Upload folder using huggingface_hub
Browse files- checkpoint-12500/config.json +43 -0
- checkpoint-12500/model.safetensors +3 -0
- checkpoint-12500/optimizer.pt +3 -0
- checkpoint-12500/rng_state.pth +3 -0
- checkpoint-12500/scheduler.pt +3 -0
- checkpoint-12500/special_tokens_map.json +37 -0
- checkpoint-12500/tokenizer.json +0 -0
- checkpoint-12500/tokenizer_config.json +60 -0
- checkpoint-12500/trainer_state.json +220 -0
- checkpoint-12500/training_args.bin +3 -0
- checkpoint-12500/vocab.txt +0 -0
- checkpoint-25000/config.json +43 -0
- checkpoint-25000/model.safetensors +3 -0
- checkpoint-25000/optimizer.pt +3 -0
- checkpoint-25000/rng_state.pth +3 -0
- checkpoint-25000/scheduler.pt +3 -0
- checkpoint-25000/special_tokens_map.json +37 -0
- checkpoint-25000/tokenizer.json +0 -0
- checkpoint-25000/tokenizer_config.json +60 -0
- checkpoint-25000/trainer_state.json +407 -0
- checkpoint-25000/training_args.bin +3 -0
- checkpoint-25000/vocab.txt +0 -0
- checkpoint-37500/config.json +43 -0
- checkpoint-37500/model.safetensors +3 -0
- checkpoint-37500/optimizer.pt +3 -0
- checkpoint-37500/rng_state.pth +3 -0
- checkpoint-37500/scheduler.pt +3 -0
- checkpoint-37500/special_tokens_map.json +37 -0
- checkpoint-37500/tokenizer.json +0 -0
- checkpoint-37500/tokenizer_config.json +60 -0
- checkpoint-37500/trainer_state.json +594 -0
- checkpoint-37500/training_args.bin +3 -0
- checkpoint-37500/vocab.txt +0 -0
- config.json +3 -3
- model.safetensors +2 -2
- runs/Mar05_14-03-48_23e08165d1e9/events.out.tfevents.1741183436.23e08165d1e9.676.0 +3 -0
- runs/Mar05_15-11-57_23e08165d1e9/events.out.tfevents.1741187522.23e08165d1e9.676.1 +3 -0
- runs/Mar05_16-20-53_23e08165d1e9/events.out.tfevents.1741191660.23e08165d1e9.676.2 +3 -0
- training_args.bin +3 -0
checkpoint-12500/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./distilbert-finetuned-hindi-ner",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-PER",
|
| 14 |
+
"2": "I-PER",
|
| 15 |
+
"3": "B-ORG",
|
| 16 |
+
"4": "I-ORG",
|
| 17 |
+
"5": "B-LOC",
|
| 18 |
+
"6": "I-LOC"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"B-LOC": 5,
|
| 23 |
+
"B-ORG": 3,
|
| 24 |
+
"B-PER": 1,
|
| 25 |
+
"I-LOC": 6,
|
| 26 |
+
"I-ORG": 4,
|
| 27 |
+
"I-PER": 2,
|
| 28 |
+
"O": 0
|
| 29 |
+
},
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "distilbert",
|
| 32 |
+
"n_heads": 12,
|
| 33 |
+
"n_layers": 6,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"qa_dropout": 0.1,
|
| 37 |
+
"seq_classif_dropout": 0.2,
|
| 38 |
+
"sinusoidal_pos_embds": false,
|
| 39 |
+
"tie_weights_": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.48.3",
|
| 42 |
+
"vocab_size": 28996
|
| 43 |
+
}
|
checkpoint-12500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06afc73e0c10d71a8f38034910b70becd6e5b8a1779c8259df4e84c746d3164e
|
| 3 |
+
size 260797516
|
checkpoint-12500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1639dd5070f5adf15a8ceb8fbf2d6f40719b90fa42b3470ef0416c6d9845b0
|
| 3 |
+
size 521655866
|
checkpoint-12500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2512dc01224b93eb46eabddb9c6d457c486013bd0731e7aeb5838a96aaecc5a5
|
| 3 |
+
size 14244
|
checkpoint-12500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd10644e8f9666cf40ad9e6edd064f6c87a35eacd0d161a739a838db73a1cb7f
|
| 3 |
+
size 1064
|
checkpoint-12500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": 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 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-12500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-12500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"stride": 0,
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
+
"unk_token": "[UNK]"
|
| 60 |
+
}
|
checkpoint-12500/trainer_state.json
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 3.339637279510498,
|
| 14 |
+
"learning_rate": 1.9733333333333336e-05,
|
| 15 |
+
"loss": 0.2685,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 1.5288997888565063,
|
| 21 |
+
"learning_rate": 1.9466666666666668e-05,
|
| 22 |
+
"loss": 0.2577,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 3.791400194168091,
|
| 28 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 29 |
+
"loss": 0.2659,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 10.789708137512207,
|
| 35 |
+
"learning_rate": 1.8933333333333334e-05,
|
| 36 |
+
"loss": 0.2651,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 1.8844208717346191,
|
| 42 |
+
"learning_rate": 1.866666666666667e-05,
|
| 43 |
+
"loss": 0.2641,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.7253724336624146,
|
| 49 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 50 |
+
"loss": 0.2652,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 2.3665554523468018,
|
| 56 |
+
"learning_rate": 1.8133333333333335e-05,
|
| 57 |
+
"loss": 0.259,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 3.057013750076294,
|
| 63 |
+
"learning_rate": 1.7866666666666666e-05,
|
| 64 |
+
"loss": 0.2708,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 2.6073246002197266,
|
| 70 |
+
"learning_rate": 1.76e-05,
|
| 71 |
+
"loss": 0.2604,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 1.4323502779006958,
|
| 77 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 78 |
+
