Upload fine-tuned toxic comment classifier model
Browse files- checkpoint-15500/config.json +25 -0
- checkpoint-15500/model.safetensors +3 -0
- checkpoint-15500/optimizer.pt +3 -0
- checkpoint-15500/rng_state.pth +3 -0
- checkpoint-15500/scheduler.pt +3 -0
- checkpoint-15500/special_tokens_map.json +7 -0
- checkpoint-15500/tokenizer.json +0 -0
- checkpoint-15500/tokenizer_config.json +56 -0
- checkpoint-15500/trainer_state.json +622 -0
- checkpoint-15500/training_args.bin +3 -0
- checkpoint-15500/vocab.txt +0 -0
- checkpoint-15958/config.json +25 -0
- checkpoint-15958/model.safetensors +3 -0
- checkpoint-15958/optimizer.pt +3 -0
- checkpoint-15958/rng_state.pth +3 -0
- checkpoint-15958/scheduler.pt +3 -0
- checkpoint-15958/special_tokens_map.json +7 -0
- checkpoint-15958/tokenizer.json +0 -0
- checkpoint-15958/tokenizer_config.json +56 -0
- checkpoint-15958/trainer_state.json +622 -0
- checkpoint-15958/training_args.bin +3 -0
- checkpoint-15958/vocab.txt +0 -0
- config.json +25 -0
- logs/events.out.tfevents.1757646327.algo-1.92.0 +3 -0
- logs/events.out.tfevents.1757663250.algo-1.92.1 +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-15500/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
checkpoint-15500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f618d20266cc912b00123de2b86529b06f173d65b62ea63bd72aa9b38beeb31f
|
| 3 |
+
size 267832560
|
checkpoint-15500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28ab06937ae9b7a4df47e3efaa4a1b54b70b48f0d4bfa8594815c4cfbbbee623
|
| 3 |
+
size 535727290
|
checkpoint-15500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02431a603e424a14725e41b9490816db5d310e43a34b337e421ed14e99ea4ee9
|
| 3 |
+
size 14244
|
checkpoint-15500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:349974239b65a6609c3f817035f6bce53b35c635dcd8d37748ff738b2764bc5f
|
| 3 |
+
size 1064
|
checkpoint-15500/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 |
+
}
|
checkpoint-15500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-15500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-15500/trainer_state.json
ADDED
|
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9425993232234617,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06266449429753101,
|
| 13 |
+
"grad_norm": 6.711787223815918,
|
| 14 |
+
"learning_rate": 4.843338764256173e-05,
|
| 15 |
+
"loss": 0.1549,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06266449429753101,
|
| 20 |
+
"eval_accuracy": 0.9584508366234255,
|
| 21 |
+
"eval_f1": 0.7559808612440191,
|
| 22 |
+
"eval_loss": 0.12494000792503357,
|
| 23 |
+
"eval_precision": 0.869602032176122,
|
| 24 |
+
"eval_recall": 0.6686197916666666,
|
| 25 |
+
"eval_runtime": 204.5919,
|
| 26 |
+
"eval_samples_per_second": 77.994,
|
| 27 |
+
"eval_steps_per_second": 4.878,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.12532898859506203,
|
| 32 |
+
"grad_norm": 0.12083161622285843,
|
| 33 |
+
"learning_rate": 4.686677528512345e-05,
|
| 34 |
+
"loss": 0.1262,
|
| 35 |
+
"step": 1000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.12532898859506203,
|
| 39 |
+
"eval_accuracy": 0.9637149840195526,
|
| 40 |
+
"eval_f1": 0.7963418923672178,
|
| 41 |
+
"eval_loss": 0.11912646889686584,
|
| 42 |
+
"eval_precision": 0.8661055853098699,
|
| 43 |
+
"eval_recall": 0.7369791666666666,
|
| 44 |
+
"eval_runtime": 205.4957,
|
| 45 |
+
"eval_samples_per_second": 77.651,
|
| 46 |
+
"eval_steps_per_second": 4.857,
|
| 47 |
+
"step": 1000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.18799348289259304,
|
| 51 |
+
"grad_norm": 0.09569524973630905,
|
| 52 |
+
"learning_rate": 4.5300162927685175e-05,
|
| 53 |
+
"loss": 0.1183,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.18799348289259304,
|
| 58 |
+
"eval_accuracy": 0.9611455787428714,
|
| 59 |
+
"eval_f1": 0.782761037140855,
|
| 60 |
+
"eval_loss": 0.11601153016090393,
|
| 61 |
+
"eval_precision": 0.8474962063732928,
|
| 62 |
+
"eval_recall": 0.7272135416666666,
|
| 63 |
+
"eval_runtime": 206.7776,
|
| 64 |
+
"eval_samples_per_second": 77.17,
|
| 65 |
+
