 |
+
"should_epoch_stop": false,
|
| 1215 |
+
"should_evaluate": false,
|
| 1216 |
+
"should_log": false,
|
| 1217 |
+
"should_save": true,
|
| 1218 |
+
"should_training_stop": true
|
| 1219 |
+
},
|
| 1220 |
+
"attributes": {}
|
| 1221 |
+
}
|
| 1222 |
+
},
|
| 1223 |
+
"total_flos": 0.0,
|
| 1224 |
+
"train_batch_size": 8,
|
| 1225 |
+
"trial_name": null,
|
| 1226 |
+
"trial_params": null
|
| 1227 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850/trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1850,
|
| 3 |
+
"best_metric": 0.8334572921524086,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1850,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06765899864682003,
|
| 14 |
+
"grad_norm": 32.623130798339844,
|
| 15 |
+
"learning_rate": 6.486486486486487e-07,
|
| 16 |
+
"loss": 4.2903,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.13531799729364005,
|
| 21 |
+
"grad_norm": 32.07653045654297,
|
| 22 |
+
"learning_rate": 1.3243243243243246e-06,
|
| 23 |
+
"loss": 4.0046,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.2029769959404601,
|
| 28 |
+
"grad_norm": 27.520421981811523,
|
| 29 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 30 |
+
"loss": 3.7296,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.2706359945872801,
|
| 35 |
+
"grad_norm": 398.8569030761719,
|
| 36 |
+
"learning_rate": 2.6756756756756757e-06,
|
| 37 |
+
"loss": 3.3633,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3382949932341001,
|
| 42 |
+
"grad_norm": 25.857133865356445,
|
| 43 |
+
"learning_rate": 3.351351351351352e-06,
|
| 44 |
+
"loss": 3.1161,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4059539918809202,
|
| 49 |
+
"grad_norm": 246.95225524902344,
|
| 50 |
+
"learning_rate": 4.027027027027028e-06,
|
| 51 |
+
"loss": 2.9379,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4736129905277402,
|
| 56 |
+
"grad_norm": 27.746816635131836,
|
| 57 |
+
"learning_rate": 4.702702702702703e-06,
|
| 58 |
+
"loss": 2.4868,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5412719891745602,
|
| 63 |
+
"grad_norm": 41.030399322509766,
|
| 64 |
+
"learning_rate": 5.378378378378378e-06,
|
| 65 |
+
"loss": 1.9473,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6089309878213802,
|
| 70 |
+
"grad_norm": 45.39463806152344,
|
| 71 |
+
"learning_rate": 6.054054054054055e-06,
|
| 72 |
+
"loss": 1.6008,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6765899864682002,
|
| 77 |
+
"grad_norm": 19.919504165649414,
|
| 78 |
+
"learning_rate": 6.729729729729731e-06,
|
| 79 |
+
"loss": 1.57,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7442489851150202,
|
| 84 |
+
"grad_norm": 85.55883026123047,
|
| 85 |
+
"learning_rate": 7.4054054054054055e-06,
|
| 86 |
+
"loss": 1.3967,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8119079837618404,
|
| 91 |
+
"grad_norm": 26.684171676635742,
|
| 92 |
+
"learning_rate": 8.081081081081081e-06,
|
| 93 |
+
"loss": 1.3399,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8795669824086604,
|
| 98 |
+
"grad_norm": 82.3696517944336,
|
| 99 |
+
"learning_rate": 8.756756756756759e-06,
|
| 100 |
+
"loss": 1.2293,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9472259810554804,
|
| 105 |
+
"grad_norm": 35.49351119995117,
|
| 106 |
+
"learning_rate": 9.432432432432433e-06,
|
| 107 |
+
"loss": 1.3651,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.0,
|
| 112 |
+
"eval_accuracy": 0.9200913242009132,
|
| 113 |
+
"eval_loss": 0.26375502347946167,
|
| 114 |
+
"eval_macro_f1": 0.6803095972494654,
|
| 115 |
+
"eval_runtime": 0.8041,
|
| 116 |
+
"eval_samples_per_second": 1634.029,
|
| 117 |
+
"eval_steps_per_second": 103.215,
|
| 118 |
+
"eval_weighted_f1": 0.906108673352771,
|
| 119 |
+
"step": 370
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.013531799729364,
|
| 123 |
+
"grad_norm": 26.559459686279297,
|
| 124 |
+
"learning_rate": 1.0108108108108109e-05,
|
| 125 |
+
"loss": 0.9871,
|
| 126 |
+
"step": 375
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.0811907983761841,
|
| 130 |
+
"grad_norm": 60.349151611328125,
|
| 131 |
+
"learning_rate": 1.0783783783783786e-05,
|
| 132 |
+
"loss": 0.9877,
|
| 133 |
+
"step": 400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.148849797023004,
|
| 137 |
+
"grad_norm": 41.36415100097656,
|
| 138 |
+
"learning_rate": 1.1459459459459462e-05,
|
| 139 |
+
"loss": 1.1243,
|
| 140 |
+
"step": 425
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.2165087956698242,
|
| 144 |
+
"grad_norm": 49.0471076965332,
|
| 145 |
+
"learning_rate": 1.2135135135135136e-05,
|
| 146 |
+
"loss": 1.0819,
|
| 147 |
+
"step": 450
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.284167794316644,
|
| 151 |
+
"grad_norm": 40.75639724731445,
|
| 152 |
+
"learning_rate": 1.2810810810810812e-05,
|
| 153 |
+
"loss": 1.0397,
|
| 154 |
+
"step": 475
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.3518267929634642,
|
| 158 |
+
"grad_norm": 45.45246887207031,
|
| 159 |
+
"learning_rate": 1.3486486486486487e-05,
|
| 160 |
+
"loss": 0.9071,
|
| 161 |
+
"step": 500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.419485791610284,
|
| 165 |
+
"grad_norm": 41.182037353515625,
|
| 166 |
+
"learning_rate": 1.4162162162162163e-05,
|
| 167 |
+
"loss": 0.9268,
|
| 168 |
+
"step": 525
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.4871447902571042,
|
| 172 |
+
"grad_norm": 25.784265518188477,
|
| 173 |
+
"learning_rate": 1.4837837837837839e-05,
|
| 174 |
+
"loss": 0.8328,
|
| 175 |
+
"step": 550
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.5548037889039241,
|
| 179 |
+
"grad_norm": 40.280208587646484,
|
| 180 |
+
"learning_rate": 1.5513513513513513e-05,
|
| 181 |
+
"loss": 1.0969,
|
| 182 |
+
"step": 575
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.6224627875507442,
|
| 186 |
+
"grad_norm": 25.957277297973633,
|
| 187 |
+
"learning_rate": 1.618918918918919e-05,
|
| 188 |
+
"loss": 0.9494,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.6901217861975644,
|
| 193 |
+
"grad_norm": 344.7492980957031,
|
| 194 |
+
"learning_rate": 1.6864864864864868e-05,
|
| 195 |
+
"loss": 0.7169,
|
| 196 |
+
"step": 625
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.7577807848443843,
|
| 200 |
+
"grad_norm": 38.54136657714844,
|
| 201 |
+
"learning_rate": 1.7540540540540542e-05,
|
| 202 |
+
"loss": 0.7706,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.8254397834912042,
|
| 207 |
+
"grad_norm": 9.827171325683594,
|
| 208 |
+
"learning_rate": 1.821621621621622e-05,
|
| 209 |
+
"loss": 1.0181,
|
| 210 |
+
"step": 675
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.8930987821380243,
|
| 214 |
+
"grad_norm": 17.84044075012207,
|
| 215 |
+
"learning_rate": 1.8891891891891893e-05,
|
| 216 |
+
"loss": 0.8857,
|
| 217 |
+
"step": 700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.9607577807848444,
|
| 221 |
+
"grad_norm": 16.306425094604492,
|
| 222 |
+
"learning_rate": 1.956756756756757e-05,
|
| 223 |
+
"loss": 0.9017,
|
| 224 |
+
"step": 725
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.0,
|
| 228 |
+
"eval_accuracy": 0.9360730593607306,
|
| 229 |
+
"eval_loss": 0.22536657750606537,
|
| 230 |
+
"eval_macro_f1": 0.7878033381341943,
|
| 231 |
+
"eval_runtime": 0.8676,
|
| 232 |
+
"eval_samples_per_second": 1514.455,
|
| 233 |
+
"eval_steps_per_second": 95.662,
|
| 234 |
+
"eval_weighted_f1": 0.931203499852228,
|
| 235 |
+
"step": 740
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.027063599458728,
|
| 239 |
+
"grad_norm": 21.91657257080078,
|
| 240 |
+
"learning_rate": 1.9972972972972974e-05,
|
| 241 |
+
"loss": 0.828,
|
| 242 |
+
"step": 750
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.094722598105548,
|
| 246 |
+
"grad_norm": 13.658709526062012,
|
| 247 |
+
"learning_rate": 1.98978978978979e-05,
|
| 248 |
+
"loss": 0.8386,
|
| 249 |
+
"step": 775
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.1623815967523683,
|
| 253 |
+
"grad_norm": 20.393001556396484,
|
| 254 |
+
"learning_rate": 1.9822822822822824e-05,
|
| 255 |
+
"loss": 0.7168,
|
| 256 |
+
"step": 800
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.230040595399188,
|
| 260 |
+
"grad_norm": 26.24353790283203,
|
| 261 |
+
"learning_rate": 1.974774774774775e-05,
|
| 262 |
+
"loss": 0.868,
|
| 263 |
+
"step": 825
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.297699594046008,
|
| 267 |
+
"grad_norm": 51.34505081176758,
|
| 268 |
+
"learning_rate": 1.9672672672672674e-05,
|
| 269 |
+
"loss": 0.8079,
|
| 270 |
+
"step": 850
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.365358592692828,
|
| 274 |
+
"grad_norm": 15.814371109008789,
|
| 275 |
+
"learning_rate": 1.95975975975976e-05,
|
| 276 |
+
"loss": 0.8553,
|
| 277 |
+
"step": 875
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.4330175913396483,
|
| 281 |
+
"grad_norm": 126.53368377685547,
|
| 282 |
+
"learning_rate": 1.9522522522522524e-05,
|
| 283 |
+
"loss": 0.6823,
|
| 284 |
+
"step": 900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.500676589986468,
|
| 288 |
+
"grad_norm": 41.05950927734375,
|
| 289 |
+
"learning_rate": 1.944744744744745e-05,
|
| 290 |
+
"loss": 0.8344,
|
| 291 |
+
"step": 925
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.568335588633288,
|
| 295 |
+
"grad_norm": 62.164241790771484,
|
| 296 |
+
"learning_rate": 1.9372372372372375e-05,
|
| 297 |
+
"loss": 0.7076,
|
| 298 |
+
"step": 950
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.6359945872801083,
|
| 302 |
+
"grad_norm": 8.865660667419434,
|
| 303 |
+
"learning_rate": 1.92972972972973e-05,
|
| 304 |
+
"loss": 0.8253,
|
| 305 |
+
"step": 975
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.7036535859269284,
|
| 309 |
+
"grad_norm": 76.10330200195312,
|
| 310 |
+
"learning_rate": 1.9222222222222225e-05,
|
| 311 |
+
"loss": 0.7442,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.7713125845737485,
|
| 316 |
+
"grad_norm": 33.64796829223633,
|
| 317 |
+
"learning_rate": 1.914714714714715e-05,
|
| 318 |
+
"loss": 0.6994,
|
| 319 |
+
"step": 1025
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.838971583220568,
|
| 323 |
+
"grad_norm": 30.980314254760742,
|
| 324 |
+
"learning_rate": 1.9072072072072075e-05,
|
| 325 |
+
"loss": 0.6101,
|
| 326 |
+
"step": 1050
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.9066305818673883,
|
| 330 |
+
"grad_norm": 15.623394966125488,
|
| 331 |
+
"learning_rate": 1.8996996996997e-05,
|
| 332 |
+
"loss": 0.6298,
|
| 333 |
+
"step": 1075
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.9742895805142084,
|
| 337 |
+
"grad_norm": 28.45555305480957,
|
| 338 |
+
"learning_rate": 1.8921921921921925e-05,
|
| 339 |
+
"loss": 0.7647,
|
| 340 |
+
"step": 1100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.0,
|
| 344 |
+
"eval_accuracy": 0.941400304414003,
|
| 345 |
+
"eval_loss": 0.19824136793613434,
|
| 346 |
+
"eval_macro_f1": 0.8233681458359056,
|
| 347 |
+
"eval_runtime": 0.8143,
|
| 348 |
+
"eval_samples_per_second": 1613.741,
|
| 349 |
+
"eval_steps_per_second": 101.933,
|
| 350 |
+
"eval_weighted_f1": 0.9381351637404532,
|
| 351 |
+
"step": 1110
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.040595399188092,
|
| 355 |
+
"grad_norm": 22.267269134521484,
|
| 356 |
+
"learning_rate": 1.884684684684685e-05,
|
| 357 |
+
"loss": 0.6295,
|
| 358 |
+
"step": 1125
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.108254397834912,
|
| 362 |
+
"grad_norm": 5.833945274353027,
|
| 363 |
+
"learning_rate": 1.8771771771771776e-05,
|
| 364 |
+
"loss": 0.751,
|
| 365 |
+
"step": 1150
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.175913396481732,
|
| 369 |
+
"grad_norm": 31.31974220275879,
|
| 370 |
+
"learning_rate": 1.86966966966967e-05,
|
| 371 |
+
"loss": 0.5862,
|
| 372 |
+
"step": 1175
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.243572395128552,
|
| 376 |
+
"grad_norm": 16.451805114746094,
|
| 377 |
+
"learning_rate": 1.8621621621621622e-05,
|
| 378 |
+
"loss": 0.5391,
|
| 379 |
+
"step": 1200
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.311231393775372,
|
| 383 |
+
"grad_norm": 41.02743911743164,
|
| 384 |
+
"learning_rate": 1.8546546546546547e-05,
|
| 385 |
+
"loss": 0.4772,
|
| 386 |
+
"step": 1225
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.3788903924221922,
|
| 390 |
+
"grad_norm": 7.986902236938477,
|
| 391 |
+
"learning_rate": 1.8471471471471473e-05,
|
| 392 |
+
"loss": 0.6664,
|
| 393 |
+
"step": 1250
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.4465493910690124,
|
| 397 |
+
"grad_norm": 39.761749267578125,
|
| 398 |
+
"learning_rate": 1.8396396396396398e-05,
|
| 399 |
+
"loss": 0.5925,
|
| 400 |
+
"step": 1275
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.514208389715832,
|
| 404 |
+
"grad_norm": 82.96751403808594,
|
| 405 |
+
"learning_rate": 1.8321321321321323e-05,
|
| 406 |
+
"loss": 0.7345,
|
| 407 |
+
"step": 1300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.581867388362652,
|
| 411 |
+
"grad_norm": 63.583526611328125,
|
| 412 |
+
"learning_rate": 1.8246246246246248e-05,
|
| 413 |
+
"loss": 0.6734,
|
| 414 |
+
"step": 1325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.6495263870094723,
|
| 418 |
+
"grad_norm": 15.574935913085938,
|
| 419 |
+
"learning_rate": 1.8171171171171173e-05,
|
| 420 |
+
"loss": 0.4913,
|
| 421 |
+
"step": 1350
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.7171853856562924,
|
| 425 |
+
"grad_norm": 46.4832649230957,
|
| 426 |
+
"learning_rate": 1.8096096096096098e-05,
|
| 427 |
+
"loss": 0.6953,
|
| 428 |
+
"step": 1375
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.7848443843031125,
|
| 432 |
+
"grad_norm": 53.56804275512695,
|
| 433 |
+
"learning_rate": 1.8021021021021023e-05,
|
| 434 |
+
"loss": 0.7296,
|
| 435 |
+
"step": 1400
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.852503382949932,
|
| 439 |
+
"grad_norm": 35.54122543334961,
|
| 440 |
+
"learning_rate": 1.7945945945945948e-05,
|
| 441 |
+
"loss": 0.6851,
|
| 442 |
+
"step": 1425
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.9201623815967523,
|
| 446 |
+
"grad_norm": 7.746444225311279,
|
| 447 |
+
"learning_rate": 1.7870870870870873e-05,
|
| 448 |
+
"loss": 0.3395,
|
| 449 |
+
"step": 1450
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.9878213802435725,
|
| 453 |
+
"grad_norm": 31.426984786987305,
|
| 454 |
+
"learning_rate": 1.77957957957958e-05,
|
| 455 |
+
"loss": 0.8226,
|
| 456 |
+
"step": 1475
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 4.0,
|
| 460 |
+
"eval_accuracy": 0.9375951293759512,
|
| 461 |
+
"eval_loss": 0.2378186732530594,
|
| 462 |
+
"eval_macro_f1": 0.8134022823330511,
|
| 463 |
+