"loss": 0.2569,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 3.2226264476776123,
|
| 84 |
+
"learning_rate": 1.706666666666667e-05,
|
| 85 |
+
"loss": 0.274,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 2.6208560466766357,
|
| 91 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 92 |
+
"loss": 0.2622,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 2.4076180458068848,
|
| 98 |
+
"learning_rate": 1.6533333333333333e-05,
|
| 99 |
+
"loss": 0.2617,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 1.4872561693191528,
|
| 105 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 106 |
+
"loss": 0.2739,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 3.3403637409210205,
|
| 112 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 113 |
+
"loss": 0.2665,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 1.4236797094345093,
|
| 119 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 120 |
+
"loss": 0.2617,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 4.096630096435547,
|
| 126 |
+
"learning_rate": 1.546666666666667e-05,
|
| 127 |
+
"loss": 0.2653,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 3.2297892570495605,
|
| 133 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 134 |
+
"loss": 0.2613,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 3.9957408905029297,
|
| 140 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 141 |
+
"loss": 0.2692,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 2.196535587310791,
|
| 147 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 148 |
+
"loss": 0.2589,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 2.062105894088745,
|
| 154 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 155 |
+
"loss": 0.2583,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 1.5509839057922363,
|
| 161 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 162 |
+
"loss": 0.2586,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 1.7661411762237549,
|
| 168 |
+
"learning_rate": 1.3866666666666669e-05,
|
| 169 |
+
"loss": 0.2602,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 2.222195625305176,
|
| 175 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 176 |
+
"loss": 0.2582,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 1.6238605976104736,
|
| 182 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 183 |
+
"loss": 0.2627,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_accuracy": 0.9296648117962265,
|
| 189 |
+
"eval_f1": 0.5910249872514025,
|
| 190 |
+
"eval_loss": 0.20293937623500824,
|
| 191 |
+
"eval_precision": 0.5815353738083292,
|
| 192 |
+
"eval_recall": 0.60082944530845,
|
| 193 |
+
"eval_runtime": 3.8098,
|
| 194 |
+
"eval_samples_per_second": 227.573,
|
| 195 |
+
"eval_steps_per_second": 28.611,
|
| 196 |
+
"step": 12500
|
| 197 |
+
}
|
| 198 |
+
],
|
| 199 |
+
"logging_steps": 500,
|
| 200 |
+
"max_steps": 37500,
|
| 201 |
+
"num_input_tokens_seen": 0,
|
| 202 |
+
"num_train_epochs": 3,
|
| 203 |
+
"save_steps": 500,
|
| 204 |
+
"stateful_callbacks": {
|
| 205 |
+
"TrainerControl": {
|
| 206 |
+
"args": {
|
| 207 |
+
"should_epoch_stop": false,
|
| 208 |
+
"should_evaluate": false,
|
| 209 |
+
"should_log": false,
|
| 210 |
+
"should_save": true,
|
| 211 |
+
"should_training_stop": false
|
| 212 |
+
},
|
| 213 |
+
"attributes": {}
|
| 214 |
+
}
|
| 215 |
+
},
|
| 216 |
+
"total_flos": 3237078235242192.0,
|
| 217 |
+
"train_batch_size": 8,
|
| 218 |
+
"trial_name": null,
|
| 219 |
+
"trial_params": null
|
| 220 |
+
}
|
checkpoint-12500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feda197231fffb20bb4da80d2a361dba76a244111fffd01def26b27559601916
|
| 3 |
+
size 5368
|
checkpoint-12500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-25000/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./distilbert-finetuned-hindi-ner",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-PER",
|
| 14 |
+
"2": "I-PER",
|
| 15 |
+
"3": "B-ORG",
|
| 16 |
+
"4": "I-ORG",
|
| 17 |
+
"5": "B-LOC",
|
| 18 |
+
"6": "I-LOC"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"B-LOC": 5,
|
| 23 |
+
"B-ORG": 3,
|
| 24 |
+
"B-PER": 1,
|
| 25 |
+
"I-LOC": 6,
|
| 26 |
+
"I-ORG": 4,
|
| 27 |
+
"I-PER": 2,
|
| 28 |
+
"O": 0
|
| 29 |
+
},
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "distilbert",
|
| 32 |
+
"n_heads": 12,
|
| 33 |
+
"n_layers": 6,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"qa_dropout": 0.1,
|
| 37 |
+
"seq_classif_dropout": 0.2,
|
| 38 |
+
"sinusoidal_pos_embds": false,
|
| 39 |
+
"tie_weights_": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.48.3",
|
| 42 |
+
"vocab_size": 28996
|
| 43 |
+
}
|
checkpoint-25000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92766038806bc58dbbd207f29a31d2f589d89b74c42c76eba8ec0dd8b2f86ea5
|
| 3 |
+
size 260797516
|
checkpoint-25000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28b3e7941a864edd4866e5553447d6f615692ad15d544f333f53ac1463e2a7d5
|
| 3 |
+
size 521655866
|
checkpoint-25000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ca856cc873b9c686ae4364995aeb81e6ac86975f358b62a7b85c21d5d19da1
|
| 3 |
+
size 14244
|
checkpoint-25000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba395418fec3faebf0a851318d7a35f897653a2fb22c748f68dc0be9c7f990d5
|
| 3 |
+
size 1064
|
