Commit ·
d4fded6
1
Parent(s): 4e67821
Model save
Browse files- README.md +2 -2
- adapter_config.json +2 -2
- added_tokens.json +3 -0
- all_results.json +8 -8
- eval_results.json +4 -4
- runs/Nov30_17-06-41_hpc-hblab/events.out.tfevents.1701338897.hpc-hblab.1611604.0 +3 -0
- runs/Nov30_17-06-41_hpc-hblab/events.out.tfevents.1701339195.hpc-hblab.1611604.1 +3 -0
- special_tokens_map.json +7 -1
- tokenizer.json +9 -0
- tokenizer_config.json +13 -2
- train_results.json +4 -4
- trainer_state.json +10 -10
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 1.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
-
| No log | 0 | 0 | 1.
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.4187
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| No log | 0 | 0 | 1.4187 |
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -16,10 +16,10 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"o_proj",
|
| 20 |
"k_proj",
|
| 21 |
"v_proj",
|
| 22 |
-
"q_proj"
|
|
|
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
| 19 |
"k_proj",
|
| 20 |
"v_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
+
"o_proj"
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 1200,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
"train_samples": 1200,
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0,
|
| 3 |
+
"eval_loss": 1.4187188148498535,
|
| 4 |
+
"eval_runtime": 58.7586,
|
| 5 |
"eval_samples": 1200,
|
| 6 |
+
"eval_samples_per_second": 20.423,
|
| 7 |
+
"eval_steps_per_second": 2.553,
|
| 8 |
+
"train_loss": 0.3546818494796753,
|
| 9 |
+
"train_runtime": 239.2844,
|
| 10 |
"train_samples": 1200,
|
| 11 |
+
"train_samples_per_second": 5.015,
|
| 12 |
+
"train_steps_per_second": 0.008
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0,
|
| 3 |
-
"eval_loss": 1.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 1200,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0,
|
| 3 |
+
"eval_loss": 1.4187188148498535,
|
| 4 |
+
"eval_runtime": 58.7586,
|
| 5 |
"eval_samples": 1200,
|
| 6 |
+
"eval_samples_per_second": 20.423,
|
| 7 |
+
"eval_steps_per_second": 2.553
|
| 8 |
}
|
runs/Nov30_17-06-41_hpc-hblab/events.out.tfevents.1701338897.hpc-hblab.1611604.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e2c0afb882b5025f67294a97983b1a3091f587d9a71486c1feeb2a820f3b7f8
|
| 3 |
+
size 4806
|
runs/Nov30_17-06-41_hpc-hblab/events.out.tfevents.1701339195.hpc-hblab.1611604.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3789884d1a74153773224e357c4048d459894ae8378bf7a4eaac07dad685c121
|
| 3 |
+
size 344
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -29,6 +29,15 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 32000,
|
| 35 |
+
"content": "[PAD]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -23,6 +25,14 @@
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
"additional_special_tokens": [],
|
|
@@ -31,8 +41,9 @@
|
|
| 31 |
"clean_up_tokenization_spaces": false,
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": true,
|
| 34 |
-
"model_max_length":
|
| 35 |
-
"pad_token": "
|
|
|
|
| 36 |
"sp_model_kwargs": {},
|
| 37 |
"spaces_between_special_tokens": false,
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"additional_special_tokens": [],
|
|
|
|
| 41 |
"clean_up_tokenization_spaces": false,
|
| 42 |
"eos_token": "</s>",
|
| 43 |
"legacy": true,
|
| 44 |
+
"model_max_length": 1024,
|
| 45 |
+
"pad_token": "[PAD]",
|
| 46 |
+
"padding_side": "right",
|
| 47 |
"sp_model_kwargs": {},
|
| 48 |
"spaces_between_special_tokens": false,
|
| 49 |
"tokenizer_class": "LlamaTokenizer",
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 1200,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 0,
|
| 3 |
+
"train_loss": 0.3546818494796753,
|
| 4 |
+
"train_runtime": 239.2844,
|
| 5 |
"train_samples": 1200,
|
| 6 |
+
"train_samples_per_second": 5.015,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -10,27 +10,27 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0,
|
| 13 |
-
"eval_loss": 1.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second":
|
| 17 |
"step": 0
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0,
|
| 21 |
"step": 0,
|
| 22 |
-
"total_flos":
|
| 23 |
-
"train_loss": 0.
|
| 24 |
-
"train_runtime":
|
| 25 |
-
"train_samples_per_second":
|
| 26 |
-
"train_steps_per_second": 0.
|
| 27 |
}
|
| 28 |
],
|
| 29 |
"logging_steps": 5,
|
| 30 |
"max_steps": 2,
|
| 31 |
"num_train_epochs": 1,
|
| 32 |
"save_steps": 500,
|
| 33 |
-
"total_flos":
|
| 34 |
"trial_name": null,
|
| 35 |
"trial_params": null
|
| 36 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0,
|
| 13 |
+
"eval_loss": 1.418718695640564,
|
| 14 |
+
"eval_runtime": 59.2437,
|
| 15 |
+
"eval_samples_per_second": 20.255,
|
| 16 |
+
"eval_steps_per_second": 2.532,
|
| 17 |
"step": 0
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0,
|
| 21 |
"step": 0,
|
| 22 |
+
"total_flos": 1.1269869630652416e+16,
|
| 23 |
+
"train_loss": 0.3546818494796753,
|
| 24 |
+
"train_runtime": 239.2844,
|
| 25 |
+
"train_samples_per_second": 5.015,
|
| 26 |
+
"train_steps_per_second": 0.008
|
| 27 |
}
|
| 28 |
],
|
| 29 |
"logging_steps": 5,
|
| 30 |
"max_steps": 2,
|
| 31 |
"num_train_epochs": 1,
|
| 32 |
"save_steps": 500,
|
| 33 |
+
"total_flos": 1.1269869630652416e+16,
|
| 34 |
"trial_name": null,
|
| 35 |
"trial_params": null
|
| 36 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0d11ab835e1773ef1f902c0fcbcfa5a15ea8e274293fd54cc24ad7877072741
|
| 3 |
+
size 4600
|