"eval_runtime": 0.8834,
|
| 464 |
+
"eval_samples_per_second": 1487.432,
|
| 465 |
+
"eval_steps_per_second": 93.955,
|
| 466 |
+
"eval_weighted_f1": 0.935890836860281,
|
| 467 |
+
"step": 1480
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.054127198917456,
|
| 471 |
+
"grad_norm": 74.3106918334961,
|
| 472 |
+
"learning_rate": 1.7720720720720724e-05,
|
| 473 |
+
"loss": 0.5015,
|
| 474 |
+
"step": 1500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.121786197564276,
|
| 478 |
+
"grad_norm": 7.395301342010498,
|
| 479 |
+
"learning_rate": 1.764564564564565e-05,
|
| 480 |
+
"loss": 0.54,
|
| 481 |
+
"step": 1525
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 4.189445196211096,
|
| 485 |
+
"grad_norm": 3.4349141120910645,
|
| 486 |
+
"learning_rate": 1.757057057057057e-05,
|
| 487 |
+
"loss": 0.4884,
|
| 488 |
+
"step": 1550
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.2571041948579165,
|
| 492 |
+
"grad_norm": 86.04708862304688,
|
| 493 |
+
"learning_rate": 1.7495495495495496e-05,
|
| 494 |
+
"loss": 0.5523,
|
| 495 |
+
"step": 1575
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.324763193504737,
|
| 499 |
+
"grad_norm": 43.00638198852539,
|
| 500 |
+
"learning_rate": 1.742042042042042e-05,
|
| 501 |
+
"loss": 0.4159,
|
| 502 |
+
"step": 1600
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 4.392422192151556,
|
| 506 |
+
"grad_norm": 29.275218963623047,
|
| 507 |
+
"learning_rate": 1.7345345345345346e-05,
|
| 508 |
+
"loss": 0.6589,
|
| 509 |
+
"step": 1625
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.460081190798376,
|
| 513 |
+
"grad_norm": 14.526114463806152,
|
| 514 |
+
"learning_rate": 1.727027027027027e-05,
|
| 515 |
+
"loss": 0.3185,
|
| 516 |
+
"step": 1650
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 4.527740189445196,
|
| 520 |
+
"grad_norm": 20.746273040771484,
|
| 521 |
+
"learning_rate": 1.7195195195195196e-05,
|
| 522 |
+
"loss": 0.674,
|
| 523 |
+
"step": 1675
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 4.595399188092016,
|
| 527 |
+
"grad_norm": 52.26481628417969,
|
| 528 |
+
"learning_rate": 1.712012012012012e-05,
|
| 529 |
+
"loss": 0.5165,
|
| 530 |
+
"step": 1700
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.663058186738836,
|
| 534 |
+
"grad_norm": 51.01518249511719,
|
| 535 |
+
"learning_rate": 1.7045045045045046e-05,
|
| 536 |
+
"loss": 0.4697,
|
| 537 |
+
"step": 1725
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.730717185385656,
|
| 541 |
+
"grad_norm": 1.2095167636871338,
|
| 542 |
+
"learning_rate": 1.696996996996997e-05,
|
| 543 |
+
"loss": 0.2753,
|
| 544 |
+
"step": 1750
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.798376184032477,
|
| 548 |
+
"grad_norm": 8.148855209350586,
|
| 549 |
+
"learning_rate": 1.6894894894894896e-05,
|
| 550 |
+
"loss": 0.5383,
|
| 551 |
+
"step": 1775
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.866035182679297,
|
| 555 |
+
"grad_norm": 31.880342483520508,
|
| 556 |
+
"learning_rate": 1.681981981981982e-05,
|
| 557 |
+
"loss": 0.631,
|
| 558 |
+
"step": 1800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.933694181326116,
|
| 562 |
+
"grad_norm": 46.66429901123047,
|
| 563 |
+
"learning_rate": 1.6744744744744747e-05,
|
| 564 |
+
"loss": 0.4328,
|
| 565 |
+
"step": 1825
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 5.0,
|
| 569 |
+
"grad_norm": 3.385221481323242,
|
| 570 |
+
"learning_rate": 1.666966966966967e-05,
|
| 571 |
+
"loss": 0.5151,
|
| 572 |
+
"step": 1850
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 5.0,
|
| 576 |
+
"eval_accuracy": 0.9421613394216134,
|
| 577 |
+
"eval_loss": 0.2795228660106659,
|
| 578 |
+
"eval_macro_f1": 0.8334572921524086,
|
| 579 |
+
"eval_runtime": 0.8079,
|
| 580 |
+
"eval_samples_per_second": 1626.49,
|
| 581 |
+
"eval_steps_per_second": 102.739,
|
| 582 |
+
"eval_weighted_f1": 0.9417341544717814,
|
| 583 |
+
"step": 1850
|
| 584 |
+
}
|
| 585 |
+
],
|
| 586 |
+
"logging_steps": 25,
|
| 587 |
+
"max_steps": 7400,
|
| 588 |
+
"num_input_tokens_seen": 0,
|
| 589 |
+
"num_train_epochs": 20,
|
| 590 |
+
"save_steps": 500,
|
| 591 |
+
"stateful_callbacks": {
|
| 592 |
+
"EarlyStoppingCallback": {
|
| 593 |
+
"args": {
|
| 594 |
+
"early_stopping_patience": 3,
|
| 595 |
+
"early_stopping_threshold": 0.0
|
| 596 |
+
},
|
| 597 |
+
"attributes": {
|
| 598 |
+
"early_stopping_patience_counter": 0
|
| 599 |
+
}
|
| 600 |
+
},
|
| 601 |
+
"TrainerControl": {
|
| 602 |
+
"args": {
|
| 603 |
+
"should_epoch_stop": false,
|
| 604 |
+
"should_evaluate": false,
|
| 605 |
+
"should_log": false,
|
| 606 |
+
"should_save": true,
|
| 607 |
+
"should_training_stop": false
|
| 608 |
+
},
|
| 609 |
+
"attributes": {}
|
| 610 |
+
}
|
| 611 |
+
},
|
| 612 |
+
"total_flos": 0.0,
|
| 613 |
+
"train_batch_size": 8,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-2960/trainer_state.json
ADDED
|
@@ -0,0 +1,957 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1850,
|
| 3 |
+
"best_metric": 0.8334572921524086,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-uit_vsfc-bamibert-topic-domain-03-s44-20260827T164444Z-b6645c77/trainer/checkpoint-1850",
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2960,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06765899864682003,
|
| 14 |
+
"grad_norm": 32.623130798339844,
|
| 15 |
+
"learning_rate": 6.486486486486487e-07,
|
| 16 |
+
"loss": 4.2903,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.13531799729364005,
|
| 21 |
+
"grad_norm": 32.07653045654297,
|
| 22 |
+
"learning_rate": 1.3243243243243246e-06,
|
| 23 |
+
"loss": 4.0046,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.2029769959404601,
|
| 28 |
+
"grad_norm": 27.520421981811523,
|
| 29 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 30 |
+
"loss": 3.7296,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.2706359945872801,
|
| 35 |
+
"grad_norm": 398.8569030761719,
|
| 36 |
+
"learning_rate": 2.6756756756756757e-06,
|
| 37 |
+
"loss": 3.3633,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3382949932341001,
|
| 42 |
+
"grad_norm": 25.857133865356445,
|
| 43 |
+
"learning_rate": 3.351351351351352e-06,
|
| 44 |
+
"loss": 3.1161,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4059539918809202,
|
| 49 |
+
"grad_norm": 246.95225524902344,
|
| 50 |
+
"learning_rate": 4.027027027027028e-06,
|
| 51 |
+
"loss": 2.9379,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4736129905277402,
|
| 56 |
+
"grad_norm": 27.746816635131836,
|
| 57 |
+
"learning_rate": 4.702702702702703e-06,
|
| 58 |
+
"loss": 2.4868,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5412719891745602,
|
| 63 |
+
"grad_norm": 41.030399322509766,
|
| 64 |
+
"learning_rate": 5.378378378378378e-06,
|
| 65 |
+
"loss": 1.9473,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6089309878213802,
|
| 70 |
+
"grad_norm": 45.39463806152344,
|
| 71 |
+
"learning_rate": 6.054054054054055e-06,
|
| 72 |
+
"loss": 1.6008,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6765899864682002,
|
| 77 |
+
"grad_norm": 19.919504165649414,
|
| 78 |
+
"learning_rate": 6.729729729729731e-06,
|
| 79 |
+
"loss": 1.57,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7442489851150202,
|
| 84 |
+
"grad_norm": 85.55883026123047,
|
| 85 |
+
"learning_rate": 7.4054054054054055e-06,
|
| 86 |
+
"loss": 1.3967,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8119079837618404,
|
| 91 |
+
"grad_norm": 26.684171676635742,
|
| 92 |
+
"learning_rate": 8.081081081081081e-06,
|
| 93 |
+
"loss": 1.3399,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8795669824086604,
|
| 98 |
+
"grad_norm": 82.3696517944336,
|
| 99 |
+
"learning_rate": 8.756756756756759e-06,
|
| 100 |
+
"loss": 1.2293,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9472259810554804,
|
| 105 |
+
"grad_norm": 35.49351119995117,
|
| 106 |
+
"learning_rate": 9.432432432432433e-06,
|
| 107 |
+
"loss": 1.3651,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.0,
|
| 112 |
+
"eval_accuracy": 0.9200913242009132,
|
| 113 |
+
"eval_loss": 0.26375502347946167,
|
| 114 |
+
"eval_macro_f1": 0.6803095972494654,
|
| 115 |
+
"eval_runtime": 0.8041,
|
| 116 |
+
"eval_samples_per_second": 1634.029,
|
| 117 |
+
"eval_steps_per_second": 103.215,
|
| 118 |
+
"eval_weighted_f1": 0.906108673352771,
|
| 119 |
+
"step": 370
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.013531799729364,
|
| 123 |
+
"grad_norm": 26.559459686279297,
|
| 124 |
+
"learning_rate": 1.0108108108108109e-05,
|
| 125 |
+
"loss": 0.9871,
|
| 126 |
+
"step": 375
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.0811907983761841,
|
| 130 |
+
"grad_norm": 60.349151611328125,
|
| 131 |
+
"learning_rate": 1.0783783783783786e-05,
|
| 132 |
+
"loss": 0.9877,
|
| 133 |
+
"step": 400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.148849797023004,
|
| 137 |
+
"grad_norm": 41.36415100097656,
|
| 138 |
+
"learning_rate": 1.1459459459459462e-05,
|
| 139 |
+
"loss": 1.1243,
|
| 140 |
+
"step": 425
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.2165087956698242,
|
| 144 |
+
"grad_norm": 49.0471076965332,
|
| 145 |
+
"learning_rate": 1.2135135135135136e-05,
|
| 146 |
+
"loss": 1.0819,
|
| 147 |
+
"step": 450
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.284167794316644,
|
| 151 |
+
"grad_norm": 40.75639724731445,
|
| 152 |
+
"learning_rate": 1.2810810810810812e-05,
|
| 153 |
+
"loss": 1.0397,
|
| 154 |
+
"step": 475
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.3518267929634642,
|
| 158 |
+
"grad_norm": 45.45246887207031,
|
| 159 |
+
"learning_rate": 1.3486486486486487e-05,
|
| 160 |
+
"loss": 0.9071,
|
| 161 |
+
"step": 500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.419485791610284,
|
| 165 |
+
"grad_norm": 41.182037353515625,
|
| 166 |
+
"learning_rate": 1.4162162162162163e-05,
|
| 167 |
+
"loss": 0.9268,
|
| 168 |
+
"step": 525
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.4871447902571042,
|
| 172 |
+
"grad_norm": 25.784265518188477,
|
| 173 |
+
"learning_rate": 1.4837837837837839e-05,
|
| 174 |
+
"loss": 0.8328,
|
| 175 |
+
"step": 550
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.5548037889039241,
|
| 179 |
+
"grad_norm": 40.280208587646484,
|
| 180 |
+
"learning_rate": 1.5513513513513513e-05,
|
| 181 |
+
"loss": 1.0969,
|
| 182 |
+
"step": 575
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.6224627875507442,
|
| 186 |
+
"grad_norm": 25.957277297973633,
|
| 187 |
+
"learning_rate": 1.618918918918919e-05,
|
| 188 |
+
"loss": 0.9494,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.6901217861975644,
|
| 193 |
+
"grad_norm": 344.7492980957031,
|
| 194 |
+
"learning_rate": 1.6864864864864868e-05,
|
| 195 |
+
"loss": 0.7169,
|
| 196 |
+
"step": 625
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.7577807848443843,
|
| 200 |
+
"grad_norm": 38.54136657714844,
|
| 201 |
+
"learning_rate": 1.7540540540540542e-05,
|
| 202 |
+
"loss": 0.7706,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.8254397834912042,
|
| 207 |
+
"grad_norm": 9.827171325683594,
|
| 208 |
+
"learning_rate": 1.821621621621622e-05,
|
| 209 |
+
"loss": 1.0181,
|
| 210 |
+
"step": 675
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.8930987821380243,
|
| 214 |
+
"grad_norm": 17.84044075012207,
|
| 215 |
+
"learning_rate": 1.8891891891891893e-05,
|
| 216 |
+
"loss": 0.8857,
|
| 217 |
+
"step": 700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.9607577807848444,
|
| 221 |
+
"grad_norm": 16.306425094604492,
|
| 222 |
+
"learning_rate": 1.956756756756757e-05,
|
| 223 |
+
"loss": 0.9017,
|
| 224 |
+
"step": 725
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.0,
|
| 228 |
+
"eval_accuracy": 0.9360730593607306,
|
| 229 |
+
"eval_loss": 0.22536657750606537,
|
| 230 |
+
"eval_macro_f1": 0.7878033381341943,
|
| 231 |
+
"eval_runtime": 0.8676,
|
| 232 |
+
"eval_samples_per_second": 1514.455,
|
| 233 |
+
"eval_steps_per_second": 95.662,
|
| 234 |
+
"eval_weighted_f1": 0.931203499852228,
|
| 235 |
+
"step": 740
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.027063599458728,
|
| 239 |
+
"grad_norm": 21.91657257080078,
|
| 240 |
+
"learning_rate": 1.9972972972972974e-05,
|
| 241 |
+
"loss": 0.828,
|
| 242 |
+
"step": 750
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.094722598105548,
|
| 246 |
+
"grad_norm": 13.658709526062012,
|
| 247 |
+
"learning_rate": 1.98978978978979e-05,
|
| 248 |
+
"loss": 0.8386,
|
| 249 |
+
"step": 775
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.1623815967523683,
|
| 253 |
+
"grad_norm": 20.393001556396484,
|
| 254 |
+
"learning_rate": 1.9822822822822824e-05,
|
| 255 |
+
"loss": 0.7168,
|
| 256 |
+
"step": 800
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.230040595399188,
|
| 260 |
+
"grad_norm": 26.24353790283203,
|
| 261 |
+
"learning_rate": 1.974774774774775e-05,
|
| 262 |
+
"loss": 0.868,
|
| 263 |
+
"step": 825
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.297699594046008,
|
| 267 |
+
"grad_norm": 51.34505081176758,
|
| 268 |
+
"learning_rate": 1.9672672672672674e-05,
|
| 269 |
+
"loss": 0.8079,
|
| 270 |
+
"step": 850
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.365358592692828,
|
| 274 |
+
"grad_norm": 15.814371109008789,
|
| 275 |
+
"learning_rate": 1.95975975975976e-05,
|
| 276 |
+
"loss": 0.8553,
|
| 277 |
+
"step": 875
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.4330175913396483,
|
| 281 |
+
"grad_norm": 126.53368377685547,
|
| 282 |
+
"learning_rate": 1.9522522522522524e-05,
|
| 283 |
+
"loss": 0.6823,
|
| 284 |
+
"step": 900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.500676589986468,
|
| 288 |
+
"grad_norm": 41.05950927734375,
|
| 289 |
+
"learning_rate": 1.944744744744745e-05,
|
| 290 |
+
"loss": 0.8344,
|
| 291 |
+
"step": 925
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.568335588633288,
|
| 295 |
+
"grad_norm": 62.164241790771484,
|
| 296 |
+
"learning_rate": 1.9372372372372375e-05,
|
| 297 |
+
"loss": 0.7076,
|
| 298 |
+
"step": 950
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.6359945872801083,
|
| 302 |
+
"grad_norm": 8.865660667419434,
|
| 303 |
+
"learning_rate": 1.92972972972973e-05,
|
| 304 |
+
"loss": 0.8253,
|
| 305 |
+
"step": 975
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.7036535859269284,
|
| 309 |
+
"grad_norm": 76.10330200195312,
|
| 310 |
+
"learning_rate": 1.9222222222222225e-05,
|
| 311 |
+
"loss": 0.7442,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.7713125845737485,
|
| 316 |
+
"grad_norm": 33.64796829223633,
|
| 317 |
+
"learning_rate": 1.914714714714715e-05,
|
| 318 |
+
"loss": 0.6994,
|
| 319 |
+
"step": 1025
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.838971583220568,