checkpoint-25000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": 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 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-25000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-25000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"stride": 0,
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
+
"unk_token": "[UNK]"
|
| 60 |
+
}
|
checkpoint-25000/trainer_state.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 25000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 3.339637279510498,
|
| 14 |
+
"learning_rate": 1.9733333333333336e-05,
|
| 15 |
+
"loss": 0.2685,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 1.5288997888565063,
|
| 21 |
+
"learning_rate": 1.9466666666666668e-05,
|
| 22 |
+
"loss": 0.2577,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 3.791400194168091,
|
| 28 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 29 |
+
"loss": 0.2659,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 10.789708137512207,
|
| 35 |
+
"learning_rate": 1.8933333333333334e-05,
|
| 36 |
+
"loss": 0.2651,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 1.8844208717346191,
|
| 42 |
+
"learning_rate": 1.866666666666667e-05,
|
| 43 |
+
"loss": 0.2641,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.7253724336624146,
|
| 49 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 50 |
+
"loss": 0.2652,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 2.3665554523468018,
|
| 56 |
+
"learning_rate": 1.8133333333333335e-05,
|
| 57 |
+
"loss": 0.259,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 3.057013750076294,
|
| 63 |
+
"learning_rate": 1.7866666666666666e-05,
|
| 64 |
+
"loss": 0.2708,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 2.6073246002197266,
|
| 70 |
+
"learning_rate": 1.76e-05,
|
| 71 |
+
"loss": 0.2604,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 1.4323502779006958,
|
| 77 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 78 |
+
"loss": 0.2569,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 3.2226264476776123,
|
| 84 |
+
"learning_rate": 1.706666666666667e-05,
|
| 85 |
+
"loss": 0.274,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 2.6208560466766357,
|
| 91 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 92 |
+
"loss": 0.2622,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 2.4076180458068848,
|
| 98 |
+
"learning_rate": 1.6533333333333333e-05,
|
| 99 |
+
"loss": 0.2617,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 1.4872561693191528,
|
| 105 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 106 |
+
"loss": 0.2739,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 3.3403637409210205,
|
| 112 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 113 |
+
"loss": 0.2665,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 1.4236797094345093,
|
| 119 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 120 |
+
"loss": 0.2617,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 4.096630096435547,
|
| 126 |
+
"learning_rate": 1.546666666666667e-05,
|
| 127 |
+
"loss": 0.2653,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 3.2297892570495605,
|
| 133 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 134 |
+
"loss": 0.2613,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 3.9957408905029297,
|
| 140 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 141 |
+
"loss": 0.2692,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 2.196535587310791,
|
| 147 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 148 |
+
"loss": 0.2589,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 2.062105894088745,
|
| 154 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 155 |
+
"loss": 0.2583,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 1.5509839057922363,
|
| 161 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 162 |
+
"loss": 0.2586,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 1.7661411762237549,
|
| 168 |
+
"learning_rate": 1.3866666666666669e-05,
|
| 169 |
+
"loss": 0.2602,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 2.222195625305176,
|
| 175 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 176 |
+
"loss": 0.2582,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 1.6238605976104736,
|
| 182 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 183 |
+
"loss": 0.2627,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_accuracy": 0.9296648117962265,
|
| 189 |
+
"eval_f1": 0.5910249872514025,
|
| 190 |
+
"eval_loss": 0.20293937623500824,
|
| 191 |
+
"eval_precision": 0.5815353738083292,
|
| 192 |
+
"eval_recall": 0.60082944530845,
|
| 193 |
+
"eval_runtime": 3.8098,
|
| 194 |
+
"eval_samples_per_second": 227.573,
|
| 195 |
+
"eval_steps_per_second": 28.611,
|
| 196 |
+
"step": 12500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.04,
|
| 200 |
+
"grad_norm": 5.0923686027526855,
|
| 201 |
+
"learning_rate": 1.3066666666666668e-05,
|
| 202 |
+
"loss": 0.2433,
|
| 203 |
+
"step": 13000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.08,
|
| 207 |
+
"grad_norm": 3.4041550159454346,
|
| 208 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 209 |
+
"loss": 0.2257,
|
| 210 |
+
"step": 13500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.12,
|
| 214 |
+
"grad_norm": 1.6454646587371826,
|
| 215 |
+
