Commit
•
8819bc9
1
Parent(s):
03c7341
Upload model checkpoint
Browse files- config.json +41 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +453 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"finetuning_task": "ner",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-FILL",
|
| 15 |
+
"1": "B-ROLE",
|
| 16 |
+
"2": "I-FILL",
|
| 17 |
+
"3": "I-ROLE",
|
| 18 |
+
"4": "O"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"B-FILL": 0,
|
| 24 |
+
"B-ROLE": 1,
|
| 25 |
+
"I-FILL": 2,
|
| 26 |
+
"I-ROLE": 3,
|
| 27 |
+
"O": 4
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "bert",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.40.1",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 28996
|
| 41 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a744d9b7cfb09e93262a90e9c7e44ebe395fbdfa4075ac0920516e16a6ca8a2c
|
| 3 |
+
size 430917436
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:184319eb464f2157def4b845526354d712690982f8df94546bf265158df4a979
|
| 3 |
+
size 861954618
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95b5fb7af749e141d332c3ae94ca9c8e2c72adfc9642f0f5b657e198c6967f50
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d562faa2fd5688b062ae27480ef9243cb9d218c8cf4729c29b9bf09d36d738fb
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,453 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7887323943661972,
|
| 3 |
+
"best_model_checkpoint": "./model_out/checkpoint-480",
|
| 4 |
+
"epoch": 15.737704918032787,
|
| 5 |
+
"eval_steps": 60,
|
| 6 |
+
"global_step": 480,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.32786885245901637,
|
| 13 |
+
"grad_norm": 3.083059549331665,
|
| 14 |
+
"learning_rate": 9.833333333333333e-05,
|
| 15 |
+
"loss": 1.3429,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6557377049180327,
|
| 20 |
+
"grad_norm": 5.27333927154541,
|
| 21 |
+
"learning_rate": 9.666666666666667e-05,
|
| 22 |
+
"loss": 0.9792,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.9836065573770492,
|
| 27 |
+
"grad_norm": 6.412991046905518,
|
| 28 |
+
"learning_rate": 9.5e-05,
|
| 29 |
+
"loss": 0.8173,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.3114754098360657,
|
| 34 |
+
"grad_norm": 4.924794673919678,
|
| 35 |
+
"learning_rate": 9.333333333333334e-05,
|
| 36 |
+
"loss": 0.5787,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.639344262295082,
|
| 41 |
+
"grad_norm": 7.327770233154297,
|
| 42 |
+
"learning_rate": 9.166666666666667e-05,
|
| 43 |
+
"loss": 0.3744,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.9672131147540983,
|
| 48 |
+
"grad_norm": 8.928845405578613,
|
| 49 |
+
"learning_rate": 9e-05,
|
| 50 |
+
"loss": 0.4815,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.9672131147540983,
|
| 55 |
+
"eval_accuracy": 0.7897310513447433,
|
| 56 |
+
"eval_f1": 0.6728971962616822,
|
| 57 |
+
"eval_loss": 0.5841665267944336,
|
| 58 |
+
"eval_precision": 0.6666666666666666,
|
| 59 |
+
"eval_recall": 0.6792452830188679,
|
| 60 |
+
"eval_runtime": 0.9794,
|
| 61 |
+
"eval_samples_per_second": 61.26,
|
| 62 |
+
"eval_steps_per_second": 8.168,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.2950819672131146,
|
| 67 |
+
"grad_norm": 5.491725444793701,
|
| 68 |
+
"learning_rate": 8.833333333333333e-05,
|
| 69 |
+
"loss": 0.2658,
|
| 70 |
+
"step": 70
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.6229508196721314,
|
| 74 |
+
"grad_norm": 5.113138675689697,
|
| 75 |
+
"learning_rate": 8.666666666666667e-05,
|
| 76 |
+
"loss": 0.2402,
|
| 77 |
+
"step": 80
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.9508196721311473,
|
| 81 |
+
"grad_norm": 6.449514865875244,
|
| 82 |
+
"learning_rate": 8.5e-05,
|
| 83 |
+
"loss": 0.1607,
|
| 84 |
+
"step": 90
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.278688524590164,
|
| 88 |
+
"grad_norm": 5.699795246124268,
|
| 89 |
+
"learning_rate": 8.333333333333334e-05,
|
| 90 |
+
"loss": 0.0852,
|
| 91 |
+
"step": 100