|
| 323 |
+
"grad_norm": 30.980314254760742,
|
| 324 |
+
"learning_rate": 1.9072072072072075e-05,
|
| 325 |
+
"loss": 0.6101,
|
| 326 |
+
"step": 1050
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.9066305818673883,
|
| 330 |
+
"grad_norm": 15.623394966125488,
|
| 331 |
+
"learning_rate": 1.8996996996997e-05,
|
| 332 |
+
"loss": 0.6298,
|
| 333 |
+
"step": 1075
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.9742895805142084,
|
| 337 |
+
"grad_norm": 28.45555305480957,
|
| 338 |
+
"learning_rate": 1.8921921921921925e-05,
|
| 339 |
+
"loss": 0.7647,
|
| 340 |
+
"step": 1100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.0,
|
| 344 |
+
"eval_accuracy": 0.941400304414003,
|
| 345 |
+
"eval_loss": 0.19824136793613434,
|
| 346 |
+
"eval_macro_f1": 0.8233681458359056,
|
| 347 |
+
"eval_runtime": 0.8143,
|
| 348 |
+
"eval_samples_per_second": 1613.741,
|
| 349 |
+
"eval_steps_per_second": 101.933,
|
| 350 |
+
"eval_weighted_f1": 0.9381351637404532,
|
| 351 |
+
"step": 1110
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.040595399188092,
|
| 355 |
+
"grad_norm": 22.267269134521484,
|
| 356 |
+
"learning_rate": 1.884684684684685e-05,
|
| 357 |
+
"loss": 0.6295,
|
| 358 |
+
"step": 1125
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.108254397834912,
|
| 362 |
+
"grad_norm": 5.833945274353027,
|
| 363 |
+
"learning_rate": 1.8771771771771776e-05,
|
| 364 |
+
"loss": 0.751,
|
| 365 |
+
"step": 1150
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.175913396481732,
|
| 369 |
+
"grad_norm": 31.31974220275879,
|
| 370 |
+
"learning_rate": 1.86966966966967e-05,
|
| 371 |
+
"loss": 0.5862,
|
| 372 |
+
"step": 1175
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.243572395128552,
|
| 376 |
+
"grad_norm": 16.451805114746094,
|
| 377 |
+
"learning_rate": 1.8621621621621622e-05,
|
| 378 |
+
"loss": 0.5391,
|
| 379 |
+
"step": 1200
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.311231393775372,
|
| 383 |
+
"grad_norm": 41.02743911743164,
|
| 384 |
+
"learning_rate": 1.8546546546546547e-05,
|
| 385 |
+
"loss": 0.4772,
|
| 386 |
+
"step": 1225
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.3788903924221922,
|
| 390 |
+
"grad_norm": 7.986902236938477,
|
| 391 |
+
"learning_rate": 1.8471471471471473e-05,
|
| 392 |
+
"loss": 0.6664,
|
| 393 |
+
"step": 1250
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.4465493910690124,
|
| 397 |
+
"grad_norm": 39.761749267578125,
|
| 398 |
+
"learning_rate": 1.8396396396396398e-05,
|
| 399 |
+
"loss": 0.5925,
|
| 400 |
+
"step": 1275
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.514208389715832,
|
| 404 |
+
"grad_norm": 82.96751403808594,
|
| 405 |
+
"learning_rate": 1.8321321321321323e-05,
|
| 406 |
+
"loss": 0.7345,
|
| 407 |
+
"step": 1300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.581867388362652,
|
| 411 |
+
"grad_norm": 63.583526611328125,
|
| 412 |
+
"learning_rate": 1.8246246246246248e-05,
|
| 413 |
+
"loss": 0.6734,
|
| 414 |
+
"step": 1325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.6495263870094723,
|
| 418 |
+
"grad_norm": 15.574935913085938,
|
| 419 |
+
"learning_rate": 1.8171171171171173e-05,
|
| 420 |
+
"loss": 0.4913,
|
| 421 |
+
"step": 1350
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.7171853856562924,
|
| 425 |
+
"grad_norm": 46.4832649230957,
|
| 426 |
+
"learning_rate": 1.8096096096096098e-05,
|
| 427 |
+
"loss": 0.6953,
|
| 428 |
+
"step": 1375
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.7848443843031125,
|
| 432 |
+
"grad_norm": 53.56804275512695,
|
| 433 |
+
"learning_rate": 1.8021021021021023e-05,
|
| 434 |
+
"loss": 0.7296,
|
| 435 |
+
"step": 1400
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.852503382949932,
|
| 439 |
+
"grad_norm": 35.54122543334961,
|
| 440 |
+
"learning_rate": 1.7945945945945948e-05,
|
| 441 |
+
"loss": 0.6851,
|
| 442 |
+
"step": 1425
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.9201623815967523,
|
| 446 |
+
"grad_norm": 7.746444225311279,
|
| 447 |
+
"learning_rate": 1.7870870870870873e-05,
|
| 448 |
+
"loss": 0.3395,
|
| 449 |
+
"step": 1450
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.9878213802435725,
|
| 453 |
+
"grad_norm": 31.426984786987305,
|
| 454 |
+
"learning_rate": 1.77957957957958e-05,
|
| 455 |
+
"loss": 0.8226,
|
| 456 |
+
"step": 1475
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 4.0,
|
| 460 |
+
"eval_accuracy": 0.9375951293759512,
|
| 461 |
+
"eval_loss": 0.2378186732530594,
|
| 462 |
+
"eval_macro_f1": 0.8134022823330511,
|
| 463 |
+
"eval_runtime": 0.8834,
|
| 464 |
+
"eval_samples_per_second": 1487.432,
|
| 465 |
+
"eval_steps_per_second": 93.955,
|
| 466 |
+
"eval_weighted_f1": 0.935890836860281,
|
| 467 |
+
"step": 1480
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.054127198917456,
|
| 471 |
+
"grad_norm": 74.3106918334961,
|
| 472 |
+
"learning_rate": 1.7720720720720724e-05,
|
| 473 |
+
"loss": 0.5015,
|
| 474 |
+
"step": 1500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.121786197564276,
|
| 478 |
+
"grad_norm": 7.395301342010498,
|
| 479 |
+
"learning_rate": 1.764564564564565e-05,
|
| 480 |
+
"loss": 0.54,
|
| 481 |
+
"step": 1525
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 4.189445196211096,
|
| 485 |
+
"grad_norm": 3.4349141120910645,
|
| 486 |
+
"learning_rate": 1.757057057057057e-05,
|
| 487 |
+
"loss": 0.4884,
|
| 488 |
+
"step": 1550
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.2571041948579165,
|
| 492 |
+
"grad_norm": 86.04708862304688,
|
| 493 |
+
"learning_rate": 1.7495495495495496e-05,
|
| 494 |
+
"loss": 0.5523,
|
| 495 |
+
"step": 1575
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.324763193504737,
|
| 499 |
+
"grad_norm": 43.00638198852539,
|
| 500 |
+
"learning_rate": 1.742042042042042e-05,
|
| 501 |
+
"loss": 0.4159,
|
| 502 |
+
"step": 1600
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 4.392422192151556,
|
| 506 |
+
"grad_norm": 29.275218963623047,
|
| 507 |
+
"learning_rate": 1.7345345345345346e-05,
|
| 508 |
+
"loss": 0.6589,
|
| 509 |
+
"step": 1625
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.460081190798376,
|
| 513 |
+
"grad_norm": 14.526114463806152,
|
| 514 |
+
"learning_rate": 1.727027027027027e-05,
|
| 515 |
+
"loss": 0.3185,
|
| 516 |
+
"step": 1650
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 4.527740189445196,
|
| 520 |
+
"grad_norm": 20.746273040771484,
|
| 521 |
+
"learning_rate": 1.7195195195195196e-05,
|
| 522 |
+
"loss": 0.674,
|
| 523 |
+
"step": 1675
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 4.595399188092016,
|
| 527 |
+
"grad_norm": 52.26481628417969,
|
| 528 |
+
"learning_rate": 1.712012012012012e-05,
|
| 529 |
+
"loss": 0.5165,
|
| 530 |
+
"step": 1700
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.663058186738836,
|
| 534 |
+
"grad_norm": 51.01518249511719,
|
| 535 |
+
"learning_rate": 1.7045045045045046e-05,
|
| 536 |
+
"loss": 0.4697,
|
| 537 |
+
"step": 1725
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.730717185385656,
|
| 541 |
+
"grad_norm": 1.2095167636871338,
|
| 542 |
+
"learning_rate": 1.696996996996997e-05,
|
| 543 |
+
"loss": 0.2753,
|
| 544 |
+
"step": 1750
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.798376184032477,
|
| 548 |
+
"grad_norm": 8.148855209350586,
|
| 549 |
+
"learning_rate": 1.6894894894894896e-05,
|
| 550 |
+
"loss": 0.5383,
|
| 551 |
+
"step": 1775
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.866035182679297,
|
| 555 |
+
"grad_norm": 31.880342483520508,
|
| 556 |
+
"learning_rate": 1.681981981981982e-05,
|
| 557 |
+
"loss": 0.631,
|
| 558 |
+
"step": 1800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.933694181326116,
|
| 562 |
+
"grad_norm": 46.66429901123047,
|
| 563 |
+
"learning_rate": 1.6744744744744747e-05,
|
| 564 |
+
"loss": 0.4328,
|
| 565 |
+
"step": 1825
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 5.0,
|
| 569 |
+
"grad_norm": 3.385221481323242,
|
| 570 |
+
"learning_rate": 1.666966966966967e-05,
|
| 571 |
+
"loss": 0.5151,
|
| 572 |
+
"step": 1850
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 5.0,
|
| 576 |
+
"eval_accuracy": 0.9421613394216134,
|
| 577 |
+
"eval_loss": 0.2795228660106659,
|
| 578 |
+
"eval_macro_f1": 0.8334572921524086,
|
| 579 |
+
"eval_runtime": 0.8079,
|
| 580 |
+
"eval_samples_per_second": 1626.49,
|
| 581 |
+
"eval_steps_per_second": 102.739,
|
| 582 |
+
"eval_weighted_f1": 0.9417341544717814,
|
| 583 |
+
"step": 1850
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 5.06765899864682,
|
| 587 |
+
"grad_norm": 2.072652578353882,
|
| 588 |
+
"learning_rate": 1.6594594594594597e-05,
|
| 589 |
+
"loss": 0.2683,
|
| 590 |
+
"step": 1875
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 5.13531799729364,
|
| 594 |
+
"grad_norm": 110.49122619628906,
|
| 595 |
+
"learning_rate": 1.651951951951952e-05,
|
| 596 |
+
"loss": 0.4739,
|
| 597 |
+
"step": 1900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 5.20297699594046,
|
| 601 |
+
"grad_norm": 0.17393624782562256,
|
| 602 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 603 |
+
"loss": 0.3841,
|
| 604 |
+
"step": 1925
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 5.2706359945872805,
|
| 608 |
+
"grad_norm": 0.357155978679657,
|
| 609 |
+
"learning_rate": 1.636936936936937e-05,
|
| 610 |
+
"loss": 0.467,
|
| 611 |
+
"step": 1950
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.3382949932341,
|
| 615 |
+
"grad_norm": 0.53045254945755,
|
| 616 |
+
"learning_rate": 1.6294294294294294e-05,
|
| 617 |
+
"loss": 0.5235,
|
| 618 |
+
"step": 1975
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.40595399188092,
|
| 622 |
+
"grad_norm": 38.95998764038086,
|
| 623 |
+
"learning_rate": 1.621921921921922e-05,
|
| 624 |
+
"loss": 0.481,
|
| 625 |
+
"step": 2000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 5.47361299052774,
|
| 629 |
+
"grad_norm": 24.88178253173828,
|
| 630 |
+
"learning_rate": 1.6144144144144144e-05,
|
| 631 |
+
"loss": 0.4468,
|
| 632 |
+
"step": 2025
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 5.54127198917456,
|
| 636 |
+
"grad_norm": 2.8248298168182373,
|
| 637 |
+
"learning_rate": 1.606906906906907e-05,
|
| 638 |
+
"loss": 0.4212,
|
| 639 |
+
"step": 2050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.60893098782138,
|
| 643 |
+
"grad_norm": 436.3692321777344,
|
| 644 |
+
"learning_rate": 1.5993993993993994e-05,
|
| 645 |
+
"loss": 0.4142,
|
| 646 |
+
"step": 2075
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 5.6765899864682,
|
| 650 |
+
"grad_norm": 72.73567962646484,
|
| 651 |
+
"learning_rate": 1.591891891891892e-05,
|
| 652 |
+
"loss": 0.4046,
|
| 653 |
+
"step": 2100
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 5.7442489851150205,
|
| 657 |
+
"grad_norm": 0.16415567696094513,
|
| 658 |
+
"learning_rate": 1.5843843843843844e-05,
|
| 659 |
+
"loss": 0.3852,
|
| 660 |
+
"step": 2125
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.811907983761841,
|
| 664 |
+
"grad_norm": 48.390411376953125,
|
| 665 |
+
"learning_rate": 1.576876876876877e-05,
|
| 666 |
+
"loss": 0.3453,
|
| 667 |
+
"step": 2150
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 5.879566982408661,
|
| 671 |
+
"grad_norm": 14.298480987548828,
|
| 672 |
+
"learning_rate": 1.5693693693693695e-05,
|
| 673 |
+
"loss": 0.3662,
|
| 674 |
+
"step": 2175
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.94722598105548,
|
| 678 |
+
"grad_norm": 3.4774065017700195,
|
| 679 |
+
"learning_rate": 1.561861861861862e-05,
|
| 680 |
+
"loss": 0.4229,
|
| 681 |
+
"step": 2200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.0,
|
| 685 |
+
"eval_accuracy": 0.9467275494672754,
|
| 686 |
+
"eval_loss": 0.2914351522922516,
|
| 687 |
+
"eval_macro_f1": 0.8252887725242569,
|
| 688 |
+
"eval_runtime": 0.7853,
|
| 689 |
+
"eval_samples_per_second": 1673.245,
|
| 690 |
+
"eval_steps_per_second": 105.692,
|
| 691 |
+
"eval_weighted_f1": 0.9433688451747941,
|
| 692 |
+
"step": 2220
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.013531799729364,
|
| 696 |
+
"grad_norm": 45.290061950683594,
|
| 697 |
+
"learning_rate": 1.5543543543543545e-05,
|
| 698 |
+
"loss": 0.59,
|
| 699 |
+
"step": 2225
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 6.081190798376184,
|
| 703 |
+
"grad_norm": 11.760050773620605,
|
| 704 |
+
"learning_rate": 1.546846846846847e-05,
|
| 705 |
+
"loss": 0.3506,
|
| 706 |
+
"step": 2250
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 6.148849797023004,
|
| 710 |
+
"grad_norm": 3.675795316696167,
|
| 711 |
+
"learning_rate": 1.5393393393393395e-05,
|
| 712 |
+
"loss": 0.3605,
|
| 713 |
+
"step": 2275
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 6.216508795669824,
|
| 717 |
+
"grad_norm": 16.916263580322266,
|
| 718 |
+
"learning_rate": 1.531831831831832e-05,
|
| 719 |
+
"loss": 0.2913,
|
| 720 |
+
"step": 2300
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 6.2841677943166445,
|
| 724 |
+
"grad_norm": 3.464608907699585,
|
| 725 |
+
"learning_rate": 1.5243243243243244e-05,
|
| 726 |
+
"loss": 0.3002,
|
| 727 |
+
"step": 2325
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 6.351826792963464,
|
| 731 |
+
"grad_norm": 0.1835533231496811,
|
| 732 |
+
"learning_rate": 1.5168168168168169e-05,
|
| 733 |
+
"loss": 0.5117,
|
| 734 |
+
"step": 2350
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 6.419485791610284,
|
| 738 |
+
"grad_norm": 0.5854179263114929,
|
| 739 |
+
"learning_rate": 1.5093093093093094e-05,
|
| 740 |
+
"loss": 0.2777,
|
| 741 |
+
"step": 2375
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.487144790257104,
|
| 745 |
+
"grad_norm": 9.520763397216797,
|
| 746 |
+
"learning_rate": 1.5018018018018019e-05,
|
| 747 |
+
"loss": 0.3583,
|
| 748 |
+
"step": 2400
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 6.554803788903924,
|
| 752 |
+
"grad_norm": 265.47479248046875,
|
| 753 |
+
"learning_rate": 1.4942942942942944e-05,
|
| 754 |
+
"loss": 0.5094,
|
| 755 |
+
"step": 2425
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 6.622462787550744,
|
| 759 |
+
"grad_norm": 20.088552474975586,
|
| 760 |
+
"learning_rate": 1.4867867867867869e-05,
|
| 761 |
+
"loss": 0.4087,
|
| 762 |
+
"step": 2450
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 6.690121786197564,
|
| 766 |
+
"grad_norm": 11.31855583190918,
|
| 767 |
+
"learning_rate": 1.4792792792792794e-05,
|
| 768 |
+
"loss": 0.4519,
|
| 769 |
+
"step": 2475
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 6.7577807848443845,
|
| 773 |
+
"grad_norm": 0.12511426210403442,
|
| 774 |
+
"learning_rate": 1.471771771771772e-05,
|
| 775 |
+