"learning_rate": 1.2533333333333336e-05,
|
| 216 |
+
"loss": 0.2275,
|
| 217 |
+
"step": 14000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.16,
|
| 221 |
+
"grad_norm": 4.137843608856201,
|
| 222 |
+
"learning_rate": 1.2266666666666667e-05,
|
| 223 |
+
"loss": 0.2326,
|
| 224 |
+
"step": 14500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.2,
|
| 228 |
+
"grad_norm": 2.6698648929595947,
|
| 229 |
+
"learning_rate": 1.2e-05,
|
| 230 |
+
"loss": 0.2219,
|
| 231 |
+
"step": 15000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.24,
|
| 235 |
+
"grad_norm": 2.044994592666626,
|
| 236 |
+
"learning_rate": 1.1733333333333335e-05,
|
| 237 |
+
"loss": 0.2366,
|
| 238 |
+
"step": 15500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.28,
|
| 242 |
+
"grad_norm": 3.0846433639526367,
|
| 243 |
+
"learning_rate": 1.1466666666666668e-05,
|
| 244 |
+
"loss": 0.2296,
|
| 245 |
+
"step": 16000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.32,
|
| 249 |
+
"grad_norm": 2.076545238494873,
|
| 250 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 251 |
+
"loss": 0.2315,
|
| 252 |
+
"step": 16500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.3599999999999999,
|
| 256 |
+
"grad_norm": 2.738480567932129,
|
| 257 |
+
"learning_rate": 1.0933333333333334e-05,
|
| 258 |
+
"loss": 0.2311,
|
| 259 |
+
"step": 17000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.4,
|
| 263 |
+
"grad_norm": 1.7157602310180664,
|
| 264 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 265 |
+
"loss": 0.2336,
|
| 266 |
+
"step": 17500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.44,
|
| 270 |
+
"grad_norm": 2.5812087059020996,
|
| 271 |
+
"learning_rate": 1.04e-05,
|
| 272 |
+
"loss": 0.2447,
|
| 273 |
+
"step": 18000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.48,
|
| 277 |
+
"grad_norm": 2.6329290866851807,
|
| 278 |
+
"learning_rate": 1.0133333333333335e-05,
|
| 279 |
+
"loss": 0.2354,
|
| 280 |
+
"step": 18500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.52,
|
| 284 |
+
"grad_norm": 1.931725025177002,
|
| 285 |
+
"learning_rate": 9.866666666666668e-06,
|
| 286 |
+
"loss": 0.2317,
|
| 287 |
+
"step": 19000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.56,
|
| 291 |
+
"grad_norm": 4.6852126121521,
|
| 292 |
+
"learning_rate": 9.600000000000001e-06,
|
| 293 |
+
"loss": 0.2401,
|
| 294 |
+
"step": 19500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.6,
|
| 298 |
+
"grad_norm": 1.21334969997406,
|
| 299 |
+
"learning_rate": 9.333333333333334e-06,
|
| 300 |
+
"loss": 0.2307,
|
| 301 |
+
"step": 20000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.6400000000000001,
|
| 305 |
+
"grad_norm": 2.32155704498291,
|
| 306 |
+
"learning_rate": 9.066666666666667e-06,
|
| 307 |
+
"loss": 0.2278,
|
| 308 |
+
"step": 20500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.6800000000000002,
|
| 312 |
+
"grad_norm": 3.032379150390625,
|
| 313 |
+
"learning_rate": 8.8e-06,
|
| 314 |
+
"loss": 0.2315,
|
| 315 |
+
"step": 21000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.72,
|
| 319 |
+
"grad_norm": 5.9133524894714355,
|
| 320 |
+
"learning_rate": 8.533333333333335e-06,
|
| 321 |
+
"loss": 0.2412,
|
| 322 |
+
"step": 21500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.76,
|
| 326 |
+
"grad_norm": 5.587306976318359,
|
| 327 |
+
"learning_rate": 8.266666666666667e-06,
|
| 328 |
+
"loss": 0.2315,
|
| 329 |
+
"step": 22000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.8,
|
| 333 |
+
"grad_norm": 2.8017914295196533,
|
| 334 |
+
"learning_rate": 8.000000000000001e-06,
|
| 335 |
+
"loss": 0.2321,
|
| 336 |
+
"step": 22500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.8399999999999999,
|
| 340 |
+
"grad_norm": 7.2547607421875,
|
| 341 |
+
"learning_rate": 7.733333333333334e-06,
|
| 342 |
+
"loss": 0.2369,
|
| 343 |
+
"step": 23000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.88,
|
| 347 |
+
"grad_norm": 1.4793908596038818,
|
| 348 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 349 |
+
"loss": 0.237,
|
| 350 |
+
"step": 23500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.92,
|
| 354 |
+
"grad_norm": 2.481879949569702,
|
| 355 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 356 |
+
"loss": 0.2221,
|
| 357 |
+
"step": 24000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.96,
|
| 361 |
+
"grad_norm": 0.8497968316078186,
|
| 362 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 363 |
+
"loss": 0.2282,
|
| 364 |
+
"step": 24500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.0,
|
| 368 |
+
"grad_norm": 1.056018590927124,
|
| 369 |
+
"learning_rate": 6.666666666666667e-06,
|
| 370 |
+
"loss": 0.2315,
|
| 371 |
+
"step": 25000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.0,
|
| 375 |
+
"eval_accuracy": 0.9270604987540517,
|
| 376 |
+
"eval_f1": 0.5862503147821707,
|
| 377 |
+
"eval_loss": 0.20907191932201385,
|
| 378 |
+
"eval_precision": 0.5700293829578844,
|
| 379 |
+
"eval_recall": 0.6034214618973561,
|
| 380 |
+
"eval_runtime": 3.7952,
|
| 381 |
+
"eval_samples_per_second": 228.446,
|
| 382 |
+
"eval_steps_per_second": 28.72,
|
| 383 |
+
"step": 25000
|
| 384 |
+
}
|
| 385 |
+
],
|
| 386 |
+
"logging_steps": 500,
|
| 387 |
+
"max_steps": 37500,
|
| 388 |
+
"num_input_tokens_seen": 0,
|