"eval_steps_per_second": 4.826,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25065797719012406,
|
| 70 |
+
"grad_norm": 1.9072543382644653,
|
| 71 |
+
"learning_rate": 4.37335505702469e-05,
|
| 72 |
+
"loss": 0.1255,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25065797719012406,
|
| 77 |
+
"eval_accuracy": 0.9617722629566962,
|
| 78 |
+
"eval_f1": 0.774741506646972,
|
| 79 |
+
"eval_loss": 0.10784206539392471,
|
| 80 |
+
"eval_precision": 0.8950511945392492,
|
| 81 |
+
"eval_recall": 0.6829427083333334,
|
| 82 |
+
"eval_runtime": 206.8947,
|
| 83 |
+
"eval_samples_per_second": 77.126,
|
| 84 |
+
"eval_steps_per_second": 4.824,
|
| 85 |
+
"step": 2000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.3133224714876551,
|
| 89 |
+
"grad_norm": 5.620913982391357,
|
| 90 |
+
"learning_rate": 4.216693821280863e-05,
|
| 91 |
+
"loss": 0.1191,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.3133224714876551,
|
| 96 |
+
"eval_accuracy": 0.9618349313780786,
|
| 97 |
+
"eval_f1": 0.7779803135253373,
|
| 98 |
+
"eval_loss": 0.13490551710128784,
|
| 99 |
+
"eval_precision": 0.884009942004971,
|
| 100 |
+
"eval_recall": 0.6946614583333334,
|
| 101 |
+
"eval_runtime": 205.7712,
|
| 102 |
+
"eval_samples_per_second": 77.547,
|
| 103 |
+
"eval_steps_per_second": 4.85,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.3759869657851861,
|
| 108 |
+
"grad_norm": 0.9537498950958252,
|
| 109 |
+
"learning_rate": 4.060032585537035e-05,
|
| 110 |
+
"loss": 0.1049,
|
| 111 |
+
"step": 3000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.3759869657851861,
|
| 115 |
+
"eval_accuracy": 0.9654696998182616,
|
| 116 |
+
"eval_f1": 0.8042628774422735,
|
| 117 |
+
"eval_loss": 0.11072225123643875,
|
| 118 |
+
"eval_precision": 0.8850664581704457,
|
| 119 |
+
"eval_recall": 0.7369791666666666,
|
| 120 |
+
"eval_runtime": 205.4633,
|
| 121 |
+
"eval_samples_per_second": 77.663,
|
| 122 |
+
"eval_steps_per_second": 4.857,
|
| 123 |
+
"step": 3000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.43865146008271716,
|
| 127 |
+
"grad_norm": 2.1389715671539307,
|
| 128 |
+
"learning_rate": 3.903371349793207e-05,
|
| 129 |
+
"loss": 0.1099,
|
| 130 |
+
"step": 3500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.43865146008271716,
|
| 134 |
+
"eval_accuracy": 0.9629002945415805,
|
| 135 |
+
"eval_f1": 0.811344805608668,
|
| 136 |
+
"eval_loss": 0.106051966547966,
|
| 137 |
+
"eval_precision": 0.7946317103620475,
|
| 138 |
+
"eval_recall": 0.8287760416666666,
|
| 139 |
+
"eval_runtime": 205.7322,
|
| 140 |
+
"eval_samples_per_second": 77.562,
|
| 141 |
+
"eval_steps_per_second": 4.851,
|
| 142 |
+
"step": 3500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5013159543802481,
|
| 146 |
+
"grad_norm": 1.8641178607940674,
|
| 147 |
+
"learning_rate": 3.74671011404938e-05,
|
| 148 |
+
"loss": 0.1103,
|
| 149 |
+
"step": 4000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5013159543802481,
|
| 153 |
+
"eval_accuracy": 0.9650936892899667,
|
| 154 |
+
"eval_f1": 0.8098327074086719,
|
| 155 |
+
"eval_loss": 0.10791335254907608,
|
| 156 |
+
"eval_precision": 0.8513998564249821,
|
| 157 |
+
"eval_recall": 0.7721354166666666,
|
| 158 |
+
"eval_runtime": 203.6878,
|
| 159 |
+
"eval_samples_per_second": 78.34,
|
| 160 |
+
"eval_steps_per_second": 4.9,
|
| 161 |
+
"step": 4000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.5639804486777792,
|
| 165 |
+
"grad_norm": 0.3474537134170532,
|
| 166 |
+
"learning_rate": 3.5900488783055526e-05,
|
| 167 |
+
"loss": 0.1143,
|
| 168 |
+
"step": 4500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.5639804486777792,
|
| 172 |
+
"eval_accuracy": 0.9654696998182616,
|
| 173 |
+
"eval_f1": 0.8197579326136736,
|
| 174 |
+
"eval_loss": 0.09943240135908127,
|
| 175 |
+
"eval_precision": 0.8238001314924391,
|
| 176 |
+
"eval_recall": 0.8157552083333334,
|
| 177 |
+
"eval_runtime": 203.9291,
|
| 178 |
+
"eval_samples_per_second": 78.248,
|
| 179 |
+
"eval_steps_per_second": 4.894,
|
| 180 |
+
"step": 4500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.6266449429753101,
|
| 184 |
+
"grad_norm": 0.30341413617134094,
|
| 185 |