"loss": 0.2015,
|
| 776 |
+
"step": 2500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 6.825439783491205,
|
| 780 |
+
"grad_norm": 166.36672973632812,
|
| 781 |
+
"learning_rate": 1.4642642642642644e-05,
|
| 782 |
+
"loss": 0.5478,
|
| 783 |
+
"step": 2525
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.893098782138025,
|
| 787 |
+
"grad_norm": 22.8408260345459,
|
| 788 |
+
"learning_rate": 1.456756756756757e-05,
|
| 789 |
+
"loss": 0.3431,
|
| 790 |
+
"step": 2550
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 6.960757780784844,
|
| 794 |
+
"grad_norm": 3.156623125076294,
|
| 795 |
+
"learning_rate": 1.4492492492492493e-05,
|
| 796 |
+
"loss": 0.333,
|
| 797 |
+
"step": 2575
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.0,
|
| 801 |
+
"eval_accuracy": 0.941400304414003,
|
| 802 |
+
"eval_loss": 0.3151552975177765,
|
| 803 |
+
"eval_macro_f1": 0.8260405352177663,
|
| 804 |
+
"eval_runtime": 0.787,
|
| 805 |
+
"eval_samples_per_second": 1669.709,
|
| 806 |
+
"eval_steps_per_second": 105.469,
|
| 807 |
+
"eval_weighted_f1": 0.9388468658329389,
|
| 808 |
+
"step": 2590
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 7.027063599458728,
|
| 812 |
+
"grad_norm": 17.512296676635742,
|
| 813 |
+
"learning_rate": 1.4417417417417418e-05,
|
| 814 |
+
"loss": 0.4989,
|
| 815 |
+
"step": 2600
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 7.094722598105548,
|
| 819 |
+
"grad_norm": 22.670480728149414,
|
| 820 |
+
"learning_rate": 1.4342342342342343e-05,
|
| 821 |
+
"loss": 0.3511,
|
| 822 |
+
"step": 2625
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 7.162381596752368,
|
| 826 |
+
"grad_norm": 25.64103126525879,
|
| 827 |
+
"learning_rate": 1.4267267267267268e-05,
|
| 828 |
+
"loss": 0.181,
|
| 829 |
+
"step": 2650
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 7.230040595399188,
|
| 833 |
+
"grad_norm": 115.15301513671875,
|
| 834 |
+
"learning_rate": 1.4192192192192193e-05,
|
| 835 |
+
"loss": 0.1558,
|
| 836 |
+
"step": 2675
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 7.2976995940460085,
|
| 840 |
+
"grad_norm": 206.58592224121094,
|
| 841 |
+
"learning_rate": 1.4117117117117118e-05,
|
| 842 |
+
"loss": 0.3703,
|
| 843 |
+
"step": 2700
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 7.365358592692828,
|
| 847 |
+
"grad_norm": 8.046409606933594,
|
| 848 |
+
"learning_rate": 1.4042042042042044e-05,
|
| 849 |
+
"loss": 0.3749,
|
| 850 |
+
"step": 2725
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 7.433017591339648,
|
| 854 |
+
"grad_norm": 3.5705652236938477,
|
| 855 |
+
"learning_rate": 1.3966966966966969e-05,
|
| 856 |
+
"loss": 0.3956,
|
| 857 |
+
"step": 2750
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 7.500676589986468,
|
| 861 |
+
"grad_norm": 21.226919174194336,
|
| 862 |
+
"learning_rate": 1.3891891891891894e-05,
|
| 863 |
+
"loss": 0.2518,
|
| 864 |
+
"step": 2775
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 7.568335588633288,
|
| 868 |
+
"grad_norm": 3.3003616333007812,
|
| 869 |
+
"learning_rate": 1.3816816816816819e-05,
|
| 870 |
+
"loss": 0.3421,
|
| 871 |
+
"step": 2800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 7.635994587280108,
|
| 875 |
+
"grad_norm": 76.74018096923828,
|
| 876 |
+
"learning_rate": 1.3741741741741744e-05,
|
| 877 |
+
"loss": 0.1933,
|
| 878 |
+
"step": 2825
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 7.703653585926928,
|
| 882 |
+
"grad_norm": 49.078487396240234,
|
| 883 |
+
"learning_rate": 1.3666666666666667e-05,
|
| 884 |
+
"loss": 0.2906,
|
| 885 |
+
"step": 2850
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 7.7713125845737485,
|
| 889 |
+
"grad_norm": 0.10225020349025726,
|
| 890 |
+
"learning_rate": 1.3591591591591592e-05,
|
| 891 |
+
"loss": 0.3641,
|
| 892 |
+
"step": 2875
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 7.838971583220569,
|
| 896 |
+
"grad_norm": 0.11365645378828049,
|
| 897 |
+
"learning_rate": 1.3516516516516518e-05,
|
| 898 |
+
"loss": 0.511,
|
| 899 |
+
"step": 2900
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 7.906630581867388,
|
| 903 |
+
"grad_norm": 7.649621963500977,
|
| 904 |
+
"learning_rate": 1.3441441441441443e-05,
|
| 905 |
+
"loss": 0.3397,
|
| 906 |
+
"step": 2925
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 7.974289580514208,
|
| 910 |
+
"grad_norm": 152.66290283203125,
|
| 911 |
+
"learning_rate": 1.3366366366366368e-05,
|
| 912 |
+
"loss": 0.2573,
|
| 913 |
+
"step": 2950
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 8.0,
|
| 917 |
+
"eval_accuracy": 0.9398782343987824,
|
| 918 |
+
"eval_loss": 0.32418501377105713,
|
| 919 |
+
"eval_macro_f1": 0.822483284455136,
|
| 920 |
+
"eval_runtime": 0.9584,
|
| 921 |
+
"eval_samples_per_second": 1371.075,
|
| 922 |
+
"eval_steps_per_second": 86.605,
|
| 923 |
+
"eval_weighted_f1": 0.9393084646548103,
|
| 924 |
+
"step": 2960
|
| 925 |
+
}
|
| 926 |
+
],
|
| 927 |
+
"logging_steps": 25,
|
| 928 |
+
"max_steps": 7400,
|
| 929 |
+
"num_input_tokens_seen": 0,
|
| 930 |
+
"num_train_epochs": 20,
|
| 931 |
+
"save_steps": 500,
|
| 932 |
+
"stateful_callbacks": {
|
| 933 |
+
"EarlyStoppingCallback": {
|
| 934 |
+
"args": {
|
| 935 |
+
"early_stopping_patience": 3,
|
| 936 |
+
"early_stopping_threshold": 0.0
|
| 937 |
+
},
|
| 938 |
+
"attributes": {
|
| 939 |
+
"early_stopping_patience_counter": 3
|
| 940 |
+
}
|
| 941 |
+
},
|
| 942 |
+
"TrainerControl": {
|
| 943 |
+
"args": {
|
| 944 |
+
"should_epoch_stop": false,
|
| 945 |
+
"should_evaluate": false,
|
| 946 |
+
"should_log": false,
|
| 947 |
+
"should_save": true,
|
| 948 |
+
"should_training_stop": true
|
| 949 |
+
},
|
| 950 |
+
"attributes": {}
|
| 951 |
+
}
|
| 952 |
+
},
|
| 953 |
+
"total_flos": 0.0,
|
| 954 |
+
"train_batch_size": 8,
|
| 955 |
+
"trial_name": null,
|
| 956 |
+
"trial_params": null
|
| 957 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405/trainer_state.json
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 405,
|
| 3 |
+
"best_metric": 0.8188997821350763,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 405,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3115264797507788,
|
| 14 |
+
"grad_norm": 74.6605224609375,
|
| 15 |
+
"learning_rate": 2.962962962962963e-06,
|
| 16 |
+
"loss": 2.986,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6230529595015576,
|
| 21 |
+
"grad_norm": 32.803749084472656,
|
| 22 |
+
"learning_rate": 6.049382716049383e-06,
|
| 23 |
+
"loss": 2.5821,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9345794392523364,
|
| 28 |
+
"grad_norm": 20.16073226928711,
|
| 29 |
+
"learning_rate": 9.135802469135803e-06,
|
| 30 |
+
"loss": 2.3097,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.7368421052631579,
|
| 36 |
+
"eval_loss": 0.5478172302246094,
|
| 37 |
+
"eval_macro_f1": 0.42424242424242425,
|
| 38 |
+
"eval_runtime": 0.2582,
|
| 39 |
+
"eval_samples_per_second": 1104.004,
|
| 40 |
+
"eval_steps_per_second": 69.727,
|
| 41 |
+
"eval_weighted_f1": 0.6251993620414673,
|
| 42 |
+
"step": 81
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.236760124610592,
|
| 46 |
+
"grad_norm": 25.482816696166992,
|
| 47 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 48 |
+
"loss": 2.0857,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5482866043613708,
|
| 53 |
+
"grad_norm": 73.98408508300781,
|
| 54 |
+
"learning_rate": 1.5308641975308643e-05,
|
| 55 |
+
"loss": 1.9422,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8598130841121496,
|
| 60 |
+
"grad_norm": 26.87640953063965,
|
| 61 |
+
"learning_rate": 1.8395061728395062e-05,
|
| 62 |
+
"loss": 1.6741,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.8385964912280702,
|
| 68 |
+
"eval_loss": 0.34797748923301697,
|
| 69 |
+
"eval_macro_f1": 0.8031058512555569,
|
| 70 |
+
"eval_runtime": 0.2382,
|
| 71 |
+
"eval_samples_per_second": 1196.606,
|
| 72 |
+
"eval_steps_per_second": 75.575,
|
| 73 |
+
"eval_weighted_f1": 0.8427028462662123,
|
| 74 |
+
"step": 162
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.161993769470405,
|
| 78 |
+
"grad_norm": 29.568578720092773,
|
| 79 |
+
"learning_rate": 1.983539094650206e-05,
|
| 80 |
+
"loss": 1.4708,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.473520249221184,
|
| 85 |
+
"grad_norm": 56.66224670410156,
|
| 86 |
+
"learning_rate": 1.9492455418381347e-05,
|
| 87 |
+
"loss": 1.2967,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.7850467289719627,
|
| 92 |
+
"grad_norm": 26.60584831237793,
|
| 93 |
+
"learning_rate": 1.9149519890260632e-05,
|
| 94 |
+
"loss": 1.5522,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8245614035087719,
|
| 100 |
+
"eval_loss": 0.3954642713069916,
|
| 101 |
+
"eval_macro_f1": 0.7294166793255354,
|
| 102 |
+
"eval_runtime": 0.2436,
|
| 103 |
+
"eval_samples_per_second": 1169.958,
|
| 104 |
+
"eval_steps_per_second": 73.892,
|
| 105 |
+
"eval_weighted_f1": 0.805419861365399,
|
| 106 |
+
"step": 243
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.087227414330218,
|
| 110 |
+
"grad_norm": 18.310441970825195,
|
| 111 |
+
"learning_rate": 1.8806584362139917e-05,
|
| 112 |
+
"loss": 1.3305,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.398753894080997,
|
| 117 |
+
"grad_norm": 30.082311630249023,
|
| 118 |
+
"learning_rate": 1.8463648834019206e-05,
|
| 119 |
+
"loss": 0.9494,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.710280373831776,
|
| 124 |
+
"grad_norm": 29.69948387145996,
|
| 125 |
+
"learning_rate": 1.812071330589849e-05,
|
| 126 |
+
"loss": 0.9747,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8456140350877193,
|
| 132 |
+
"eval_loss": 0.3795156478881836,
|
| 133 |
+
"eval_macro_f1": 0.7875440498780157,
|
| 134 |
+
"eval_runtime": 0.241,
|
| 135 |
+
"eval_samples_per_second": 1182.661,
|
| 136 |
+
"eval_steps_per_second": 74.694,
|
| 137 |
+
"eval_weighted_f1": 0.8401577948666734,
|
| 138 |
+
"step": 324
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.012461059190031,
|
| 142 |
+
"grad_norm": 40.68852615356445,
|
| 143 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 144 |
+
"loss": 0.9144,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.32398753894081,
|
| 149 |
+
"grad_norm": 43.66241455078125,
|
| 150 |
+
"learning_rate": 1.7434842249657065e-05,
|
| 151 |
+
"loss": 0.6306,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.635514018691588,
|
| 156 |
+
"grad_norm": 15.007004737854004,
|
| 157 |
+
"learning_rate": 1.7091906721536354e-05,
|
| 158 |
+
"loss": 0.6864,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.947040498442368,
|
| 163 |
+
"grad_norm": 42.70766830444336,
|
| 164 |
+
"learning_rate": 1.674897119341564e-05,
|
| 165 |
+
"loss": 0.6598,
|
| 166 |
+
"step": 400
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.0,
|
| 170 |
+
"eval_accuracy": 0.8526315789473684,
|
| 171 |
+
"eval_loss": 0.3710324168205261,
|
| 172 |
+
"eval_macro_f1": 0.8188997821350763,
|
| 173 |
+
"eval_runtime": 0.2378,
|
| 174 |
+
"eval_samples_per_second": 1198.24,
|
| 175 |
+
"eval_steps_per_second": 75.678,
|
| 176 |
+
"eval_weighted_f1": 0.8559224859534457,
|
| 177 |
+
"step": 405
|
| 178 |
+
}
|
| 179 |
+
],
|
| 180 |
+
"logging_steps": 25,
|
| 181 |
+
"max_steps": 1620,
|
| 182 |
+
"num_input_tokens_seen": 0,
|
| 183 |
+
"num_train_epochs": 20,
|
| 184 |
+
"save_steps": 500,
|
| 185 |
+
"stateful_callbacks": {
|
| 186 |
+
"EarlyStoppingCallback": {
|
| 187 |
+
"args": {
|
| 188 |
+
"early_stopping_patience": 3,
|
| 189 |
+
"early_stopping_threshold": 0.0
|
| 190 |
+
},
|
| 191 |
+
"attributes": {
|
| 192 |
+
"early_stopping_patience_counter": 0
|
| 193 |
+
}
|
| 194 |
+
},
|
| 195 |
+
"TrainerControl": {
|
| 196 |
+
"args": {
|
| 197 |
+
"should_epoch_stop": false,
|
| 198 |
+
"should_evaluate": false,
|
| 199 |
+
"should_log": false,
|
| 200 |
+
"should_save": true,
|
| 201 |
+
"should_training_stop": false
|
| 202 |
+
},
|
| 203 |
+
"attributes": {}
|
| 204 |
+
}
|
| 205 |
+
},
|
| 206 |
+
"total_flos": 0.0,
|
| 207 |
+
"train_batch_size": 8,
|
| 208 |
+
"trial_name": null,
|
| 209 |
+
"trial_params": null
|
| 210 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-648/trainer_state.json
ADDED
|
@@ -0,0 +1,306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 405,
|
| 3 |
+
"best_metric": 0.8188997821350763,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-00-s42-20260827T171653Z-ee19aa8e/trainer/checkpoint-405",
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 648,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3115264797507788,
|
| 14 |
+
"grad_norm": 74.6605224609375,
|
| 15 |
+
"learning_rate": 2.962962962962963e-06,
|
| 16 |
+
"loss": 2.986,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6230529595015576,
|
| 21 |
+
"grad_norm": 32.803749084472656,
|
| 22 |
+
"learning_rate": 6.049382716049383e-06,
|
| 23 |
+
"loss": 2.5821,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9345794392523364,
|
| 28 |
+
"grad_norm": 20.16073226928711,
|
| 29 |
+
"learning_rate": 9.135802469135803e-06,
|
| 30 |
+
"loss": 2.3097,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.7368421052631579,
|
| 36 |
+
"eval_loss": 0.5478172302246094,
|
| 37 |
+
"eval_macro_f1": 0.42424242424242425,
|
| 38 |
+
"eval_runtime": 0.2582,
|
| 39 |
+
"eval_samples_per_second": 1104.004,
|
| 40 |
+
"eval_steps_per_second": 69.727,
|
| 41 |
+
"eval_weighted_f1": 0.6251993620414673,
|
| 42 |
+
"step": 81
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.236760124610592,
|
| 46 |
+
"grad_norm": 25.482816696166992,
|
| 47 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 48 |
+
"loss": 2.0857,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5482866043613708,
|
| 53 |
+
"grad_norm": 73.98408508300781,
|
| 54 |
+
"learning_rate": 1.5308641975308643e-05,
|
| 55 |
+
"loss": 1.9422,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8598130841121496,
|
| 60 |
+
"grad_norm": 26.87640953063965,
|
| 61 |
+
"learning_rate": 1.8395061728395062e-05,
|
| 62 |
+
"loss": 1.6741,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.8385964912280702,
|
| 68 |
+
"eval_loss": 0.34797748923301697,
|
| 69 |
+
"eval_macro_f1": 0.8031058512555569,
|
| 70 |
+
"eval_runtime": 0.2382,
|
| 71 |
+
"eval_samples_per_second": 1196.606,
|
| 72 |
+
"eval_steps_per_second": 75.575,
|
| 73 |
+
"eval_weighted_f1": 0.8427028462662123,
|
| 74 |
+
"step": 162
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.161993769470405,
|
| 78 |
+
"grad_norm": 29.568578720092773,
|
| 79 |
+
"learning_rate": 1.983539094650206e-05,
|
| 80 |
+
"loss": 1.4708,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.473520249221184,
|
| 85 |
+
"grad_norm": 56.66224670410156,
|
| 86 |
+
