Add checkpoint files
Browse files- checkpoint-1100/config.json +74 -0
- checkpoint-1100/generation_config.json +13 -0
- checkpoint-1100/merges.txt +0 -0
- checkpoint-1100/model.safetensors +3 -0
- checkpoint-1100/optimizer.pt +3 -0
- checkpoint-1100/rng_state.pth +3 -0
- checkpoint-1100/scheduler.pt +3 -0
- checkpoint-1100/special_tokens_map.json +51 -0
- checkpoint-1100/tokenizer_config.json +57 -0
- checkpoint-1100/trainer_state.json +176 -0
- checkpoint-1100/training_args.bin +3 -0
- checkpoint-1100/vocab.json +0 -0
- checkpoint-880/config.json +74 -0
- checkpoint-880/generation_config.json +13 -0
- checkpoint-880/merges.txt +0 -0
- checkpoint-880/model.safetensors +3 -0
- checkpoint-880/optimizer.pt +3 -0
- checkpoint-880/rng_state.pth +3 -0
- checkpoint-880/scheduler.pt +3 -0
- checkpoint-880/special_tokens_map.json +51 -0
- checkpoint-880/tokenizer_config.json +57 -0
- checkpoint-880/trainer_state.json +145 -0
- checkpoint-880/training_args.bin +3 -0
- checkpoint-880/vocab.json +0 -0
- runs/Dec04_14-48-03_7f7fe3780155/events.out.tfevents.1733323684.7f7fe3780155.23.2 +3 -0
checkpoint-1100/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./finetuned_bart_samsum",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.3,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.46.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
checkpoint-1100/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.46.3"
|
| 13 |
+
}
|
checkpoint-1100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63b90d9bc31885a5c9b71abed601419d2e0515dd8a59111c9628518e7453ff39
|
| 3 |
+
size 557912620
|
checkpoint-1100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a02be0205ce2f5b42f1958db8d15cdc468a5f0ce4d08e6648475ed7a1dc482e
|
| 3 |
+
size 1115579898
|
checkpoint-1100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02f8755614309428882ee57a57c17bbb2458fd6dc62a6889871e77fc0509496a
|
| 3 |
+
size 14244
|
checkpoint-1100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1671862da72ff9786c7bc49a3efd0139c5774d70a75fd8e8c42599e2ebff09e
|
| 3 |
+
size 1064
|
checkpoint-1100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-1100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-1100/trainer_state.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6016,
|
| 3 |
+
"best_model_checkpoint": "./results/fine-tuned-model/checkpoint-880",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_R1": 0.5873,
|
| 14 |
+
"eval_R2": 0.2994,
|
| 15 |
+
"eval_RL": 0.5458,
|
| 16 |
+
"eval_RLsum": 0.5457,
|
| 17 |
+
"eval_loss": 0.6845592260360718,
|
| 18 |
+
"eval_runtime": 3.9726,
|
| 19 |
+
"eval_samples_per_second": 27.69,
|
| 20 |
+
"eval_steps_per_second": 3.524,
|
| 21 |
+
"step": 110
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_R1": 0.5949,
|
| 26 |
+
"eval_R2": 0.3124,
|
| 27 |
+
"eval_RL": 0.5538,
|
| 28 |
+
"eval_RLsum": 0.5537,
|
| 29 |
+
"eval_loss": 0.6449041366577148,
|
| 30 |
+
"eval_runtime": 3.9537,
|
| 31 |
+
"eval_samples_per_second": 27.822,
|
| 32 |
+
"eval_steps_per_second": 3.541,
|
| 33 |
+
"step": 220
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_R1": 0.5973,
|
| 38 |
+
"eval_R2": 0.3255,
|
| 39 |
+
"eval_RL": 0.5578,
|
| 40 |
+
"eval_RLsum": 0.5584,
|
| 41 |
+
"eval_loss": 0.6413412690162659,
|
| 42 |
+
"eval_runtime": 3.943,
|
| 43 |
+
"eval_samples_per_second": 27.897,
|
| 44 |
+
"eval_steps_per_second": 3.551,