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.6065573770491803,
|
| 95 |
+
"grad_norm": 3.382863998413086,
|
| 96 |
+
"learning_rate": 8.166666666666667e-05,
|
| 97 |
+
"loss": 0.1513,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.9344262295081966,
|
| 102 |
+
"grad_norm": 2.5515336990356445,
|
| 103 |
+
"learning_rate": 8e-05,
|
| 104 |
+
"loss": 0.2612,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.9344262295081966,
|
| 109 |
+
"eval_accuracy": 0.8166259168704156,
|
| 110 |
+
"eval_f1": 0.7009345794392523,
|
| 111 |
+
"eval_loss": 0.7145981192588806,
|
| 112 |
+
"eval_precision": 0.6944444444444444,
|
| 113 |
+
"eval_recall": 0.7075471698113207,
|
| 114 |
+
"eval_runtime": 0.9765,
|
| 115 |
+
"eval_samples_per_second": 61.442,
|
| 116 |
+
"eval_steps_per_second": 8.192,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.262295081967213,
|
| 121 |
+
"grad_norm": 3.4330668449401855,
|
| 122 |
+
"learning_rate": 7.833333333333333e-05,
|
| 123 |
+
"loss": 0.0857,
|
| 124 |
+
"step": 130
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.590163934426229,
|
| 128 |
+
"grad_norm": 0.7570230960845947,
|
| 129 |
+
"learning_rate": 7.666666666666667e-05,
|
| 130 |
+
"loss": 0.0339,
|
| 131 |
+
"step": 140
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.918032786885246,
|
| 135 |
+
"grad_norm": 13.973723411560059,
|
| 136 |
+
"learning_rate": 7.500000000000001e-05,
|
| 137 |
+
"loss": 0.0939,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.245901639344262,
|
| 142 |
+
"grad_norm": 6.072541236877441,
|
| 143 |
+
"learning_rate": 7.333333333333333e-05,
|
| 144 |
+
"loss": 0.0753,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.573770491803279,
|
| 149 |
+
"grad_norm": 6.689024925231934,
|
| 150 |
+
"learning_rate": 7.166666666666667e-05,
|
| 151 |
+
"loss": 0.0497,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.901639344262295,
|
| 156 |
+
"grad_norm": 2.9444985389709473,
|
| 157 |
+
"learning_rate": 7e-05,
|
| 158 |
+
"loss": 0.0535,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.901639344262295,
|
| 163 |
+
"eval_accuracy": 0.8166259168704156,
|
| 164 |
+
"eval_f1": 0.6697247706422018,
|
| 165 |
+
"eval_loss": 0.7874237298965454,
|
| 166 |
+
"eval_precision": 0.6517857142857143,
|
| 167 |
+
"eval_recall": 0.6886792452830188,
|
| 168 |
+
"eval_runtime": 0.9781,
|
| 169 |
+
"eval_samples_per_second": 61.346,
|
| 170 |
+
"eval_steps_per_second": 8.179,
|
| 171 |
+
"step": 180
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.229508196721311,
|
| 175 |
+
"grad_norm": 1.6225782632827759,
|
| 176 |
+
"learning_rate": 6.833333333333333e-05,
|
| 177 |
+
"loss": 0.0258,
|
| 178 |
+
"step": 190
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 6.557377049180328,
|
| 182 |
+
"grad_norm": 0.07454058527946472,
|
| 183 |
+
"learning_rate": 6.666666666666667e-05,
|
| 184 |
+
"loss": 0.0273,
|
| 185 |
+
"step": 200
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 6.885245901639344,
|
| 189 |
+
"grad_norm": 5.249931812286377,
|
| 190 |
+
"learning_rate": 6.500000000000001e-05,
|
| 191 |
+
"loss": 0.023,
|
| 192 |
+
"step": 210
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 7.213114754098361,
|
| 196 |
+
"grad_norm": 0.14014603197574615,
|
| 197 |
+
"learning_rate": 6.333333333333333e-05,
|
| 198 |
+
"loss": 0.0162,
|
| 199 |
+
"step": 220
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 7.540983606557377,
|
| 203 |
+
"grad_norm": 0.024733418598771095,
|
| 204 |
+
"learning_rate": 6.166666666666667e-05,
|
| 205 |
+
"loss": 0.0099,
|
| 206 |
+
"step": 230
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.868852459016393,
|
| 210 |
+
"grad_norm": 1.4897031784057617,
|
| 211 |
+
"learning_rate": 6e-05,
|
| 212 |
+
"loss": 0.0141,
|
| 213 |
+
"step": 240
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 7.868852459016393,
|
| 217 |
+
"eval_accuracy": 0.8557457212713936,
|
| 218 |
+
"eval_f1": 0.780269058295964,
|
| 219 |
+
"eval_loss": 0.8452157378196716,