"learning_rate": 1.9492455418381347e-05,
|
| 87 |
+
"loss": 1.2967,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.7850467289719627,
|
| 92 |
+
"grad_norm": 26.60584831237793,
|
| 93 |
+
"learning_rate": 1.9149519890260632e-05,
|
| 94 |
+
"loss": 1.5522,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8245614035087719,
|
| 100 |
+
"eval_loss": 0.3954642713069916,
|
| 101 |
+
"eval_macro_f1": 0.7294166793255354,
|
| 102 |
+
"eval_runtime": 0.2436,
|
| 103 |
+
"eval_samples_per_second": 1169.958,
|
| 104 |
+
"eval_steps_per_second": 73.892,
|
| 105 |
+
"eval_weighted_f1": 0.805419861365399,
|
| 106 |
+
"step": 243
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.087227414330218,
|
| 110 |
+
"grad_norm": 18.310441970825195,
|
| 111 |
+
"learning_rate": 1.8806584362139917e-05,
|
| 112 |
+
"loss": 1.3305,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.398753894080997,
|
| 117 |
+
"grad_norm": 30.082311630249023,
|
| 118 |
+
"learning_rate": 1.8463648834019206e-05,
|
| 119 |
+
"loss": 0.9494,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.710280373831776,
|
| 124 |
+
"grad_norm": 29.69948387145996,
|
| 125 |
+
"learning_rate": 1.812071330589849e-05,
|
| 126 |
+
"loss": 0.9747,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8456140350877193,
|
| 132 |
+
"eval_loss": 0.3795156478881836,
|
| 133 |
+
"eval_macro_f1": 0.7875440498780157,
|
| 134 |
+
"eval_runtime": 0.241,
|
| 135 |
+
"eval_samples_per_second": 1182.661,
|
| 136 |
+
"eval_steps_per_second": 74.694,
|
| 137 |
+
"eval_weighted_f1": 0.8401577948666734,
|
| 138 |
+
"step": 324
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.012461059190031,
|
| 142 |
+
"grad_norm": 40.68852615356445,
|
| 143 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 144 |
+
"loss": 0.9144,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.32398753894081,
|
| 149 |
+
"grad_norm": 43.66241455078125,
|
| 150 |
+
"learning_rate": 1.7434842249657065e-05,
|
| 151 |
+
"loss": 0.6306,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.635514018691588,
|
| 156 |
+
"grad_norm": 15.007004737854004,
|
| 157 |
+
"learning_rate": 1.7091906721536354e-05,
|
| 158 |
+
"loss": 0.6864,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.947040498442368,
|
| 163 |
+
"grad_norm": 42.70766830444336,
|
| 164 |
+
"learning_rate": 1.674897119341564e-05,
|
| 165 |
+
"loss": 0.6598,
|
| 166 |
+
"step": 400
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.0,
|
| 170 |
+
"eval_accuracy": 0.8526315789473684,
|
| 171 |
+
"eval_loss": 0.3710324168205261,
|
| 172 |
+
"eval_macro_f1": 0.8188997821350763,
|
| 173 |
+
"eval_runtime": 0.2378,
|
| 174 |
+
"eval_samples_per_second": 1198.24,
|
| 175 |
+
"eval_steps_per_second": 75.678,
|
| 176 |
+
"eval_weighted_f1": 0.8559224859534457,
|
| 177 |
+
"step": 405
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.249221183800623,
|
| 181 |
+
"grad_norm": 74.53379821777344,
|
| 182 |
+
"learning_rate": 1.6406035665294924e-05,
|
| 183 |
+
"loss": 0.4279,
|
| 184 |
+
"step": 425
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.5607476635514015,
|
| 188 |
+
"grad_norm": 14.357966423034668,
|
| 189 |
+
"learning_rate": 1.6063100137174213e-05,
|
| 190 |
+
"loss": 0.4402,
|
| 191 |
+
"step": 450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.872274143302181,
|
| 195 |
+
"grad_norm": 93.94502258300781,
|
| 196 |
+
"learning_rate": 1.5720164609053498e-05,
|
| 197 |
+
"loss": 0.4423,
|
| 198 |
+
"step": 475
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.0,
|
| 202 |
+
"eval_accuracy": 0.8421052631578947,
|
| 203 |
+
"eval_loss": 0.5149381160736084,
|
| 204 |
+
"eval_macro_f1": 0.8022084792029733,
|
| 205 |
+
"eval_runtime": 0.231,
|
| 206 |
+
"eval_samples_per_second": 1233.665,
|
| 207 |
+
"eval_steps_per_second": 77.916,
|
| 208 |
+
"eval_weighted_f1": 0.8442871185304294,
|
| 209 |
+
"step": 486
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.174454828660436,
|
| 213 |
+
"grad_norm": 49.509578704833984,
|
| 214 |
+
"learning_rate": 1.5377229080932784e-05,
|
| 215 |
+
"loss": 0.5305,
|
| 216 |
+
"step": 500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 6.485981308411215,
|
| 220 |
+
"grad_norm": 88.38027954101562,
|
| 221 |
+
"learning_rate": 1.5034293552812072e-05,
|
| 222 |
+
"loss": 0.3848,
|
| 223 |
+
"step": 525
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 6.797507788161994,
|
| 227 |
+
"grad_norm": 106.94081115722656,
|
| 228 |
+
"learning_rate": 1.469135802469136e-05,
|
| 229 |
+
"loss": 0.3015,
|
| 230 |
+
"step": 550
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.0,
|
| 234 |
+
"eval_accuracy": 0.8421052631578947,
|
| 235 |
+
"eval_loss": 0.712656557559967,
|
| 236 |
+
"eval_macro_f1": 0.7793396534815299,
|
| 237 |
+
"eval_runtime": 0.2385,
|
| 238 |
+
"eval_samples_per_second": 1195.01,
|
| 239 |
+
"eval_steps_per_second": 75.474,
|
| 240 |
+
"eval_weighted_f1": 0.8350854252335643,
|
| 241 |
+
"step": 567
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 7.099688473520249,
|
| 245 |
+
"grad_norm": 87.89366149902344,
|
| 246 |
+
"learning_rate": 1.4348422496570646e-05,
|
| 247 |
+
"loss": 0.2763,
|
| 248 |
+
"step": 575
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.411214953271028,
|
| 252 |
+
"grad_norm": 102.92950439453125,
|
| 253 |
+
"learning_rate": 1.4005486968449933e-05,
|
| 254 |
+
"loss": 0.4516,
|
| 255 |
+
"step": 600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.722741433021807,
|
| 259 |
+
"grad_norm": 2.066065788269043,
|
| 260 |
+
"learning_rate": 1.366255144032922e-05,
|
| 261 |
+
"loss": 0.4423,
|
| 262 |
+
"step": 625
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 8.0,
|
| 266 |
+
"eval_accuracy": 0.8385964912280702,
|
| 267 |
+
"eval_loss": 0.7841327786445618,
|
| 268 |
+
"eval_macro_f1": 0.7953608891108891,
|
| 269 |
+
"eval_runtime": 0.257,
|
| 270 |
+
"eval_samples_per_second": 1108.74,
|
| 271 |
+
"eval_steps_per_second": 70.026,
|
| 272 |
+
"eval_weighted_f1": 0.8399166622850833,
|
| 273 |
+
"step": 648
|
| 274 |
+
}
|
| 275 |
+
],
|
| 276 |
+
"logging_steps": 25,
|
| 277 |
+
"max_steps": 1620,
|
| 278 |
+
"num_input_tokens_seen": 0,
|
| 279 |
+
"num_train_epochs": 20,
|
| 280 |
+
"save_steps": 500,
|
| 281 |
+
"stateful_callbacks": {
|
| 282 |
+
"EarlyStoppingCallback": {
|
| 283 |
+
"args": {
|
| 284 |
+
"early_stopping_patience": 3,
|
| 285 |
+
"early_stopping_threshold": 0.0
|
| 286 |
+
},
|
| 287 |
+
"attributes": {
|
| 288 |
+
"early_stopping_patience_counter": 3
|
| 289 |
+
}
|
| 290 |
+
},
|
| 291 |
+
"TrainerControl": {
|
| 292 |
+
"args": {
|
| 293 |
+
"should_epoch_stop": false,
|
| 294 |
+
"should_evaluate": false,
|
| 295 |
+
"should_log": false,
|
| 296 |
+
"should_save": true,
|
| 297 |
+
"should_training_stop": true
|
| 298 |
+
},
|
| 299 |
+
"attributes": {}
|
| 300 |
+
}
|
| 301 |
+
},
|
| 302 |
+
"total_flos": 0.0,
|
| 303 |
+
"train_batch_size": 8,
|
| 304 |
+
"trial_name": null,
|
| 305 |
+
"trial_params": null
|
| 306 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405/trainer_state.json
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 405,
|
| 3 |
+
"best_metric": 0.8243215476773775,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 405,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3115264797507788,
|
| 14 |
+
"grad_norm": 21.24897575378418,
|
| 15 |
+
"learning_rate": 2.962962962962963e-06,
|
| 16 |
+
"loss": 2.8071,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6230529595015576,
|
| 21 |
+
"grad_norm": 32.491214752197266,
|
| 22 |
+
"learning_rate": 6.049382716049383e-06,
|
| 23 |
+
"loss": 2.5157,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9345794392523364,
|
| 28 |
+
"grad_norm": 18.924034118652344,
|
| 29 |
+
"learning_rate": 9.135802469135803e-06,
|
| 30 |
+
"loss": 2.3872,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.7403508771929824,
|
| 36 |
+
"eval_loss": 0.5790091156959534,
|
| 37 |
+
"eval_macro_f1": 0.45043777360850534,
|
| 38 |
+
"eval_runtime": 0.2698,
|
| 39 |
+
"eval_samples_per_second": 1056.272,
|
| 40 |
+
"eval_steps_per_second": 66.712,
|
| 41 |
+
"eval_weighted_f1": 0.639511536815773,
|
| 42 |
+
"step": 81
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.236760124610592,
|
| 46 |
+
"grad_norm": 20.041439056396484,
|
| 47 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 48 |
+
"loss": 2.2483,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5482866043613708,
|
| 53 |
+
"grad_norm": 51.579586029052734,
|
| 54 |
+
"learning_rate": 1.5308641975308643e-05,
|
| 55 |
+
"loss": 2.2483,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8598130841121496,
|
| 60 |
+
"grad_norm": 30.99344253540039,
|
| 61 |
+
"learning_rate": 1.8395061728395062e-05,
|
| 62 |
+
"loss": 1.9011,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.8035087719298246,
|
| 68 |
+
"eval_loss": 0.38539478182792664,
|
| 69 |
+
"eval_macro_f1": 0.7147147147147147,
|
| 70 |
+
"eval_runtime": 0.2679,
|
| 71 |
+
"eval_samples_per_second": 1063.94,
|
| 72 |
+
"eval_steps_per_second": 67.196,
|
| 73 |
+
"eval_weighted_f1": 0.7901058953690533,
|
| 74 |
+
"step": 162
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.161993769470405,
|
| 78 |
+
"grad_norm": 46.52235794067383,
|
| 79 |
+
"learning_rate": 1.983539094650206e-05,
|
| 80 |
+
"loss": 1.6991,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.473520249221184,
|
| 85 |
+
"grad_norm": 30.829317092895508,
|
| 86 |
+
"learning_rate": 1.9492455418381347e-05,
|
| 87 |
+
"loss": 1.3303,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.7850467289719627,
|
| 92 |
+
"grad_norm": 33.438621520996094,
|
| 93 |
+
"learning_rate": 1.9149519890260632e-05,
|
| 94 |
+
"loss": 1.4532,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8175438596491228,
|
| 100 |
+
"eval_loss": 0.38704320788383484,
|
| 101 |
+
"eval_macro_f1": 0.7489156953103822,
|
| 102 |
+
"eval_runtime": 0.2519,
|
| 103 |
+
"eval_samples_per_second": 1131.462,
|
| 104 |
+
"eval_steps_per_second": 71.461,
|
| 105 |
+
"eval_weighted_f1": 0.8110955757515231,
|
| 106 |
+
"step": 243
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.087227414330218,
|
| 110 |
+
"grad_norm": 35.07852554321289,
|
| 111 |
+
"learning_rate": 1.8806584362139917e-05,
|
| 112 |
+
"loss": 1.2798,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.398753894080997,
|
| 117 |
+
"grad_norm": 46.10211944580078,
|
| 118 |
+
"learning_rate": 1.8463648834019206e-05,
|
| 119 |
+
"loss": 1.1157,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.710280373831776,
|
| 124 |
+
"grad_norm": 50.647193908691406,
|
| 125 |
+
"learning_rate": 1.812071330589849e-05,
|
| 126 |
+
"loss": 0.9991,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8491228070175438,
|
| 132 |
+
"eval_loss": 0.35041648149490356,
|
| 133 |
+
"eval_macro_f1": 0.8046358143761259,
|
| 134 |
+
"eval_runtime": 0.2684,
|
| 135 |
+
"eval_samples_per_second": 1061.804,
|
| 136 |
+
"eval_steps_per_second": 67.061,
|
| 137 |
+
"eval_weighted_f1": 0.8487956967775334,
|
| 138 |
+
"step": 324
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.012461059190031,
|
| 142 |
+
"grad_norm": 16.286457061767578,
|
| 143 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 144 |
+
"loss": 0.9097,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.32398753894081,
|
| 149 |
+
"grad_norm": 57.44338607788086,
|
| 150 |
+
"learning_rate": 1.7434842249657065e-05,
|
| 151 |
+
"loss": 0.7571,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.635514018691588,
|
| 156 |
+
"grad_norm": 71.78002166748047,
|
| 157 |
+
"learning_rate": 1.7091906721536354e-05,
|
| 158 |
+
"loss": 0.7307,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.947040498442368,
|
| 163 |
+
"grad_norm": 18.25688934326172,
|
| 164 |
+
"learning_rate": 1.674897119341564e-05,
|
| 165 |
+
"loss": 1.0148,
|
| 166 |
+
"step": 400
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.0,
|
| 170 |
+
"eval_accuracy": 0.8631578947368421,
|
| 171 |
+
"eval_loss": 0.3332683742046356,
|
| 172 |
+
"eval_macro_f1": 0.8243215476773775,
|
| 173 |
+
"eval_runtime": 0.2875,
|
| 174 |
+
"eval_samples_per_second": 991.363,
|
| 175 |
+
"eval_steps_per_second": 62.612,
|
| 176 |
+
"eval_weighted_f1": 0.8634477182223605,
|
| 177 |
+
"step": 405
|
| 178 |
+
}
|
| 179 |
+
],
|
| 180 |
+
"logging_steps": 25,
|
| 181 |
+
"max_steps": 1620,
|
| 182 |
+
"num_input_tokens_seen": 0,
|
| 183 |
+
"num_train_epochs": 20,
|
| 184 |
+
"save_steps": 500,
|
| 185 |
+
"stateful_callbacks": {
|
| 186 |
+
"EarlyStoppingCallback": {
|
| 187 |
+
"args": {
|
| 188 |
+
"early_stopping_patience": 3,
|
| 189 |
+
"early_stopping_threshold": 0.0
|
| 190 |
+
},
|
| 191 |
+
"attributes": {
|
| 192 |
+
"early_stopping_patience_counter": 0
|
| 193 |
+
}
|
| 194 |
+
},
|
| 195 |
+
"TrainerControl": {
|
| 196 |
+
"args": {
|
| 197 |
+
"should_epoch_stop": false,
|
| 198 |
+
"should_evaluate": false,
|
| 199 |
+
"should_log": false,
|
| 200 |
+
"should_save": true,
|
| 201 |
+
"should_training_stop": false
|
| 202 |
+
},
|
| 203 |
+
"attributes": {}
|
| 204 |
+
}
|
| 205 |
+
},
|
| 206 |
+
"total_flos": 0.0,
|
| 207 |
+
"train_batch_size": 8,
|
| 208 |
+
"trial_name": null,
|
| 209 |
+
"trial_params": null
|
| 210 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-648/trainer_state.json
ADDED
|
@@ -0,0 +1,306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 405,
|
| 3 |
+
"best_metric": 0.8243215476773775,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-00-s43-20260827T172817Z-32d744c6/trainer/checkpoint-405",
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 648,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3115264797507788,
|
| 14 |
+
"grad_norm": 21.24897575378418,
|
| 15 |
+
"learning_rate": 2.962962962962963e-06,
|
| 16 |
+
"loss": 2.8071,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6230529595015576,
|
| 21 |
+
"grad_norm": 32.491214752197266,
|
| 22 |
+
"learning_rate": 6.049382716049383e-06,
|
| 23 |
+
"loss": 2.5157,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9345794392523364,
|
| 28 |
+
"grad_norm": 18.924034118652344,
|
| 29 |
+
"learning_rate": 9.135802469135803e-06,
|
| 30 |
+
"loss": 2.3872,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.7403508771929824,
|
| 36 |
+
"eval_loss": 0.5790091156959534,
|
| 37 |
+
"eval_macro_f1": 0.45043777360850534,
|
| 38 |
+
"eval_runtime": 0.2698,
|
| 39 |
+
"eval_samples_per_second": 1056.272,
|
| 40 |
+
"eval_steps_per_second": 66.712,
|
| 41 |
+
"eval_weighted_f1": 0.639511536815773,
|
| 42 |
+
"step": 81
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.236760124610592,
|
| 46 |
+
"grad_norm": 20.041439056396484,
|
| 47 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 48 |