| 389 |
+
"num_train_epochs": 3,
|
| 390 |
+
"save_steps": 500,
|
| 391 |
+
"stateful_callbacks": {
|
| 392 |
+
"TrainerControl": {
|
| 393 |
+
"args": {
|
| 394 |
+
"should_epoch_stop": false,
|
| 395 |
+
"should_evaluate": false,
|
| 396 |
+
"should_log": false,
|
| 397 |
+
"should_save": true,
|
| 398 |
+
"should_training_stop": false
|
| 399 |
+
},
|
| 400 |
+
"attributes": {}
|
| 401 |
+
}
|
| 402 |
+
},
|
| 403 |
+
"total_flos": 6475256914039056.0,
|
| 404 |
+
"train_batch_size": 8,
|
| 405 |
+
"trial_name": null,
|
| 406 |
+
"trial_params": null
|
| 407 |
+
}
|
checkpoint-25000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feda197231fffb20bb4da80d2a361dba76a244111fffd01def26b27559601916
|
| 3 |
+
size 5368
|
checkpoint-25000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-37500/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./distilbert-finetuned-hindi-ner",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-PER",
|
| 14 |
+
"2": "I-PER",
|
| 15 |
+
"3": "B-ORG",
|
| 16 |
+
"4": "I-ORG",
|
| 17 |
+
"5": "B-LOC",
|
| 18 |
+
"6": "I-LOC"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"B-LOC": 5,
|
| 23 |
+
"B-ORG": 3,
|
| 24 |
+
"B-PER": 1,
|
| 25 |
+
"I-LOC": 6,
|
| 26 |
+
"I-ORG": 4,
|
| 27 |
+
"I-PER": 2,
|
| 28 |
+
"O": 0
|
| 29 |
+
},
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "distilbert",
|
| 32 |
+
"n_heads": 12,
|
| 33 |
+
"n_layers": 6,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"qa_dropout": 0.1,
|
| 37 |
+
"seq_classif_dropout": 0.2,
|
| 38 |
+
"sinusoidal_pos_embds": false,
|
| 39 |
+
"tie_weights_": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.48.3",
|
| 42 |
+
"vocab_size": 28996
|
| 43 |
+
}
|
checkpoint-37500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842437e0defc7b49b9bd0e0bf94bb2db4e8462d7fe93d66d525499f72b75da1f
|
| 3 |
+
size 260797516
|
checkpoint-37500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b857a2db0a265e0e3002db7adbddc00c6862fb8a05667c4fc2e6ab4a5913de94
|
| 3 |
+
size 521655866
|
checkpoint-37500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d76677858d2fb183630a1acbe5944a91e1d19b54e2a27319e8d26364b22ea44
|
| 3 |
+
size 14244
|
checkpoint-37500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afce7cbf6aab256e5ff40cfb3218b45cc289e5fd0f8e409e0b58cb42ef3e61f8
|
| 3 |
+
size 1064
|
checkpoint-37500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": 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 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-37500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-37500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"stride": 0,
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
+
"unk_token": "[UNK]"
|
| 60 |
+
}
|
checkpoint-37500/trainer_state.json
ADDED
|
@@ -0,0 +1,594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 37500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 3.339637279510498,
|
| 14 |
+
"learning_rate": 1.9733333333333336e-05,
|
| 15 |
+
"loss": 0.2685,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 1.5288997888565063,
|
| 21 |
+
"learning_rate": 1.9466666666666668e-05,
|
| 22 |
+
"loss": 0.2577,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 3.791400194168091,
|
| 28 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 29 |
+
"loss": 0.2659,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 10.789708137512207,
|
| 35 |
+
"learning_rate": 1.8933333333333334e-05,
|
| 36 |
+
"loss": 0.2651,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 1.8844208717346191,
|
| 42 |
+
"learning_rate": 1.866666666666667e-05,
|
| 43 |
+
"loss": 0.2641,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.7253724336624146,
|
| 49 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 50 |
+
"loss": 0.2652,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 2.3665554523468018,
|
| 56 |
+
"learning_rate": 1.8133333333333335e-05,
|
| 57 |
+
"loss": 0.259,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 3.057013750076294,
|
| 63 |
+
"learning_rate": 1.7866666666666666e-05,
|
| 64 |
+
"loss": 0.2708,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 2.6073246002197266,
|
| 70 |
+
"learning_rate": 1.76e-05,
|
| 71 |
+
"loss": 0.2604,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 1.4323502779006958,
|
| 77 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 78 |
+
"loss": 0.2569,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 3.2226264476776123,
|
| 84 |
+
"learning_rate": 1.706666666666667e-05,
|
| 85 |
+
"loss": 0.274,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 2.6208560466766357,
|
| 91 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 92 |
+
"loss": 0.2622,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 2.4076180458068848,
|
| 98 |
+
"learning_rate": 1.6533333333333333e-05,
|
| 99 |
+
"loss": 0.2617,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 1.4872561693191528,
|
| 105 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 106 |
+
"loss": 0.2739,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 3.3403637409210205,
|
| 112 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 113 |
+
"loss": 0.2665,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 1.4236797094345093,
|
| 119 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 120 |