|
| 45 |
+
"step": 330
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.0,
|
| 49 |
+
"eval_R1": 0.5947,
|
| 50 |
+
"eval_R2": 0.3223,
|
| 51 |
+
"eval_RL": 0.5606,
|
| 52 |
+
"eval_RLsum": 0.5607,
|
| 53 |
+
"eval_loss": 0.6398307085037231,
|
| 54 |
+
"eval_runtime": 3.9318,
|
| 55 |
+
"eval_samples_per_second": 27.977,
|
| 56 |
+
"eval_steps_per_second": 3.561,
|
| 57 |
+
"step": 440
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.545454545454545,
|
| 61 |
+
"grad_norm": 2.3488950729370117,
|
| 62 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 63 |
+
"loss": 0.6988,
|
| 64 |
+
"step": 500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"eval_R1": 0.5994,
|
| 69 |
+
"eval_R2": 0.3258,
|
| 70 |
+
"eval_RL": 0.5617,
|
| 71 |
+
"eval_RLsum": 0.5623,
|
| 72 |
+
"eval_loss": 0.6241134405136108,
|
| 73 |
+
"eval_runtime": 3.9366,
|
| 74 |
+
"eval_samples_per_second": 27.943,
|
| 75 |
+
"eval_steps_per_second": 3.556,
|
| 76 |
+
"step": 550
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 6.0,
|
| 80 |
+
"eval_R1": 0.597,
|
| 81 |
+
"eval_R2": 0.3248,
|
| 82 |
+
"eval_RL": 0.5587,
|
| 83 |
+
"eval_RLsum": 0.5596,
|
| 84 |
+
"eval_loss": 0.6201192140579224,
|
| 85 |
+
"eval_runtime": 3.9442,
|
| 86 |
+
"eval_samples_per_second": 27.889,
|
| 87 |
+
"eval_steps_per_second": 3.55,
|
| 88 |
+
"step": 660
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 7.0,
|
| 92 |
+
"eval_R1": 0.5993,
|
| 93 |
+
"eval_R2": 0.3298,
|
| 94 |
+
"eval_RL": 0.5633,
|
| 95 |
+
"eval_RLsum": 0.5644,
|
| 96 |
+
"eval_loss": 0.6225252747535706,
|
| 97 |
+
"eval_runtime": 3.9412,
|
| 98 |
+
"eval_samples_per_second": 27.91,
|
| 99 |
+
"eval_steps_per_second": 3.552,
|
| 100 |
+
"step": 770
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_R1": 0.6016,
|
| 105 |
+
"eval_R2": 0.3314,
|
| 106 |
+
"eval_RL": 0.5639,
|
| 107 |
+
"eval_RLsum": 0.5649,
|
| 108 |
+
"eval_loss": 0.6228554248809814,
|
| 109 |
+
"eval_runtime": 3.9344,
|
| 110 |
+
"eval_samples_per_second": 27.958,
|
| 111 |
+
"eval_steps_per_second": 3.558,
|
| 112 |
+
"step": 880
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 9.0,
|
| 116 |
+
"eval_R1": 0.6006,
|
| 117 |
+
"eval_R2": 0.3295,
|
| 118 |
+
"eval_RL": 0.5629,
|
| 119 |
+
"eval_RLsum": 0.5636,
|
| 120 |
+
"eval_loss": 0.623293399810791,
|
| 121 |
+
"eval_runtime": 3.9834,
|
| 122 |
+
"eval_samples_per_second": 27.615,
|
| 123 |
+
"eval_steps_per_second": 3.515,
|
| 124 |
+
"step": 990
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 9.090909090909092,
|
| 128 |
+
"grad_norm": 3.2348780632019043,
|
| 129 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 130 |
+
"loss": 0.5747,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 10.0,
|
| 135 |
+
"eval_R1": 0.6012,
|
| 136 |
+
"eval_R2": 0.3301,
|
| 137 |
+
"eval_RL": 0.5642,
|
| 138 |
+
"eval_RLsum": 0.5652,
|
| 139 |
+
"eval_loss": 0.6230303049087524,
|
| 140 |
+
"eval_runtime": 3.9395,
|
| 141 |
+
"eval_samples_per_second": 27.922,
|
| 142 |
+
"eval_steps_per_second": 3.554,
|
| 143 |
+
"step": 1100
|
| 144 |
+
}
|
| 145 |
+
],
|
| 146 |
+
"logging_steps": 500,
|
| 147 |
+
"max_steps": 1100,
|
| 148 |
+
"num_input_tokens_seen": 0,
|
| 149 |
+
"num_train_epochs": 10,
|
| 150 |
+
"save_steps": 500,
|
| 151 |
+
"stateful_callbacks": {
|
| 152 |
+
"EarlyStoppingCallback": {
|
| 153 |
+
"args": {
|
| 154 |
+
"early_stopping_patience": 3,