+
"loss": 2.2483,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5482866043613708,
|
| 53 |
+
"grad_norm": 51.579586029052734,
|
| 54 |
+
"learning_rate": 1.5308641975308643e-05,
|
| 55 |
+
"loss": 2.2483,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8598130841121496,
|
| 60 |
+
"grad_norm": 30.99344253540039,
|
| 61 |
+
"learning_rate": 1.8395061728395062e-05,
|
| 62 |
+
"loss": 1.9011,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.8035087719298246,
|
| 68 |
+
"eval_loss": 0.38539478182792664,
|
| 69 |
+
"eval_macro_f1": 0.7147147147147147,
|
| 70 |
+
"eval_runtime": 0.2679,
|
| 71 |
+
"eval_samples_per_second": 1063.94,
|
| 72 |
+
"eval_steps_per_second": 67.196,
|
| 73 |
+
"eval_weighted_f1": 0.7901058953690533,
|
| 74 |
+
"step": 162
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.161993769470405,
|
| 78 |
+
"grad_norm": 46.52235794067383,
|
| 79 |
+
"learning_rate": 1.983539094650206e-05,
|
| 80 |
+
"loss": 1.6991,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.473520249221184,
|
| 85 |
+
"grad_norm": 30.829317092895508,
|
| 86 |
+
"learning_rate": 1.9492455418381347e-05,
|
| 87 |
+
"loss": 1.3303,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.7850467289719627,
|
| 92 |
+
"grad_norm": 33.438621520996094,
|
| 93 |
+
"learning_rate": 1.9149519890260632e-05,
|
| 94 |
+
"loss": 1.4532,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8175438596491228,
|
| 100 |
+
"eval_loss": 0.38704320788383484,
|
| 101 |
+
"eval_macro_f1": 0.7489156953103822,
|
| 102 |
+
"eval_runtime": 0.2519,
|
| 103 |
+
"eval_samples_per_second": 1131.462,
|
| 104 |
+
"eval_steps_per_second": 71.461,
|
| 105 |
+
"eval_weighted_f1": 0.8110955757515231,
|
| 106 |
+
"step": 243
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.087227414330218,
|
| 110 |
+
"grad_norm": 35.07852554321289,
|
| 111 |
+
"learning_rate": 1.8806584362139917e-05,
|
| 112 |
+
"loss": 1.2798,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.398753894080997,
|
| 117 |
+
"grad_norm": 46.10211944580078,
|
| 118 |
+
"learning_rate": 1.8463648834019206e-05,
|
| 119 |
+
"loss": 1.1157,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.710280373831776,
|
| 124 |
+
"grad_norm": 50.647193908691406,
|
| 125 |
+
"learning_rate": 1.812071330589849e-05,
|
| 126 |
+
"loss": 0.9991,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8491228070175438,
|
| 132 |
+
"eval_loss": 0.35041648149490356,
|
| 133 |
+
"eval_macro_f1": 0.8046358143761259,
|
| 134 |
+
"eval_runtime": 0.2684,
|
| 135 |
+
"eval_samples_per_second": 1061.804,
|
| 136 |
+
"eval_steps_per_second": 67.061,
|
| 137 |
+
"eval_weighted_f1": 0.8487956967775334,
|
| 138 |
+
"step": 324
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.012461059190031,
|
| 142 |
+
"grad_norm": 16.286457061767578,
|
| 143 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 144 |
+
"loss": 0.9097,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.32398753894081,
|
| 149 |
+
"grad_norm": 57.44338607788086,
|
| 150 |
+
"learning_rate": 1.7434842249657065e-05,
|
| 151 |
+
"loss": 0.7571,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.635514018691588,
|
| 156 |
+
"grad_norm": 71.78002166748047,
|
| 157 |
+
"learning_rate": 1.7091906721536354e-05,
|
| 158 |
+
"loss": 0.7307,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.947040498442368,
|
| 163 |
+
"grad_norm": 18.25688934326172,
|
| 164 |
+
"learning_rate": 1.674897119341564e-05,
|
| 165 |
+
"loss": 1.0148,
|
| 166 |
+
"step": 400
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.0,
|
| 170 |
+
"eval_accuracy": 0.8631578947368421,
|
| 171 |
+
"eval_loss": 0.3332683742046356,
|
| 172 |
+
"eval_macro_f1": 0.8243215476773775,
|
| 173 |
+
"eval_runtime": 0.2875,
|
| 174 |
+
"eval_samples_per_second": 991.363,
|
| 175 |
+
"eval_steps_per_second": 62.612,
|
| 176 |
+
"eval_weighted_f1": 0.8634477182223605,
|
| 177 |
+
"step": 405
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.249221183800623,
|
| 181 |
+
"grad_norm": 13.496033668518066,
|
| 182 |
+
"learning_rate": 1.6406035665294924e-05,
|
| 183 |
+
"loss": 0.6095,
|
| 184 |
+
"step": 425
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.5607476635514015,
|
| 188 |
+
"grad_norm": 57.01813507080078,
|
| 189 |
+
"learning_rate": 1.6063100137174213e-05,
|
| 190 |
+
"loss": 0.5563,
|
| 191 |
+
"step": 450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.872274143302181,
|
| 195 |
+
"grad_norm": 20.31565284729004,
|
| 196 |
+
"learning_rate": 1.5720164609053498e-05,
|
| 197 |
+
"loss": 0.5987,
|
| 198 |
+
"step": 475
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.0,
|
| 202 |
+
"eval_accuracy": 0.8526315789473684,
|
| 203 |
+
"eval_loss": 0.42762887477874756,
|
| 204 |
+
"eval_macro_f1": 0.8131555944055944,
|
| 205 |
+
"eval_runtime": 0.2532,
|
| 206 |
+
"eval_samples_per_second": 1125.629,
|
| 207 |
+
"eval_steps_per_second": 71.092,
|
| 208 |
+
"eval_weighted_f1": 0.8538369525211631,
|
| 209 |
+
"step": 486
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.174454828660436,
|
| 213 |
+
"grad_norm": 68.44770050048828,
|
| 214 |
+
"learning_rate": 1.5377229080932784e-05,
|
| 215 |
+
"loss": 0.3781,
|
| 216 |
+
"step": 500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 6.485981308411215,
|
| 220 |
+
"grad_norm": 1.2322463989257812,
|
| 221 |
+
"learning_rate": 1.5034293552812072e-05,
|
| 222 |
+
"loss": 0.2263,
|
| 223 |
+
"step": 525
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 6.797507788161994,
|
| 227 |
+
"grad_norm": 121.1266098022461,
|
| 228 |
+
"learning_rate": 1.469135802469136e-05,
|
| 229 |
+
"loss": 0.6143,
|
| 230 |
+
"step": 550
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.0,
|
| 234 |
+
"eval_accuracy": 0.8456140350877193,
|
| 235 |
+
"eval_loss": 0.6453030705451965,
|
| 236 |
+
"eval_macro_f1": 0.7992186499295504,
|
| 237 |
+
"eval_runtime": 0.2634,
|
| 238 |
+
"eval_samples_per_second": 1081.98,
|
| 239 |
+
"eval_steps_per_second": 68.336,
|
| 240 |
+
"eval_weighted_f1": 0.8449367301948995,
|
| 241 |
+
"step": 567
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 7.099688473520249,
|
| 245 |
+
"grad_norm": 2.986179828643799,
|
| 246 |
+
"learning_rate": 1.4348422496570646e-05,
|
| 247 |
+
"loss": 0.3853,
|
| 248 |
+
"step": 575
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.411214953271028,
|
| 252 |
+
"grad_norm": 3.9859023094177246,
|
| 253 |
+
"learning_rate": 1.4005486968449933e-05,
|
| 254 |
+
"loss": 0.228,
|
| 255 |
+
"step": 600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.722741433021807,
|
| 259 |
+
"grad_norm": 115.37552642822266,
|
| 260 |
+
"learning_rate": 1.366255144032922e-05,
|
| 261 |
+
"loss": 0.4523,
|
| 262 |
+
"step": 625
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 8.0,
|
| 266 |
+
"eval_accuracy": 0.8385964912280702,
|
| 267 |
+
"eval_loss": 0.7025076150894165,
|
| 268 |
+
"eval_macro_f1": 0.7842898512570752,
|
| 269 |
+
"eval_runtime": 0.2593,
|
| 270 |
+
"eval_samples_per_second": 1099.043,
|
| 271 |
+
"eval_steps_per_second": 69.413,
|
| 272 |
+
"eval_weighted_f1": 0.8355583575233991,
|
| 273 |
+
"step": 648
|
| 274 |
+
}
|
| 275 |
+
],
|
| 276 |
+
"logging_steps": 25,
|
| 277 |
+
"max_steps": 1620,
|
| 278 |
+
"num_input_tokens_seen": 0,
|
| 279 |
+
"num_train_epochs": 20,
|
| 280 |
+
"save_steps": 500,
|
| 281 |
+
"stateful_callbacks": {
|
| 282 |
+
"EarlyStoppingCallback": {
|
| 283 |
+
"args": {
|
| 284 |
+
"early_stopping_patience": 3,
|
| 285 |
+
"early_stopping_threshold": 0.0
|
| 286 |
+
},
|
| 287 |
+
"attributes": {
|
| 288 |
+
"early_stopping_patience_counter": 3
|
| 289 |
+
}
|
| 290 |
+
},
|
| 291 |
+
"TrainerControl": {
|
| 292 |
+
"args": {
|
| 293 |
+
"should_epoch_stop": false,
|
| 294 |
+
"should_evaluate": false,
|
| 295 |
+
"should_log": false,
|
| 296 |
+
"should_save": true,
|
| 297 |
+
"should_training_stop": true
|
| 298 |
+
},
|
| 299 |
+
"attributes": {}
|
| 300 |
+
}
|
| 301 |
+
},
|
| 302 |
+
"total_flos": 0.0,
|
| 303 |
+
"train_batch_size": 8,
|
| 304 |
+
"trial_name": null,
|
| 305 |
+
"trial_params": null
|
| 306 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304/trainer_state.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 304,
|
| 3 |
+
"best_metric": 0.840828402366864,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 304,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.33112582781456956,
|
| 14 |
+
"grad_norm": 27.125289916992188,
|
| 15 |
+
"learning_rate": 3.157894736842105e-06,
|
| 16 |
+
"loss": 2.941,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6622516556291391,
|
| 21 |
+
"grad_norm": 13.892107963562012,
|
| 22 |
+
"learning_rate": 6.447368421052632e-06,
|
| 23 |
+
"loss": 2.6557,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9933774834437086,
|
| 28 |
+
"grad_norm": 23.493927001953125,
|
| 29 |
+
"learning_rate": 9.736842105263159e-06,
|
| 30 |
+
"loss": 2.5564,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6468401486988847,
|
| 36 |
+
"eval_loss": 0.6324349641799927,
|
| 37 |
+
"eval_macro_f1": 0.3927765237020316,
|
| 38 |
+
"eval_runtime": 0.2351,
|
| 39 |
+
"eval_samples_per_second": 1144.36,
|
| 40 |
+
"eval_steps_per_second": 72.32,
|
| 41 |
+
"eval_weighted_f1": 0.5081272499937063,
|
| 42 |
+
"step": 76
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.3178807947019868,
|
| 46 |
+
"grad_norm": 22.98215675354004,
|
| 47 |
+
"learning_rate": 1.3026315789473684e-05,
|
| 48 |
+
"loss": 2.4406,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.6490066225165563,
|
| 53 |
+
"grad_norm": 52.174076080322266,
|
| 54 |
+
"learning_rate": 1.6315789473684213e-05,
|
| 55 |
+
"loss": 2.219,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.980132450331126,
|
| 60 |
+
"grad_norm": 35.46211624145508,
|
| 61 |
+
"learning_rate": 1.960526315789474e-05,
|
| 62 |
+
"loss": 1.8057,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.7769516728624535,
|
| 68 |
+
"eval_loss": 0.4137992858886719,
|
| 69 |
+
"eval_macro_f1": 0.7249113716934824,
|
| 70 |
+
"eval_runtime": 0.3246,
|
| 71 |
+
"eval_samples_per_second": 828.611,
|
| 72 |
+
"eval_steps_per_second": 52.366,
|
| 73 |
+
"eval_weighted_f1": 0.7600496947050099,
|
| 74 |
+
"step": 152
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.304635761589404,
|
| 78 |
+
"grad_norm": 22.65528678894043,
|
| 79 |
+
"learning_rate": 1.9678362573099416e-05,
|
| 80 |
+
"loss": 1.6003,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.6357615894039736,
|
| 85 |
+
"grad_norm": 49.942893981933594,
|
| 86 |
+
"learning_rate": 1.9312865497076027e-05,
|
| 87 |
+
"loss": 1.5183,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.966887417218543,
|
| 92 |
+
"grad_norm": 36.1726188659668,
|
| 93 |
+
"learning_rate": 1.894736842105263e-05,
|
| 94 |
+
"loss": 1.52,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8513011152416357,
|
| 100 |
+
"eval_loss": 0.33471089601516724,
|
| 101 |
+
"eval_macro_f1": 0.8380298651252408,
|
| 102 |
+
"eval_runtime": 0.2418,
|
| 103 |
+
"eval_samples_per_second": 1112.522,
|
| 104 |
+
"eval_steps_per_second": 70.308,
|
| 105 |
+
"eval_weighted_f1": 0.8516458230368668,
|
| 106 |
+
"step": 228
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.2913907284768213,
|
| 110 |
+
"grad_norm": 83.95234680175781,
|
| 111 |
+
"learning_rate": 1.8581871345029242e-05,
|
| 112 |
+
"loss": 1.0833,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.622516556291391,
|
| 117 |
+
"grad_norm": 46.81095886230469,
|
| 118 |
+
"learning_rate": 1.821637426900585e-05,
|
| 119 |
+
"loss": 1.2554,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.9536423841059603,
|
| 124 |
+
"grad_norm": 26.40545654296875,
|
| 125 |
+
"learning_rate": 1.785087719298246e-05,
|
| 126 |
+
"loss": 1.2182,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8513011152416357,
|
| 132 |
+
"eval_loss": 0.35946735739707947,
|
| 133 |
+
"eval_macro_f1": 0.840828402366864,
|
| 134 |
+
"eval_runtime": 0.2205,
|
| 135 |
+
"eval_samples_per_second": 1220.055,
|
| 136 |
+
"eval_steps_per_second": 77.104,
|
| 137 |
+
"eval_weighted_f1": 0.8528188997162403,
|
| 138 |
+
"step": 304
|
| 139 |
+
}
|
| 140 |
+
],
|
| 141 |
+
"logging_steps": 25,
|
| 142 |
+
"max_steps": 1520,
|
| 143 |
+
"num_input_tokens_seen": 0,
|
| 144 |
+
"num_train_epochs": 20,
|
| 145 |
+
"save_steps": 500,
|
| 146 |
+
"stateful_callbacks": {
|
| 147 |
+
"EarlyStoppingCallback": {
|
| 148 |
+
"args": {
|
| 149 |
+
"early_stopping_patience": 3,
|
| 150 |
+
"early_stopping_threshold": 0.0
|
| 151 |
+
},
|
| 152 |
+
"attributes": {
|
| 153 |
+
"early_stopping_patience_counter": 0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"TrainerControl": {
|
| 157 |
+
"args": {
|
| 158 |
+
"should_epoch_stop": false,
|
| 159 |
+
"should_evaluate": false,
|
| 160 |
+
"should_log": false,
|
| 161 |
+
"should_save": true,
|
| 162 |
+
"should_training_stop": false
|
| 163 |
+
},
|
| 164 |
+
"attributes": {}
|
| 165 |
+
}
|
| 166 |
+
},
|
| 167 |
+
"total_flos": 0.0,
|
| 168 |
+
"train_batch_size": 8,
|
| 169 |
+
"trial_name": null,
|
| 170 |
+
"trial_params": null
|
| 171 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-532/trainer_state.json
ADDED
|
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 304,
|
| 3 |
+
"best_metric": 0.840828402366864,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-01-s42-20260827T171817Z-ee19aa8e/trainer/checkpoint-304",
|
| 5 |
+
"epoch": 7.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 532,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.33112582781456956,
|
| 14 |
+
"grad_norm": 27.125289916992188,
|
| 15 |
+
"learning_rate": 3.157894736842105e-06,
|
| 16 |
+
"loss": 2.941,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6622516556291391,
|
| 21 |
+
"grad_norm": 13.892107963562012,
|
| 22 |
+
"learning_rate": 6.447368421052632e-06,
|
| 23 |
+
"loss": 2.6557,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9933774834437086,
|
| 28 |
+
"grad_norm": 23.493927001953125,
|
| 29 |
+
"learning_rate": 9.736842105263159e-06,
|
| 30 |
+
"loss": 2.5564,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6468401486988847,
|
| 36 |
+
"eval_loss": 0.6324349641799927,
|
| 37 |
+
"eval_macro_f1": 0.3927765237020316,
|
| 38 |
+
"eval_runtime": 0.2351,
|
| 39 |
+
"eval_samples_per_second": 1144.36,
|
| 40 |
+
"eval_steps_per_second": 72.32,
|
| 41 |
+
"eval_weighted_f1": 0.5081272499937063,
|
| 42 |
+
"step": 76
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.3178807947019868,
|
| 46 |
+
"grad_norm": 22.98215675354004,
|
| 47 |
+
"learning_rate": 1.3026315789473684e-05,
|
| 48 |
+
"loss": 2.4406,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.6490066225165563,