|
| 220 |
+
"eval_precision": 0.7435897435897436,
|
| 221 |
+
"eval_recall": 0.8207547169811321,
|
| 222 |
+
"eval_runtime": 0.9777,
|
| 223 |
+
"eval_samples_per_second": 61.371,
|
| 224 |
+
"eval_steps_per_second": 8.183,
|
| 225 |
+
"step": 240
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.19672131147541,
|
| 229 |
+
"grad_norm": 6.675982475280762,
|
| 230 |
+
"learning_rate": 5.833333333333334e-05,
|
| 231 |
+
"loss": 0.0201,
|
| 232 |
+
"step": 250
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 8.524590163934427,
|
| 236 |
+
"grad_norm": 0.21795310080051422,
|
| 237 |
+
"learning_rate": 5.666666666666667e-05,
|
| 238 |
+
"loss": 0.0098,
|
| 239 |
+
"step": 260
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 8.852459016393443,
|
| 243 |
+
"grad_norm": 1.0106713771820068,
|
| 244 |
+
"learning_rate": 5.500000000000001e-05,
|
| 245 |
+
"loss": 0.0162,
|
| 246 |
+
"step": 270
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 9.180327868852459,
|
| 250 |
+
"grad_norm": 1.9501103162765503,
|
| 251 |
+
"learning_rate": 5.333333333333333e-05,
|
| 252 |
+
"loss": 0.0166,
|
| 253 |
+
"step": 280
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 9.508196721311476,
|
| 257 |
+
"grad_norm": 0.09368854761123657,
|
| 258 |
+
"learning_rate": 5.166666666666667e-05,
|
| 259 |
+
"loss": 0.0178,
|
| 260 |
+
"step": 290
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 9.836065573770492,
|
| 264 |
+
"grad_norm": 5.705907821655273,
|
| 265 |
+
"learning_rate": 5e-05,
|
| 266 |
+
"loss": 0.0102,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 9.836065573770492,
|
| 271 |
+
"eval_accuracy": 0.8068459657701712,
|
| 272 |
+
"eval_f1": 0.7296137339055794,
|
| 273 |
+
"eval_loss": 1.098240613937378,
|
| 274 |
+
"eval_precision": 0.6692913385826772,
|
| 275 |
+
"eval_recall": 0.8018867924528302,
|
| 276 |
+
"eval_runtime": 0.9802,
|
| 277 |
+
"eval_samples_per_second": 61.211,
|
| 278 |
+
"eval_steps_per_second": 8.161,
|
| 279 |
+
"step": 300
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 10.163934426229508,
|
| 283 |
+
"grad_norm": 0.016423122957348824,
|
| 284 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 285 |
+
"loss": 0.0048,
|
| 286 |
+
"step": 310
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 10.491803278688524,
|
| 290 |
+
"grad_norm": 0.013950828462839127,
|
| 291 |
+
"learning_rate": 4.666666666666667e-05,
|
| 292 |
+
"loss": 0.0023,
|
| 293 |
+
"step": 320
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 10.819672131147541,
|
| 297 |
+
"grad_norm": 0.0043854909017682076,
|
| 298 |
+
"learning_rate": 4.5e-05,
|
| 299 |
+
"loss": 0.0049,
|
| 300 |
+
"step": 330
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 11.147540983606557,
|
| 304 |
+
"grad_norm": 0.5211315751075745,
|
| 305 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 306 |
+
"loss": 0.0218,
|
| 307 |
+
"step": 340
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 11.475409836065573,
|
| 311 |
+
"grad_norm": 0.0140004837885499,
|
| 312 |
+
"learning_rate": 4.166666666666667e-05,
|
| 313 |
+
"loss": 0.0085,
|
| 314 |
+
"step": 350
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 11.80327868852459,
|
| 318 |
+
"grad_norm": 1.8254053592681885,
|
| 319 |
+
"learning_rate": 4e-05,
|
| 320 |
+
"loss": 0.0099,
|
| 321 |
+
"step": 360
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.80327868852459,
|
| 325 |
+
"eval_accuracy": 0.80440097799511,
|
| 326 |
+
"eval_f1": 0.7203791469194313,
|
| 327 |
+
"eval_loss": 1.3635536432266235,
|
| 328 |
+
"eval_precision": 0.7238095238095238,
|
| 329 |
+
"eval_recall": 0.7169811320754716,
|
| 330 |
+
"eval_runtime": 0.9823,
|
| 331 |
+
"eval_samples_per_second": 61.081,
|
| 332 |
+
"eval_steps_per_second": 8.144,
|
| 333 |
+
"step": 360
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 12.131147540983607,
|
| 337 |
+
"grad_norm": 0.1549140065908432,
|
| 338 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 339 |