|
| 155 |
+
"early_stopping_threshold": 0.0
|
| 156 |
+
},
|
| 157 |
+
"attributes": {
|
| 158 |
+
"early_stopping_patience_counter": 2
|
| 159 |
+
}
|
| 160 |
+
},
|
| 161 |
+
"TrainerControl": {
|
| 162 |
+
"args": {
|
| 163 |
+
"should_epoch_stop": false,
|
| 164 |
+
"should_evaluate": false,
|
| 165 |
+
"should_log": false,
|
| 166 |
+
"should_save": true,
|
| 167 |
+
"should_training_stop": true
|
| 168 |
+
},
|
| 169 |
+
"attributes": {}
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"total_flos": 5359583467929600.0,
|
| 173 |
+
"train_batch_size": 8,
|
| 174 |
+
"trial_name": null,
|
| 175 |
+
"trial_params": null
|
| 176 |
+
}
|
checkpoint-1100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70d1dda0456e0b18baf683ffd2627b7727998054bfaeb83f825e5bd090ba14d
|
| 3 |
+
size 5304
|
checkpoint-1100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-880/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./finetuned_bart_samsum",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.3,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.46.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
checkpoint-880/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.46.3"
|
| 13 |
+
}
|
checkpoint-880/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-880/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ef32fbde51bc6007c59f952948f209d4139073b7bed2fc062ba276f863677fb
|
| 3 |
+
size 557912620
|
checkpoint-880/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5ffc31d3e11e3fa7fb30566e2029e427fdd47e839d2bfd85bef3ea84106c7e6
|
| 3 |
+
size 1115579898
|
checkpoint-880/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d8c94bbeb0a5ca9ebe8ebe8359de7bf58b9f099fde9a2f84160522f9aba1d94
|
| 3 |
+
size 14244
|
checkpoint-880/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bc23d334cfdc8b01f67813f519a50ad221f21e8c9bd6b985bfa3a82206e91a4
|
| 3 |
+
size 1064
|
checkpoint-880/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-880/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-880/trainer_state.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6016,
|
| 3 |
+
"best_model_checkpoint": "./results/fine-tuned-model/checkpoint-880",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 880,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_R1": 0.5873,
|
| 14 |
+
"eval_R2": 0.2994,
|
| 15 |
+
"eval_RL": 0.5458,
|
| 16 |
+
"eval_RLsum": 0.5457,
|
| 17 |
+
"eval_loss": 0.6845592260360718,
|
| 18 |
+
"eval_runtime": 3.9726,
|
| 19 |
+
"eval_samples_per_second": 27.69,
|
| 20 |
+
"eval_steps_per_second": 3.524,
|
| 21 |
+
"step": 110
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_R1": 0.5949,
|
| 26 |
+
"eval_R2": 0.3124,
|
| 27 |
+
"eval_RL": 0.5538,
|
| 28 |
+
"eval_RLsum": 0.5537,
|
| 29 |
+
"eval_loss": 0.6449041366577148,
|
| 30 |
+
"eval_runtime": 3.9537,
|
| 31 |
+
"eval_samples_per_second": 27.822,
|
| 32 |
+
"eval_steps_per_second": 3.541,
|
| 33 |
+
"step": 220
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_R1": 0.5973,
|
| 38 |
+
"eval_R2": 0.3255,
|
| 39 |
+
"eval_RL": 0.5578,
|
| 40 |
+
"eval_RLsum": 0.5584,
|
| 41 |
+
"eval_loss": 0.6413412690162659,
|
| 42 |
+
"eval_runtime": 3.943,
|
| 43 |
+
"eval_samples_per_second": 27.897,
|
| 44 |
+
"eval_steps_per_second": 3.551,
|
| 45 |
+
"step": 330
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.0,
|
| 49 |
+
"eval_R1": 0.5947,
|
| 50 |