|
| 53 |
+
"grad_norm": 52.174076080322266,
|
| 54 |
+
"learning_rate": 1.6315789473684213e-05,
|
| 55 |
+
"loss": 2.219,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.980132450331126,
|
| 60 |
+
"grad_norm": 35.46211624145508,
|
| 61 |
+
"learning_rate": 1.960526315789474e-05,
|
| 62 |
+
"loss": 1.8057,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.7769516728624535,
|
| 68 |
+
"eval_loss": 0.4137992858886719,
|
| 69 |
+
"eval_macro_f1": 0.7249113716934824,
|
| 70 |
+
"eval_runtime": 0.3246,
|
| 71 |
+
"eval_samples_per_second": 828.611,
|
| 72 |
+
"eval_steps_per_second": 52.366,
|
| 73 |
+
"eval_weighted_f1": 0.7600496947050099,
|
| 74 |
+
"step": 152
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.304635761589404,
|
| 78 |
+
"grad_norm": 22.65528678894043,
|
| 79 |
+
"learning_rate": 1.9678362573099416e-05,
|
| 80 |
+
"loss": 1.6003,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.6357615894039736,
|
| 85 |
+
"grad_norm": 49.942893981933594,
|
| 86 |
+
"learning_rate": 1.9312865497076027e-05,
|
| 87 |
+
"loss": 1.5183,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.966887417218543,
|
| 92 |
+
"grad_norm": 36.1726188659668,
|
| 93 |
+
"learning_rate": 1.894736842105263e-05,
|
| 94 |
+
"loss": 1.52,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8513011152416357,
|
| 100 |
+
"eval_loss": 0.33471089601516724,
|
| 101 |
+
"eval_macro_f1": 0.8380298651252408,
|
| 102 |
+
"eval_runtime": 0.2418,
|
| 103 |
+
"eval_samples_per_second": 1112.522,
|
| 104 |
+
"eval_steps_per_second": 70.308,
|
| 105 |
+
"eval_weighted_f1": 0.8516458230368668,
|
| 106 |
+
"step": 228
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.2913907284768213,
|
| 110 |
+
"grad_norm": 83.95234680175781,
|
| 111 |
+
"learning_rate": 1.8581871345029242e-05,
|
| 112 |
+
"loss": 1.0833,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.622516556291391,
|
| 117 |
+
"grad_norm": 46.81095886230469,
|
| 118 |
+
"learning_rate": 1.821637426900585e-05,
|
| 119 |
+
"loss": 1.2554,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.9536423841059603,
|
| 124 |
+
"grad_norm": 26.40545654296875,
|
| 125 |
+
"learning_rate": 1.785087719298246e-05,
|
| 126 |
+
"loss": 1.2182,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8513011152416357,
|
| 132 |
+
"eval_loss": 0.35946735739707947,
|
| 133 |
+
"eval_macro_f1": 0.840828402366864,
|
| 134 |
+
"eval_runtime": 0.2205,
|
| 135 |
+
"eval_samples_per_second": 1220.055,
|
| 136 |
+
"eval_steps_per_second": 77.104,
|
| 137 |
+
"eval_weighted_f1": 0.8528188997162403,
|
| 138 |
+
"step": 304
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.2781456953642385,
|
| 142 |
+
"grad_norm": 51.75857925415039,
|
| 143 |
+
"learning_rate": 1.7485380116959064e-05,
|
| 144 |
+
"loss": 0.8731,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.609271523178808,
|
| 149 |
+
"grad_norm": 40.995330810546875,
|
| 150 |
+
"learning_rate": 1.7119883040935675e-05,
|
| 151 |
+
"loss": 0.7769,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.940397350993377,
|
| 156 |
+
"grad_norm": 39.89021301269531,
|
| 157 |
+
"learning_rate": 1.6754385964912282e-05,
|
| 158 |
+
"loss": 0.9406,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.0,
|
| 163 |
+
"eval_accuracy": 0.7806691449814126,
|
| 164 |
+
"eval_loss": 0.5851720571517944,
|
| 165 |
+
"eval_macro_f1": 0.7190227494024962,
|
| 166 |
+
"eval_runtime": 0.2472,
|
| 167 |
+
"eval_samples_per_second": 1088.098,
|
| 168 |
+
"eval_steps_per_second": 68.765,
|
| 169 |
+
"eval_weighted_f1": 0.7576740609162612,
|
| 170 |
+
"step": 380
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.264900662251655,
|
| 174 |
+
"grad_norm": 50.7684440612793,
|
| 175 |
+
"learning_rate": 1.638888888888889e-05,
|
| 176 |
+
"loss": 0.8143,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.596026490066225,
|
| 181 |
+
"grad_norm": 16.185564041137695,
|
| 182 |
+
"learning_rate": 1.60233918128655e-05,
|
| 183 |
+
"loss": 0.6104,
|
| 184 |
+
"step": 425
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.927152317880795,
|
| 188 |
+
"grad_norm": 20.571857452392578,
|
| 189 |
+
"learning_rate": 1.5657894736842107e-05,
|
| 190 |
+
"loss": 0.7008,
|
| 191 |
+
"step": 450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.0,
|
| 195 |
+
"eval_accuracy": 0.828996282527881,
|
| 196 |
+
"eval_loss": 0.5399294495582581,
|
| 197 |
+
"eval_macro_f1": 0.8046292787672098,
|
| 198 |
+
"eval_runtime": 0.2389,
|
| 199 |
+
"eval_samples_per_second": 1126.049,
|
| 200 |
+
"eval_steps_per_second": 71.163,
|
| 201 |
+
"eval_weighted_f1": 0.8248923661050311,
|
| 202 |
+
"step": 456
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.251655629139073,
|
| 206 |
+
"grad_norm": 57.705810546875,
|
| 207 |
+
"learning_rate": 1.5292397660818715e-05,
|
| 208 |
+
"loss": 0.5516,
|
| 209 |
+
"step": 475
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.582781456953643,
|
| 213 |
+
"grad_norm": 88.18408203125,
|
| 214 |
+
"learning_rate": 1.4926900584795322e-05,
|
| 215 |
+
"loss": 0.4566,
|
| 216 |
+
"step": 500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 6.913907284768212,
|
| 220 |
+
"grad_norm": 9.079241752624512,
|
| 221 |
+
"learning_rate": 1.4561403508771931e-05,
|
| 222 |
+
"loss": 0.5492,
|
| 223 |
+
"step": 525
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 7.0,
|
| 227 |
+
"eval_accuracy": 0.8252788104089219,
|
| 228 |
+
"eval_loss": 0.514789342880249,
|
| 229 |
+
"eval_macro_f1": 0.8125880138153896,
|
| 230 |
+
"eval_runtime": 0.2462,
|
| 231 |
+
"eval_samples_per_second": 1092.4,
|
| 232 |
+
"eval_steps_per_second": 69.036,
|
| 233 |
+
"eval_weighted_f1": 0.8269104842566619,
|
| 234 |
+
"step": 532
|
| 235 |
+
}
|
| 236 |
+
],
|
| 237 |
+
"logging_steps": 25,
|
| 238 |
+
"max_steps": 1520,
|
| 239 |
+
"num_input_tokens_seen": 0,
|
| 240 |
+
"num_train_epochs": 20,
|
| 241 |
+
"save_steps": 500,
|
| 242 |
+
"stateful_callbacks": {
|
| 243 |
+
"EarlyStoppingCallback": {
|
| 244 |
+
"args": {
|
| 245 |
+
"early_stopping_patience": 3,
|
| 246 |
+
"early_stopping_threshold": 0.0
|
| 247 |
+
},
|
| 248 |
+
"attributes": {
|
| 249 |
+
"early_stopping_patience_counter": 3
|
| 250 |
+
}
|
| 251 |
+
},
|
| 252 |
+
"TrainerControl": {
|
| 253 |
+
"args": {
|
| 254 |
+
"should_epoch_stop": false,
|
| 255 |
+
"should_evaluate": false,
|
| 256 |
+
"should_log": false,
|
| 257 |
+
"should_save": true,
|
| 258 |
+
"should_training_stop": true
|
| 259 |
+
},
|
| 260 |
+
"attributes": {}
|
| 261 |
+
}
|
| 262 |
+
},
|
| 263 |
+
"total_flos": 0.0,
|
| 264 |
+
"train_batch_size": 8,
|
| 265 |
+
"trial_name": null,
|
| 266 |
+
"trial_params": null
|
| 267 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608/trainer_state.json
ADDED
|
@@ -0,0 +1,299 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 608,
|
| 3 |
+
"best_metric": 0.8422336090875416,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608",
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 608,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.33112582781456956,
|
| 14 |
+
"grad_norm": 23.64274024963379,
|
| 15 |
+
"learning_rate": 3.157894736842105e-06,
|
| 16 |
+
"loss": 2.7721,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6622516556291391,
|
| 21 |
+
"grad_norm": 30.64603042602539,
|
| 22 |
+
"learning_rate": 6.447368421052632e-06,
|
| 23 |
+
"loss": 2.6206,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9933774834437086,
|
| 28 |
+
"grad_norm": 33.40311813354492,
|
| 29 |
+
"learning_rate": 9.736842105263159e-06,
|
| 30 |
+
"loss": 2.5051,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6468401486988847,
|
| 36 |
+
"eval_loss": 0.6445711851119995,
|
| 37 |
+
"eval_macro_f1": 0.3927765237020316,
|
| 38 |
+
"eval_runtime": 0.2522,
|
| 39 |
+
"eval_samples_per_second": 1066.772,
|
| 40 |
+
"eval_steps_per_second": 67.417,
|
| 41 |
+
"eval_weighted_f1": 0.5081272499937063,
|
| 42 |
+
"step": 76
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.3178807947019868,
|
| 46 |
+
"grad_norm": 28.27245330810547,
|
| 47 |
+
"learning_rate": 1.3026315789473684e-05,
|
| 48 |
+
"loss": 2.5051,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.6490066225165563,
|
| 53 |
+
"grad_norm": 34.48577880859375,
|
| 54 |
+
"learning_rate": 1.6315789473684213e-05,
|
| 55 |
+
"loss": 2.39,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.980132450331126,
|
| 60 |
+
"grad_norm": 38.14251708984375,
|
| 61 |
+
"learning_rate": 1.960526315789474e-05,
|
| 62 |
+
"loss": 2.1665,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.8029739776951673,
|
| 68 |
+
"eval_loss": 0.4049725830554962,
|
| 69 |
+
"eval_macro_f1": 0.7816859352270118,
|
| 70 |
+
"eval_runtime": 0.2517,
|
| 71 |
+
"eval_samples_per_second": 1068.687,
|
| 72 |
+
"eval_steps_per_second": 67.538,
|
| 73 |
+
"eval_weighted_f1": 0.801706832310158,
|
| 74 |
+
"step": 152
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.304635761589404,
|
| 78 |
+
"grad_norm": 39.85519027709961,
|
| 79 |
+
"learning_rate": 1.9678362573099416e-05,
|
| 80 |
+
"loss": 1.5946,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.6357615894039736,
|
| 85 |
+
"grad_norm": 34.119476318359375,
|
| 86 |
+
"learning_rate": 1.9312865497076027e-05,
|
| 87 |
+
"loss": 1.7321,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.966887417218543,
|
| 92 |
+
"grad_norm": 25.580774307250977,
|
| 93 |
+
"learning_rate": 1.894736842105263e-05,
|
| 94 |
+
"loss": 1.6342,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8104089219330854,
|
| 100 |
+
"eval_loss": 0.3940223157405853,
|
| 101 |
+
"eval_macro_f1": 0.800482831837815,
|
| 102 |
+
"eval_runtime": 0.2517,
|
| 103 |
+
"eval_samples_per_second": 1068.642,
|
| 104 |
+
"eval_steps_per_second": 67.535,
|
| 105 |
+
"eval_weighted_f1": 0.8135521837965878,
|
| 106 |
+
"step": 228
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.2913907284768213,
|
| 110 |
+
"grad_norm": 53.363826751708984,
|
| 111 |
+
"learning_rate": 1.8581871345029242e-05,
|
| 112 |
+
"loss": 1.3174,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.622516556291391,
|
| 117 |
+
"grad_norm": 31.605037689208984,
|
| 118 |
+
"learning_rate": 1.821637426900585e-05,
|
| 119 |
+
"loss": 1.3081,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.9536423841059603,
|
| 124 |
+
"grad_norm": 41.72595977783203,
|
| 125 |
+
"learning_rate": 1.785087719298246e-05,
|
| 126 |
+
"loss": 1.3529,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8066914498141264,
|
| 132 |
+
"eval_loss": 0.4612957537174225,
|
| 133 |
+
"eval_macro_f1": 0.7555912776069331,
|
| 134 |
+
"eval_runtime": 0.2513,
|
| 135 |
+
"eval_samples_per_second": 1070.515,
|
| 136 |
+
"eval_steps_per_second": 67.653,
|
| 137 |
+
"eval_weighted_f1": 0.7884117134148052,
|
| 138 |
+
"step": 304
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.2781456953642385,
|
| 142 |
+
"grad_norm": 35.946903228759766,
|
| 143 |
+
"learning_rate": 1.7485380116959064e-05,
|
| 144 |
+
"loss": 0.8802,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.609271523178808,
|
| 149 |
+
"grad_norm": 41.89992904663086,
|
| 150 |
+
"learning_rate": 1.7119883040935675e-05,
|
| 151 |
+
"loss": 1.004,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.940397350993377,
|
| 156 |
+
"grad_norm": 89.8902816772461,
|
| 157 |
+
"learning_rate": 1.6754385964912282e-05,
|
| 158 |
+
"loss": 0.8487,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.0,
|
| 163 |
+
"eval_accuracy": 0.8327137546468402,
|
| 164 |
+
"eval_loss": 0.40940529108047485,
|
| 165 |
+
"eval_macro_f1": 0.8116275812701328,
|
| 166 |
+
"eval_runtime": 0.3011,
|
| 167 |
+
"eval_samples_per_second": 893.283,
|
| 168 |
+
"eval_steps_per_second": 56.453,
|
| 169 |
+
"eval_weighted_f1": 0.8301365556785759,
|
| 170 |
+
"step": 380
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.264900662251655,
|
| 174 |
+
"grad_norm": 21.58188247680664,
|
| 175 |
+
"learning_rate": 1.638888888888889e-05,
|
| 176 |
+
"loss": 0.6041,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.596026490066225,
|
| 181 |
+
"grad_norm": 53.391258239746094,
|
| 182 |
+
"learning_rate": 1.60233918128655e-05,
|
| 183 |
+
"loss": 0.6679,
|
| 184 |
+
"step": 425
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.927152317880795,
|
| 188 |
+
"grad_norm": 23.110708236694336,
|
| 189 |
+
"learning_rate": 1.5657894736842107e-05,
|
| 190 |
+
"loss": 0.7013,
|
| 191 |
+
"step": 450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.0,
|
| 195 |
+
"eval_accuracy": 0.8587360594795539,
|
| 196 |
+
"eval_loss": 0.42313677072525024,
|
| 197 |
+
"eval_macro_f1": 0.8395592667001507,
|
| 198 |
+
"eval_runtime": 0.2326,
|
| 199 |
+
"eval_samples_per_second": 1156.688,
|
| 200 |
+
"eval_steps_per_second": 73.099,
|
| 201 |
+
"eval_weighted_f1": 0.8558492304589985,
|
| 202 |
+
"step": 456
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.251655629139073,
|
| 206 |
+
"grad_norm": 14.765984535217285,
|
| 207 |
+
"learning_rate": 1.5292397660818715e-05,
|
| 208 |
+
"loss": 0.3904,
|
| 209 |
+
"step": 475
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.582781456953643,
|
| 213 |
+
"grad_norm": 58.89537048339844,
|
| 214 |
+
"learning_rate": 1.4926900584795322e-05,
|
| 215 |
+
"loss": 0.5426,
|
| 216 |
+
"step": 500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 6.913907284768212,
|
| 220 |
+
"grad_norm": 32.96780776977539,
|
| 221 |
+
"learning_rate": 1.4561403508771931e-05,
|
| 222 |
+
"loss": 0.5764,
|
| 223 |
+
"step": 525
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 7.0,
|
| 227 |
+
"eval_accuracy": 0.828996282527881,
|
| 228 |
+
"eval_loss": 0.4706585705280304,
|
| 229 |
+
"eval_macro_f1": 0.8203542392566783,
|
| 230 |
+
"eval_runtime": 0.2529,
|
| 231 |
+
"eval_samples_per_second": 1063.503,
|
| 232 |
+
"eval_steps_per_second": 67.21,
|
| 233 |
+
"eval_weighted_f1": 0.831925788721509,
|
| 234 |
+
"step": 532
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.23841059602649,
|
| 238 |
+
"grad_norm": 42.506404876708984,
|
| 239 |
+
"learning_rate": 1.4195906432748539e-05,
|
| 240 |
+
"loss": 0.485,
|
| 241 |
+
"step": 550
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 7.569536423841059,
|
| 245 |
+
"grad_norm": 47.10829544067383,
|
| 246 |
+
"learning_rate": 1.3830409356725148e-05,
|
| 247 |
+
"loss": 0.4954,
|
| 248 |
+
"step": 575
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.900662251655629,
|
| 252 |
+
"grad_norm": 34.07044982910156,
|
| 253 |
+
"learning_rate": 1.3464912280701757e-05,
|
| 254 |
+
"loss": 0.4538,
|
| 255 |
+
"step": 600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.0,
|
| 259 |
+
"eval_accuracy": 0.8587360594795539,
|
| 260 |
+