+
"loss": 0.0004,
|
| 340 |
+
"step": 370
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 12.459016393442623,
|
| 344 |
+
"grad_norm": 4.475136756896973,
|
| 345 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 346 |
+
"loss": 0.0026,
|
| 347 |
+
"step": 380
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 12.78688524590164,
|
| 351 |
+
"grad_norm": 11.31729507446289,
|
| 352 |
+
"learning_rate": 3.5e-05,
|
| 353 |
+
"loss": 0.0024,
|
| 354 |
+
"step": 390
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 13.114754098360656,
|
| 358 |
+
"grad_norm": 0.003214745782315731,
|
| 359 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 360 |
+
"loss": 0.0012,
|
| 361 |
+
"step": 400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 13.442622950819672,
|
| 365 |
+
"grad_norm": 0.9436277747154236,
|
| 366 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 367 |
+
"loss": 0.0145,
|
| 368 |
+
"step": 410
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 13.770491803278688,
|
| 372 |
+
"grad_norm": 5.284872055053711,
|
| 373 |
+
"learning_rate": 3e-05,
|
| 374 |
+
"loss": 0.0087,
|
| 375 |
+
"step": 420
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 13.770491803278688,
|
| 379 |
+
"eval_accuracy": 0.8166259168704156,
|
| 380 |
+
"eval_f1": 0.7751196172248804,
|
| 381 |
+
"eval_loss": 1.346622347831726,
|
| 382 |
+
"eval_precision": 0.7864077669902912,
|
| 383 |
+
"eval_recall": 0.7641509433962265,
|
| 384 |
+
"eval_runtime": 0.9819,
|
| 385 |
+
"eval_samples_per_second": 61.108,
|
| 386 |
+
"eval_steps_per_second": 8.148,
|
| 387 |
+
"step": 420
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 14.098360655737705,
|
| 391 |
+
"grad_norm": 0.003362592775374651,
|
| 392 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 393 |
+
"loss": 0.0011,
|
| 394 |
+
"step": 430
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 14.426229508196721,
|
| 398 |
+
"grad_norm": 0.011366785503923893,
|
| 399 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 400 |
+
"loss": 0.0003,
|
| 401 |
+
"step": 440
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 14.754098360655737,
|
| 405 |
+
"grad_norm": 0.003698177170008421,
|
| 406 |
+
"learning_rate": 2.5e-05,
|
| 407 |
+
"loss": 0.0002,
|
| 408 |
+
"step": 450
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 15.081967213114755,
|
| 412 |
+
"grad_norm": 0.0021139541640877724,
|
| 413 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 414 |
+
"loss": 0.0047,
|
| 415 |
+
"step": 460
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 15.40983606557377,
|
| 419 |
+
"grad_norm": 0.0036122933961451054,
|
| 420 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 421 |
+
"loss": 0.0002,
|
| 422 |
+
"step": 470
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 15.737704918032787,
|
| 426 |
+
"grad_norm": 0.010879104025661945,
|
| 427 |
+
"learning_rate": 2e-05,
|
| 428 |
+
"loss": 0.0002,
|
| 429 |
+
"step": 480
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 15.737704918032787,
|
| 433 |
+
"eval_accuracy": 0.8288508557457213,
|
| 434 |
+
"eval_f1": 0.7887323943661972,
|
| 435 |
+
"eval_loss": 1.271989107131958,
|
| 436 |
+
"eval_precision": 0.7850467289719626,
|
| 437 |
+
"eval_recall": 0.7924528301886793,
|
| 438 |
+
"eval_runtime": 0.9809,
|
| 439 |
+
"eval_samples_per_second": 61.168,
|
| 440 |
+
"eval_steps_per_second": 8.156,
|
| 441 |
+
"step": 480
|
| 442 |
+
}
|
| 443 |
+
],
|
| 444 |
+
"logging_steps": 10,
|
| 445 |
+
"max_steps": 600,
|
| 446 |
+
"num_input_tokens_seen": 0,
|
| 447 |
+
"num_train_epochs": 20,
|
| 448 |
+
"save_steps": 60,
|
| 449 |
+
"total_flos": 995567645030400.0,
|
| 450 |
+
"train_batch_size": 8,
|
| 451 |
+
"trial_name": null,
|
| 452 |
+
"trial_params": null
|
| 453 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7026924840e4aa3b8e2db88a642cd24bd019a103608b064c47f7cc2fa0e2224
|
| 3 |
+
size 4984
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|