+
"eval_R2": 0.3223,
|
| 51 |
+
"eval_RL": 0.5606,
|
| 52 |
+
"eval_RLsum": 0.5607,
|
| 53 |
+
"eval_loss": 0.6398307085037231,
|
| 54 |
+
"eval_runtime": 3.9318,
|
| 55 |
+
"eval_samples_per_second": 27.977,
|
| 56 |
+
"eval_steps_per_second": 3.561,
|
| 57 |
+
"step": 440
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.545454545454545,
|
| 61 |
+
"grad_norm": 2.3488950729370117,
|
| 62 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 63 |
+
"loss": 0.6988,
|
| 64 |
+
"step": 500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"eval_R1": 0.5994,
|
| 69 |
+
"eval_R2": 0.3258,
|
| 70 |
+
"eval_RL": 0.5617,
|
| 71 |
+
"eval_RLsum": 0.5623,
|
| 72 |
+
"eval_loss": 0.6241134405136108,
|
| 73 |
+
"eval_runtime": 3.9366,
|
| 74 |
+
"eval_samples_per_second": 27.943,
|
| 75 |
+
"eval_steps_per_second": 3.556,
|
| 76 |
+
"step": 550
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 6.0,
|
| 80 |
+
"eval_R1": 0.597,
|
| 81 |
+
"eval_R2": 0.3248,
|
| 82 |
+
"eval_RL": 0.5587,
|
| 83 |
+
"eval_RLsum": 0.5596,
|
| 84 |
+
"eval_loss": 0.6201192140579224,
|
| 85 |
+
"eval_runtime": 3.9442,
|
| 86 |
+
"eval_samples_per_second": 27.889,
|
| 87 |
+
"eval_steps_per_second": 3.55,
|
| 88 |
+
"step": 660
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 7.0,
|
| 92 |
+
"eval_R1": 0.5993,
|
| 93 |
+
"eval_R2": 0.3298,
|
| 94 |
+
"eval_RL": 0.5633,
|
| 95 |
+
"eval_RLsum": 0.5644,
|
| 96 |
+
"eval_loss": 0.6225252747535706,
|
| 97 |
+
"eval_runtime": 3.9412,
|
| 98 |
+
"eval_samples_per_second": 27.91,
|
| 99 |
+
"eval_steps_per_second": 3.552,
|
| 100 |
+
"step": 770
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_R1": 0.6016,
|
| 105 |
+
"eval_R2": 0.3314,
|
| 106 |
+
"eval_RL": 0.5639,
|
| 107 |
+
"eval_RLsum": 0.5649,
|
| 108 |
+
"eval_loss": 0.6228554248809814,
|
| 109 |
+
"eval_runtime": 3.9344,
|
| 110 |
+
"eval_samples_per_second": 27.958,
|
| 111 |
+
"eval_steps_per_second": 3.558,
|
| 112 |
+
"step": 880
|
| 113 |
+
}
|
| 114 |
+
],
|
| 115 |
+
"logging_steps": 500,
|
| 116 |
+
"max_steps": 1100,
|
| 117 |
+
"num_input_tokens_seen": 0,
|
| 118 |
+
"num_train_epochs": 10,
|
| 119 |
+
"save_steps": 500,
|
| 120 |
+
"stateful_callbacks": {
|
| 121 |
+
"EarlyStoppingCallback": {
|
| 122 |
+
"args": {
|
| 123 |
+
"early_stopping_patience": 3,
|
| 124 |
+
"early_stopping_threshold": 0.0
|
| 125 |
+
},
|
| 126 |
+
"attributes": {
|
| 127 |
+
"early_stopping_patience_counter": 0
|
| 128 |
+
}
|
| 129 |
+
},
|
| 130 |
+
"TrainerControl": {
|
| 131 |
+
"args": {
|
| 132 |
+
"should_epoch_stop": false,
|
| 133 |
+
"should_evaluate": false,
|
| 134 |
+
"should_log": false,
|
| 135 |
+
"should_save": true,
|
| 136 |
+
"should_training_stop": false
|
| 137 |
+
},
|
| 138 |
+
"attributes": {}
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"total_flos": 4287666774343680.0,
|
| 142 |
+
"train_batch_size": 8,
|
| 143 |
+
"trial_name": null,
|
| 144 |
+
"trial_params": null
|
| 145 |
+
}
|
checkpoint-880/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70d1dda0456e0b18baf683ffd2627b7727998054bfaeb83f825e5bd090ba14d
|
| 3 |
+
size 5304
|
checkpoint-880/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/Dec04_14-48-03_7f7fe3780155/events.out.tfevents.1733323684.7f7fe3780155.23.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f5c1a4b37cf36ca7805d5a81488d92a29f6478e2d987c24b3ded0767bb697d8
|
| 3 |
+
size 11516
|