+
"loss": 0.2617,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 4.096630096435547,
|
| 126 |
+
"learning_rate": 1.546666666666667e-05,
|
| 127 |
+
"loss": 0.2653,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 3.2297892570495605,
|
| 133 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 134 |
+
"loss": 0.2613,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 3.9957408905029297,
|
| 140 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 141 |
+
"loss": 0.2692,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 2.196535587310791,
|
| 147 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 148 |
+
"loss": 0.2589,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 2.062105894088745,
|
| 154 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 155 |
+
"loss": 0.2583,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 1.5509839057922363,
|
| 161 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 162 |
+
"loss": 0.2586,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 1.7661411762237549,
|
| 168 |
+
"learning_rate": 1.3866666666666669e-05,
|
| 169 |
+
"loss": 0.2602,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 2.222195625305176,
|
| 175 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 176 |
+
"loss": 0.2582,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 1.6238605976104736,
|
| 182 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 183 |
+
"loss": 0.2627,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_accuracy": 0.9296648117962265,
|
| 189 |
+
"eval_f1": 0.5910249872514025,
|
| 190 |
+
"eval_loss": 0.20293937623500824,
|
| 191 |
+
"eval_precision": 0.5815353738083292,
|
| 192 |
+
"eval_recall": 0.60082944530845,
|
| 193 |
+
"eval_runtime": 3.8098,
|
| 194 |
+
"eval_samples_per_second": 227.573,
|
| 195 |
+
"eval_steps_per_second": 28.611,
|
| 196 |
+
"step": 12500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.04,
|
| 200 |
+
"grad_norm": 5.0923686027526855,
|
| 201 |
+
"learning_rate": 1.3066666666666668e-05,
|
| 202 |
+
"loss": 0.2433,
|
| 203 |
+
"step": 13000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.08,
|
| 207 |
+
"grad_norm": 3.4041550159454346,
|
| 208 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 209 |
+
"loss": 0.2257,
|
| 210 |
+
"step": 13500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.12,
|
| 214 |
+
"grad_norm": 1.6454646587371826,
|
| 215 |
+
"learning_rate": 1.2533333333333336e-05,
|
| 216 |
+
"loss": 0.2275,
|
| 217 |
+
"step": 14000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.16,
|
| 221 |
+
"grad_norm": 4.137843608856201,
|
| 222 |
+
"learning_rate": 1.2266666666666667e-05,
|
| 223 |
+
"loss": 0.2326,
|
| 224 |
+
"step": 14500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.2,
|
| 228 |
+
"grad_norm": 2.6698648929595947,
|
| 229 |
+
"learning_rate": 1.2e-05,
|
| 230 |
+
"loss": 0.2219,
|
| 231 |
+
"step": 15000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.24,
|
| 235 |
+
"grad_norm": 2.044994592666626,
|
| 236 |
+
"learning_rate": 1.1733333333333335e-05,
|
| 237 |
+
"loss": 0.2366,
|
| 238 |
+
"step": 15500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.28,
|
| 242 |
+
"grad_norm": 3.0846433639526367,
|
| 243 |
+
"learning_rate": 1.1466666666666668e-05,
|
| 244 |
+
"loss": 0.2296,
|
| 245 |
+
"step": 16000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.32,
|
| 249 |
+
"grad_norm": 2.076545238494873,
|
| 250 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 251 |
+
"loss": 0.2315,
|
| 252 |
+
"step": 16500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.3599999999999999,
|
| 256 |
+
"grad_norm": 2.738480567932129,
|
| 257 |
+
"learning_rate": 1.0933333333333334e-05,
|
| 258 |
+
"loss": 0.2311,
|
| 259 |
+
"step": 17000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.4,
|
| 263 |
+
"grad_norm": 1.7157602310180664,
|
| 264 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 265 |
+
"loss": 0.2336,
|
| 266 |
+
"step": 17500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.44,
|
| 270 |
+
"grad_norm": 2.5812087059020996,
|
| 271 |
+
"learning_rate": 1.04e-05,
|
| 272 |
+
"loss": 0.2447,
|
| 273 |
+
"step": 18000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.48,
|
| 277 |
+
"grad_norm": 2.6329290866851807,
|
| 278 |
+
"learning_rate": 1.0133333333333335e-05,
|
| 279 |
+
"loss": 0.2354,
|
| 280 |
+
"step": 18500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.52,
|
| 284 |
+
"grad_norm": 1.931725025177002,
|
| 285 |
+
"learning_rate": 9.866666666666668e-06,
|
| 286 |
+
"loss": 0.2317,
|
| 287 |
+
"step": 19000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.56,
|
| 291 |
+
"grad_norm": 4.6852126121521,
|
| 292 |
+
"learning_rate": 9.600000000000001e-06,
|
| 293 |
+
"loss": 0.2401,
|
| 294 |
+
"step": 19500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.6,
|
| 298 |
+
"grad_norm": 1.21334969997406,
|
| 299 |
+
"learning_rate": 9.333333333333334e-06,
|
| 300 |
+
"loss": 0.2307,
|
| 301 |
+
"step": 20000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.6400000000000001,
|
| 305 |
+
"grad_norm": 2.32155704498291,
|
| 306 |
+
"learning_rate": 9.066666666666667e-06,
|
| 307 |
+
"loss": 0.2278,
|
| 308 |
+
"step": 20500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.6800000000000002,
|