"eval_loss": 0.5537682771682739,
|
| 261 |
+
"eval_macro_f1": 0.8422336090875416,
|
| 262 |
+
"eval_runtime": 0.2427,
|
| 263 |
+
"eval_samples_per_second": 1108.57,
|
| 264 |
+
"eval_steps_per_second": 70.058,
|
| 265 |
+
"eval_weighted_f1": 0.8572185927768402,
|
| 266 |
+
"step": 608
|
| 267 |
+
}
|
| 268 |
+
],
|
| 269 |
+
"logging_steps": 25,
|
| 270 |
+
"max_steps": 1520,
|
| 271 |
+
"num_input_tokens_seen": 0,
|
| 272 |
+
"num_train_epochs": 20,
|
| 273 |
+
"save_steps": 500,
|
| 274 |
+
"stateful_callbacks": {
|
| 275 |
+
"EarlyStoppingCallback": {
|
| 276 |
+
"args": {
|
| 277 |
+
"early_stopping_patience": 3,
|
| 278 |
+
"early_stopping_threshold": 0.0
|
| 279 |
+
},
|
| 280 |
+
"attributes": {
|
| 281 |
+
"early_stopping_patience_counter": 0
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
+
"TrainerControl": {
|
| 285 |
+
"args": {
|
| 286 |
+
"should_epoch_stop": false,
|
| 287 |
+
"should_evaluate": false,
|
| 288 |
+
"should_log": false,
|
| 289 |
+
"should_save": true,
|
| 290 |
+
"should_training_stop": false
|
| 291 |
+
},
|
| 292 |
+
"attributes": {}
|
| 293 |
+
}
|
| 294 |
+
},
|
| 295 |
+
"total_flos": 0.0,
|
| 296 |
+
"train_batch_size": 8,
|
| 297 |
+
"trial_name": null,
|
| 298 |
+
"trial_params": null
|
| 299 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-836/trainer_state.json
ADDED
|
@@ -0,0 +1,395 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 608,
|
| 3 |
+
"best_metric": 0.8422336090875416,
|
| 4 |
+
"best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-viclickbait2025-bamibert-source-source-01-s43-20260827T172942Z-32d744c6/trainer/checkpoint-608",
|
| 5 |
+
"epoch": 11.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 836,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.33112582781456956,
|
| 14 |
+
"grad_norm": 23.64274024963379,
|
| 15 |
+
"learning_rate": 3.157894736842105e-06,
|
| 16 |
+
"loss": 2.7721,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6622516556291391,
|
| 21 |
+
"grad_norm": 30.64603042602539,
|
| 22 |
+
"learning_rate": 6.447368421052632e-06,
|
| 23 |
+
"loss": 2.6206,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.9933774834437086,
|
| 28 |
+
"grad_norm": 33.40311813354492,
|
| 29 |
+
"learning_rate": 9.736842105263159e-06,
|
| 30 |
+
"loss": 2.5051,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6468401486988847,
|
| 36 |
+
"eval_loss": 0.6445711851119995,
|
| 37 |
+
"eval_macro_f1": 0.3927765237020316,
|
| 38 |
+
"eval_runtime": 0.2522,
|
| 39 |
+
"eval_samples_per_second": 1066.772,
|
| 40 |
+
"eval_steps_per_second": 67.417,
|
| 41 |
+
"eval_weighted_f1": 0.5081272499937063,
|
| 42 |
+
"step": 76
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.3178807947019868,
|
| 46 |
+
"grad_norm": 28.27245330810547,
|
| 47 |
+
"learning_rate": 1.3026315789473684e-05,
|
| 48 |
+
"loss": 2.5051,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.6490066225165563,
|
| 53 |
+
"grad_norm": 34.48577880859375,
|
| 54 |
+
"learning_rate": 1.6315789473684213e-05,
|
| 55 |
+
"loss": 2.39,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.980132450331126,
|
| 60 |
+
"grad_norm": 38.14251708984375,
|
| 61 |
+
"learning_rate": 1.960526315789474e-05,
|
| 62 |
+
"loss": 2.1665,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.8029739776951673,
|
| 68 |
+
"eval_loss": 0.4049725830554962,
|
| 69 |
+
"eval_macro_f1": 0.7816859352270118,
|
| 70 |
+
"eval_runtime": 0.2517,
|
| 71 |
+
"eval_samples_per_second": 1068.687,
|
| 72 |
+
"eval_steps_per_second": 67.538,
|
| 73 |
+
"eval_weighted_f1": 0.801706832310158,
|
| 74 |
+
"step": 152
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.304635761589404,
|
| 78 |
+
"grad_norm": 39.85519027709961,
|
| 79 |
+
"learning_rate": 1.9678362573099416e-05,
|
| 80 |
+
"loss": 1.5946,
|
| 81 |
+
"step": 175
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.6357615894039736,
|
| 85 |
+
"grad_norm": 34.119476318359375,
|
| 86 |
+
"learning_rate": 1.9312865497076027e-05,
|
| 87 |
+
"loss": 1.7321,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.966887417218543,
|
| 92 |
+
"grad_norm": 25.580774307250977,
|
| 93 |
+
"learning_rate": 1.894736842105263e-05,
|
| 94 |
+
"loss": 1.6342,
|
| 95 |
+
"step": 225
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_accuracy": 0.8104089219330854,
|
| 100 |
+
"eval_loss": 0.3940223157405853,
|
| 101 |
+
"eval_macro_f1": 0.800482831837815,
|
| 102 |
+
"eval_runtime": 0.2517,
|
| 103 |
+
"eval_samples_per_second": 1068.642,
|
| 104 |
+
"eval_steps_per_second": 67.535,
|
| 105 |
+
"eval_weighted_f1": 0.8135521837965878,
|
| 106 |
+
"step": 228
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.2913907284768213,
|
| 110 |
+
"grad_norm": 53.363826751708984,
|
| 111 |
+
"learning_rate": 1.8581871345029242e-05,
|
| 112 |
+
"loss": 1.3174,
|
| 113 |
+
"step": 250
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.622516556291391,
|
| 117 |
+
"grad_norm": 31.605037689208984,
|
| 118 |
+
"learning_rate": 1.821637426900585e-05,
|
| 119 |
+
"loss": 1.3081,
|
| 120 |
+
"step": 275
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.9536423841059603,
|
| 124 |
+
"grad_norm": 41.72595977783203,
|
| 125 |
+
"learning_rate": 1.785087719298246e-05,
|
| 126 |
+
"loss": 1.3529,
|
| 127 |
+
"step": 300
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.0,
|
| 131 |
+
"eval_accuracy": 0.8066914498141264,
|
| 132 |
+
"eval_loss": 0.4612957537174225,
|
| 133 |
+
"eval_macro_f1": 0.7555912776069331,
|
| 134 |
+
"eval_runtime": 0.2513,
|
| 135 |
+
"eval_samples_per_second": 1070.515,
|
| 136 |
+
"eval_steps_per_second": 67.653,
|
| 137 |
+
"eval_weighted_f1": 0.7884117134148052,
|
| 138 |
+
"step": 304
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.2781456953642385,
|
| 142 |
+
"grad_norm": 35.946903228759766,
|
| 143 |
+
"learning_rate": 1.7485380116959064e-05,
|
| 144 |
+
"loss": 0.8802,
|
| 145 |
+
"step": 325
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.609271523178808,
|
| 149 |
+
"grad_norm": 41.89992904663086,
|
| 150 |
+
"learning_rate": 1.7119883040935675e-05,
|
| 151 |
+
"loss": 1.004,
|
| 152 |
+
"step": 350
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.940397350993377,
|
| 156 |
+
"grad_norm": 89.8902816772461,
|
| 157 |
+
"learning_rate": 1.6754385964912282e-05,
|
| 158 |
+
"loss": 0.8487,
|
| 159 |
+
"step": 375
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.0,
|
| 163 |
+
"eval_accuracy": 0.8327137546468402,
|
| 164 |
+
"eval_loss": 0.40940529108047485,
|
| 165 |
+
"eval_macro_f1": 0.8116275812701328,
|
| 166 |
+
"eval_runtime": 0.3011,
|
| 167 |
+
"eval_samples_per_second": 893.283,
|
| 168 |
+
"eval_steps_per_second": 56.453,
|
| 169 |
+
"eval_weighted_f1": 0.8301365556785759,
|
| 170 |
+
"step": 380
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.264900662251655,
|
| 174 |
+
"grad_norm": 21.58188247680664,
|
| 175 |
+
"learning_rate": 1.638888888888889e-05,
|
| 176 |
+
"loss": 0.6041,
|
| 177 |
+
"step": 400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.596026490066225,
|
| 181 |
+
"grad_norm": 53.391258239746094,
|
| 182 |
+
"learning_rate": 1.60233918128655e-05,
|
| 183 |
+
"loss": 0.6679,
|
| 184 |
+
"step": 425
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.927152317880795,
|
| 188 |
+
"grad_norm": 23.110708236694336,
|
| 189 |
+
"learning_rate": 1.5657894736842107e-05,
|
| 190 |
+
"loss": 0.7013,
|
| 191 |
+
"step": 450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.0,
|
| 195 |
+
"eval_accuracy": 0.8587360594795539,
|
| 196 |
+
"eval_loss": 0.42313677072525024,
|
| 197 |
+
"eval_macro_f1": 0.8395592667001507,
|
| 198 |
+
"eval_runtime": 0.2326,
|
| 199 |
+
"eval_samples_per_second": 1156.688,
|
| 200 |
+
"eval_steps_per_second": 73.099,
|
| 201 |
+
"eval_weighted_f1": 0.8558492304589985,
|
| 202 |
+
"step": 456
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.251655629139073,
|
| 206 |
+
"grad_norm": 14.765984535217285,
|
| 207 |
+
"learning_rate": 1.5292397660818715e-05,
|
| 208 |
+
"loss": 0.3904,
|
| 209 |
+
"step": 475
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.582781456953643,
|
| 213 |
+
"grad_norm": 58.89537048339844,
|
| 214 |
+
"learning_rate": 1.4926900584795322e-05,
|
| 215 |
+
"loss": 0.5426,
|
| 216 |
+
"step": 500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 6.913907284768212,
|
| 220 |
+
"grad_norm": 32.96780776977539,
|
| 221 |
+
"learning_rate": 1.4561403508771931e-05,
|
| 222 |
+
"loss": 0.5764,
|
| 223 |
+
"step": 525
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 7.0,
|
| 227 |
+
"eval_accuracy": 0.828996282527881,
|
| 228 |
+
"eval_loss": 0.4706585705280304,
|
| 229 |
+
"eval_macro_f1": 0.8203542392566783,
|
| 230 |
+
"eval_runtime": 0.2529,
|
| 231 |
+
"eval_samples_per_second": 1063.503,
|
| 232 |
+
"eval_steps_per_second": 67.21,
|
| 233 |
+
"eval_weighted_f1": 0.831925788721509,
|
| 234 |
+
"step": 532
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.23841059602649,
|
| 238 |
+
"grad_norm": 42.506404876708984,
|
| 239 |
+
"learning_rate": 1.4195906432748539e-05,
|
| 240 |
+
"loss": 0.485,
|
| 241 |
+
"step": 550
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 7.569536423841059,
|
| 245 |
+
"grad_norm": 47.10829544067383,
|
| 246 |
+
"learning_rate": 1.3830409356725148e-05,
|
| 247 |
+
"loss": 0.4954,
|
| 248 |
+
"step": 575
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.900662251655629,
|
| 252 |
+
"grad_norm": 34.07044982910156,
|
| 253 |
+
"learning_rate": 1.3464912280701757e-05,
|
| 254 |
+
"loss": 0.4538,
|
| 255 |
+
"step": 600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.0,
|
| 259 |
+
"eval_accuracy": 0.8587360594795539,
|
| 260 |
+
"eval_loss": 0.5537682771682739,
|
| 261 |
+
"eval_macro_f1": 0.8422336090875416,
|
| 262 |
+
"eval_runtime": 0.2427,
|
| 263 |
+
"eval_samples_per_second": 1108.57,
|
| 264 |
+
"eval_steps_per_second": 70.058,
|
| 265 |
+
"eval_weighted_f1": 0.8572185927768402,
|
| 266 |
+
"step": 608
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.225165562913908,
|
| 270 |
+
"grad_norm": 73.26912689208984,
|
| 271 |
+
"learning_rate": 1.3099415204678362e-05,
|
| 272 |
+
"loss": 0.3656,
|
| 273 |
+
"step": 625
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.556291390728477,
|
| 277 |
+
"grad_norm": 170.6850128173828,
|
| 278 |
+
"learning_rate": 1.2733918128654971e-05,
|
| 279 |
+
"loss": 0.3243,
|
| 280 |
+
"step": 650
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.887417218543046,
|
| 284 |
+
"grad_norm": 4.319545269012451,
|
| 285 |
+
"learning_rate": 1.236842105263158e-05,
|
| 286 |
+
"loss": 0.2586,
|
| 287 |
+
"step": 675
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 9.0,
|
| 291 |
+
"eval_accuracy": 0.8438661710037175,
|
| 292 |
+
"eval_loss": 0.6647192239761353,
|
| 293 |
+
"eval_macro_f1": 0.8216180371352785,
|
| 294 |
+
"eval_runtime": 0.2421,
|
| 295 |
+
"eval_samples_per_second": 1110.965,
|
| 296 |
+
"eval_steps_per_second": 70.21,
|
| 297 |
+
"eval_weighted_f1": 0.8401191168785067,
|
| 298 |
+
"step": 684
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 9.211920529801324,
|
| 302 |
+
"grad_norm": 64.7196044921875,
|
| 303 |
+
"learning_rate": 1.2002923976608188e-05,
|
| 304 |
+
"loss": 0.2011,
|
| 305 |
+
"step": 700
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 9.543046357615895,
|
| 309 |
+
"grad_norm": 46.1414680480957,
|
| 310 |
+
"learning_rate": 1.1637426900584797e-05,
|
| 311 |
+
"loss": 0.1906,
|
| 312 |
+
"step": 725
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 9.874172185430464,
|
| 316 |
+
"grad_norm": 2.761384963989258,
|
| 317 |
+
"learning_rate": 1.1271929824561404e-05,
|
| 318 |
+
"loss": 0.3672,
|
| 319 |
+
"step": 750
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 10.0,
|
| 323 |
+
"eval_accuracy": 0.8475836431226765,
|
| 324 |
+
"eval_loss": 0.8873733282089233,
|
| 325 |
+
"eval_macro_f1": 0.8253385066117666,
|
| 326 |
+
"eval_runtime": 0.2426,
|
| 327 |
+
"eval_samples_per_second": 1108.753,
|
| 328 |
+
"eval_steps_per_second": 70.07,
|
| 329 |
+
"eval_weighted_f1": 0.8436444001988695,
|
| 330 |
+
"step": 760
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 10.198675496688741,
|
| 334 |
+
"grad_norm": 3.454347610473633,
|
| 335 |
+
"learning_rate": 1.0906432748538012e-05,
|
| 336 |
+
"loss": 0.2574,
|
| 337 |
+
"step": 775
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 10.52980132450331,
|
| 341 |
+
"grad_norm": 202.893310546875,
|
| 342 |
+
"learning_rate": 1.054093567251462e-05,
|
| 343 |
+
"loss": 0.3241,
|
| 344 |
+
"step": 800
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 10.860927152317881,
|
| 348 |
+
"grad_norm": 0.3046122193336487,
|
| 349 |
+
"learning_rate": 1.017543859649123e-05,
|
| 350 |
+
"loss": 0.2606,
|
| 351 |
+
"step": 825
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 11.0,
|
| 355 |
+
"eval_accuracy": 0.8550185873605948,
|
| 356 |
+
"eval_loss": 0.8593987226486206,
|
| 357 |
+
"eval_macro_f1": 0.8393538013934615,
|
| 358 |
+
"eval_runtime": 0.2486,
|
| 359 |
+
"eval_samples_per_second": 1082.202,
|
| 360 |
+
"eval_steps_per_second": 68.392,
|
| 361 |
+
"eval_weighted_f1": 0.854086159624456,
|
| 362 |
+
"step": 836
|
| 363 |
+
}
|
| 364 |
+
],
|
| 365 |
+
"logging_steps": 25,
|
| 366 |
+
"max_steps": 1520,
|
| 367 |
+
"num_input_tokens_seen": 0,
|
| 368 |
+
"num_train_epochs": 20,
|
| 369 |
+
"save_steps": 500,
|
| 370 |
+
"stateful_callbacks": {
|
| 371 |
+
"EarlyStoppingCallback": {
|
| 372 |
+
"args": {
|
| 373 |
+
"early_stopping_patience": 3,
|
| 374 |
+
"early_stopping_threshold": 0.0
|
| 375 |
+
},
|
| 376 |
+
"attributes": {
|
| 377 |
+
"early_stopping_patience_counter": 3
|
| 378 |
+
}
|
| 379 |
+
},
|
| 380 |
+
"TrainerControl": {
|
| 381 |
+
"args": {
|
| 382 |
+
"should_epoch_stop": false,
|
| 383 |
+
"should_evaluate": false,
|
| 384 |
+
"should_log": false,
|
| 385 |
+
"should_save": true,
|
| 386 |
+
"should_training_stop": true
|
| 387 |
+
},
|
| 388 |
+
"attributes": {}
|
| 389 |
+
}
|
| 390 |
+
},
|
| 391 |
+
"total_flos": 0.0,
|
| 392 |
+
"train_batch_size": 8,
|
| 393 |
+
"trial_name": null,
|
| 394 |
+
"trial_params": null
|
| 395 |
+
}
|
ood-viclickbait2025-bamibert-source-source-02-s42-20260827T171930Z-ee19aa8e/trainer/checkpoint-380/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
ood-viclickbait2025-bamibert-source-source-02-s42-20260827T171930Z-ee19aa8e/trainer/checkpoint-380/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ood-viclickbait2025-bamibert-source-source-02-s42-20260827T171930Z-ee19aa8e/trainer/checkpoint-380/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"20480": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|