| 312 |
+
"grad_norm": 3.032379150390625,
|
| 313 |
+
"learning_rate": 8.8e-06,
|
| 314 |
+
"loss": 0.2315,
|
| 315 |
+
"step": 21000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.72,
|
| 319 |
+
"grad_norm": 5.9133524894714355,
|
| 320 |
+
"learning_rate": 8.533333333333335e-06,
|
| 321 |
+
"loss": 0.2412,
|
| 322 |
+
"step": 21500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.76,
|
| 326 |
+
"grad_norm": 5.587306976318359,
|
| 327 |
+
"learning_rate": 8.266666666666667e-06,
|
| 328 |
+
"loss": 0.2315,
|
| 329 |
+
"step": 22000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.8,
|
| 333 |
+
"grad_norm": 2.8017914295196533,
|
| 334 |
+
"learning_rate": 8.000000000000001e-06,
|
| 335 |
+
"loss": 0.2321,
|
| 336 |
+
"step": 22500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.8399999999999999,
|
| 340 |
+
"grad_norm": 7.2547607421875,
|
| 341 |
+
"learning_rate": 7.733333333333334e-06,
|
| 342 |
+
"loss": 0.2369,
|
| 343 |
+
"step": 23000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.88,
|
| 347 |
+
"grad_norm": 1.4793908596038818,
|
| 348 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 349 |
+
"loss": 0.237,
|
| 350 |
+
"step": 23500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.92,
|
| 354 |
+
"grad_norm": 2.481879949569702,
|
| 355 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 356 |
+
"loss": 0.2221,
|
| 357 |
+
"step": 24000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.96,
|
| 361 |
+
"grad_norm": 0.8497968316078186,
|
| 362 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 363 |
+
"loss": 0.2282,
|
| 364 |
+
"step": 24500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.0,
|
| 368 |
+
"grad_norm": 1.056018590927124,
|
| 369 |
+
"learning_rate": 6.666666666666667e-06,
|
| 370 |
+
"loss": 0.2315,
|
| 371 |
+
"step": 25000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.0,
|
| 375 |
+
"eval_accuracy": 0.9270604987540517,
|
| 376 |
+
"eval_f1": 0.5862503147821707,
|
| 377 |
+
"eval_loss": 0.20907191932201385,
|
| 378 |
+
"eval_precision": 0.5700293829578844,
|
| 379 |
+
"eval_recall": 0.6034214618973561,
|
| 380 |
+
"eval_runtime": 3.7952,
|
| 381 |
+
"eval_samples_per_second": 228.446,
|
| 382 |
+
"eval_steps_per_second": 28.72,
|
| 383 |
+
"step": 25000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.04,
|
| 387 |
+
"grad_norm": 1.8908640146255493,
|
| 388 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 389 |
+
"loss": 0.2111,
|
| 390 |
+
"step": 25500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.08,
|
| 394 |
+
"grad_norm": 2.534010648727417,
|
| 395 |
+
"learning_rate": 6.133333333333334e-06,
|
| 396 |
+
"loss": 0.1973,
|
| 397 |
+
"step": 26000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.12,
|
| 401 |
+
"grad_norm": 1.7518447637557983,
|
| 402 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 403 |
+
"loss": 0.2091,
|
| 404 |
+
"step": 26500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.16,
|
| 408 |
+
"grad_norm": 1.7830463647842407,
|
| 409 |
+
"learning_rate": 5.600000000000001e-06,
|
| 410 |
+
"loss": 0.2139,
|
| 411 |
+
"step": 27000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.2,
|
| 415 |
+
"grad_norm": 5.354440212249756,
|
| 416 |
+
"learning_rate": 5.333333333333334e-06,
|
| 417 |
+
"loss": 0.2143,
|
| 418 |
+
"step": 27500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.24,
|
| 422 |
+
"grad_norm": 2.237147569656372,
|
| 423 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 424 |
+
"loss": 0.2104,
|
| 425 |
+
"step": 28000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.2800000000000002,
|
| 429 |
+
"grad_norm": 1.6922296285629272,
|
| 430 |
+
"learning_rate": 4.800000000000001e-06,
|
| 431 |
+
"loss": 0.1973,
|
| 432 |
+
"step": 28500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.32,
|
| 436 |
+
"grad_norm": 1.9520875215530396,
|
| 437 |
+
"learning_rate": 4.533333333333334e-06,
|
| 438 |
+
"loss": 0.2093,
|
| 439 |
+
"step": 29000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.36,
|
| 443 |
+
"grad_norm": 2.9851980209350586,
|
| 444 |
+
"learning_rate": 4.266666666666668e-06,
|
| 445 |
+
"loss": 0.2048,
|
| 446 |
+
"step": 29500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.4,
|
| 450 |
+
"grad_norm": 4.275035858154297,
|
| 451 |
+
"learning_rate": 4.000000000000001e-06,
|
| 452 |
+
"loss": 0.2078,
|
| 453 |
+
"step": 30000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.44,
|
| 457 |
+
"grad_norm": 8.405248641967773,
|
| 458 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 459 |
+
"loss": 0.2044,
|
| 460 |
+
"step": 30500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.48,
|
| 464 |
+
"grad_norm": 1.7770625352859497,
|
| 465 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 466 |
+
"loss": 0.2122,
|
| 467 |
+
"step": 31000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.52,
|
| 471 |
+
"grad_norm": 1.771949052810669,
|
| 472 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 473 |
+
"loss": 0.2054,
|
| 474 |
+
"step": 31500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.56,
|
| 478 |
+
"grad_norm": 3.629131317138672,
|
| 479 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 480 |
+
"loss": 0.2158,
|
| 481 |
+
"step": 32000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.6,
|
| 485 |
+
"grad_norm": 1.4482274055480957,
|
| 486 |
+
"learning_rate": 2.666666666666667e-06,
|
| 487 |
+
"loss": 0.2101,
|
| 488 |
+
"step": 32500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.64,
|
| 492 |
+
"grad_norm": 3.019331693649292,
|
| 493 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 494 |
+
"loss": 0.1936,
|
| 495 |
+
"step": 33000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.68,
|
| 499 |
+
"grad_norm": 1.6766985654830933,
|
| 500 |
+
"learning_rate": 2.133333333333334e-06,
|
| 501 |
+
"loss": 0.2097,
|
| 502 |
+
"step": 33500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.7199999999999998,
|
| 506 |
+
"grad_norm": 2.99959397315979,
|
| 507 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 508 |
+
"loss": 0.2073,
|
| 509 |
+
"step": 34000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.76,
|
| 513 |
+
"grad_norm": 3.5642282962799072,
|
| 514 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 515 |
+
"loss": 0.2131,
|
| 516 |
+
"step": 34500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.8,
|
| 520 |
+
"grad_norm": 2.3027596473693848,
|
| 521 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 522 |
+
"loss": 0.2054,
|
| 523 |
+
"step": 35000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.84,
|
| 527 |
+
"grad_norm": 2.8312253952026367,
|
| 528 |
+
"learning_rate": 1.066666666666667e-06,
|
| 529 |
+
"loss": 0.1987,
|
| 530 |
+
"step": 35500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.88,
|
| 534 |
+
"grad_norm": 1.6539475917816162,
|
| 535 |
+
"learning_rate": 8.000000000000001e-07,
|
| 536 |
+
"loss": 0.2131,
|
| 537 |
+
"step": 36000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.92,
|
| 541 |
+
"grad_norm": 2.7067487239837646,
|
| 542 |
+
"learning_rate": 5.333333333333335e-07,
|
| 543 |
+
"loss": 0.1959,
|
| 544 |
+
"step": 36500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.96,
|
| 548 |
+
"grad_norm": 2.1856722831726074,
|
| 549 |
+
"learning_rate": 2.666666666666667e-07,
|
| 550 |
+
"loss": 0.2147,
|
| 551 |
+
"step": 37000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 3.0,
|
| 555 |
+
"grad_norm": 4.923337459564209,
|
| 556 |
+
"learning_rate": 0.0,
|
| 557 |
+
"loss": 0.1981,
|
| 558 |
+
"step": 37500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 3.0,
|
| 562 |
+
"eval_accuracy": 0.9298334363816911,
|
| 563 |
+
"eval_f1": 0.596446046870976,
|
| 564 |
+
"eval_loss": 0.2079714834690094,
|
| 565 |
+
"eval_precision": 0.5926305015353122,
|
| 566 |
+
"eval_recall": 0.6003110419906688,
|
| 567 |
+
"eval_runtime": 3.8558,
|
| 568 |
+
"eval_samples_per_second": 224.855,
|
| 569 |
+
"eval_steps_per_second": 28.269,
|
| 570 |
+
"step": 37500
|
| 571 |
+
}
|
| 572 |
+
],
|
| 573 |
+
"logging_steps": 500,
|
| 574 |
+
"max_steps": 37500,
|
| 575 |
+
"num_input_tokens_seen": 0,
|
| 576 |
+
"num_train_epochs": 3,
|
| 577 |
+
"save_steps": 500,
|
| 578 |
+
"stateful_callbacks": {
|
| 579 |
+
"TrainerControl": {
|
| 580 |
+
"args": {
|
| 581 |
+
"should_epoch_stop": false,
|
| 582 |
+
"should_evaluate": false,
|
| 583 |
+
"should_log": false,
|
| 584 |
+
"should_save": true,
|
| 585 |
+
"should_training_stop": true
|
| 586 |
+
},
|
| 587 |
+
"attributes": {}
|
| 588 |
+
}
|
| 589 |
+
},
|
| 590 |
+
"total_flos": 9710573214610224.0,
|
| 591 |
+
"train_batch_size": 8,
|
| 592 |
+
"trial_name": null,
|
| 593 |
+
"trial_params": null
|
| 594 |
+
}
|
checkpoint-37500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feda197231fffb20bb4da80d2a361dba76a244111fffd01def26b27559601916
|
| 3 |
+
size 5368
|
checkpoint-37500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "distilbert-finetuned-hindi-ner",
|
| 3 |
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"dim": 768,
|
|
@@ -38,6 +38,6 @@
|
|
| 38 |
"sinusoidal_pos_embds": false,
|
| 39 |
"tie_weights_": true,
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
-
"transformers_version": "4.
|
| 42 |
"vocab_size": 28996
|
| 43 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./distilbert-finetuned-hindi-ner",
|
| 3 |
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"dim": 768,
|
|
|
|
| 38 |
"sinusoidal_pos_embds": false,
|
| 39 |
"tie_weights_": true,
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.48.3",
|
| 42 |
"vocab_size": 28996
|
| 43 |
}
|
model.safetensors
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 sha256:842437e0defc7b49b9bd0e0bf94bb2db4e8462d7fe93d66d525499f72b75da1f
|
| 3 |
+
size 260797516
|
runs/Mar05_14-03-48_23e08165d1e9/events.out.tfevents.1741183436.23e08165d1e9.676.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe4f8091f177fea64be6b7b631a5db4bb71236836920bdfe1495e65f4a2ee0df
|
| 3 |
+
size 23110
|
runs/Mar05_15-11-57_23e08165d1e9/events.out.tfevents.1741187522.23e08165d1e9.676.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04094e8d971ec87a6f6d86922beab70ec3cabaec0f30483d7658bb20caf943ec
|
| 3 |
+
size 23116
|
runs/Mar05_16-20-53_23e08165d1e9/events.out.tfevents.1741191660.23e08165d1e9.676.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be388e0c6d09ad98e1b2aa11cf3a09f6f89b05df0fc0eaaac6362a016bbd8fc0
|
| 3 |
+
size 23116
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feda197231fffb20bb4da80d2a361dba76a244111fffd01def26b27559601916
|
| 3 |
+
size 5368
|