+
"learning_rate": 3.4333876425617245e-05,
|
| 186 |
+
"loss": 0.1113,
|
| 187 |
+
"step": 5000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.6266449429753101,
|
| 191 |
+
"eval_accuracy": 0.9659710471893213,
|
| 192 |
+
"eval_f1": 0.8135942327497425,
|
| 193 |
+
"eval_loss": 0.0937616229057312,
|
| 194 |
+
"eval_precision": 0.8605664488017429,
|
| 195 |
+
"eval_recall": 0.771484375,
|
| 196 |
+
"eval_runtime": 204.8838,
|
| 197 |
+
"eval_samples_per_second": 77.883,
|
| 198 |
+
"eval_steps_per_second": 4.871,
|
| 199 |
+
"step": 5000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6893094372728412,
|
| 203 |
+
"grad_norm": 0.12893885374069214,
|
| 204 |
+
"learning_rate": 3.276726406817897e-05,
|
| 205 |
+
"loss": 0.0996,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6893094372728412,
|
| 210 |
+
"eval_accuracy": 0.9642163313906122,
|
| 211 |
+
"eval_f1": 0.8130932896890344,
|
| 212 |
+
"eval_loss": 0.09818771481513977,
|
| 213 |
+
"eval_precision": 0.8176431863067808,
|
| 214 |
+
"eval_recall": 0.80859375,
|
| 215 |
+
"eval_runtime": 205.4245,
|
| 216 |
+
"eval_samples_per_second": 77.678,
|
| 217 |
+
"eval_steps_per_second": 4.858,
|
| 218 |
+
"step": 5500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.7519739315703722,
|
| 222 |
+
"grad_norm": 0.8224383592605591,
|
| 223 |
+
"learning_rate": 3.12006517107407e-05,
|
| 224 |
+
"loss": 0.0922,
|
| 225 |
+
"step": 6000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.7519739315703722,
|
| 229 |
+
"eval_accuracy": 0.9662843892962336,
|
| 230 |
+
"eval_f1": 0.8153740562800275,
|
| 231 |
+
"eval_loss": 0.09692925959825516,
|
| 232 |
+
"eval_precision": 0.8621190130624092,
|
| 233 |
+
"eval_recall": 0.7734375,
|
| 234 |
+
"eval_runtime": 204.8207,
|
| 235 |
+
"eval_samples_per_second": 77.907,
|
| 236 |
+
"eval_steps_per_second": 4.873,
|
| 237 |
+
"step": 6000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.8146384258679032,
|
| 241 |
+
"grad_norm": 1.5743597745895386,
|
| 242 |
+
"learning_rate": 2.9634039353302424e-05,
|
| 243 |
+
"loss": 0.1027,
|
| 244 |
+
"step": 6500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8146384258679032,
|
| 248 |
+
"eval_accuracy": 0.9654070313968791,
|
| 249 |
+
"eval_f1": 0.8201954397394137,
|
| 250 |
+
"eval_loss": 0.10549037158489227,
|
| 251 |
+
"eval_precision": 0.8207301173402868,
|
| 252 |
+
"eval_recall": 0.8196614583333334,
|
| 253 |
+
"eval_runtime": 204.7577,
|
| 254 |
+
"eval_samples_per_second": 77.931,
|
| 255 |
+
"eval_steps_per_second": 4.874,
|
| 256 |
+
"step": 6500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.8773029201654343,
|
| 260 |
+
"grad_norm": 0.1999007612466812,
|
| 261 |
+
"learning_rate": 2.8067426995864144e-05,
|
| 262 |
+
"loss": 0.103,
|
| 263 |
+
"step": 7000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.8773029201654343,
|
| 267 |
+
"eval_accuracy": 0.9650310208685843,
|
| 268 |
+
"eval_f1": 0.7985559566787004,
|
| 269 |
+
"eval_loss": 0.10736460983753204,
|
| 270 |
+
"eval_precision": 0.8962722852512156,
|
| 271 |
+
"eval_recall": 0.7200520833333334,
|
| 272 |
+
"eval_runtime": 204.3013,
|
| 273 |
+
"eval_samples_per_second": 78.105,
|
| 274 |
+
"eval_steps_per_second": 4.885,
|
| 275 |
+
"step": 7000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9399674144629653,
|
| 279 |
+
"grad_norm": 0.1346016526222229,
|
| 280 |
+
"learning_rate": 2.650081463842587e-05,
|
| 281 |
+
"loss": 0.0961,
|
| 282 |
+
"step": 7500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9399674144629653,
|
| 286 |
+
"eval_accuracy": 0.9674750893025005,
|
| 287 |
+
"eval_f1": 0.8284297520661157,
|
| 288 |
+
"eval_loss": 0.10356267541646957,
|
| 289 |
+
"eval_precision": 0.8415043653458697,
|
| 290 |
+
"eval_recall": 0.8157552083333334,
|
| 291 |
+
"eval_runtime": 204.3737,
|
| 292 |
+
"eval_samples_per_second": 78.078,
|
| 293 |
+
"eval_steps_per_second": 4.883,
|
| 294 |
+
"step": 7500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.0026319087604962,
|
| 298 |
+
"grad_norm": 0.2624149024486542,
|
| 299 |
+
"learning_rate": 2.4934202280987593e-05,
|
| 300 |
+
"loss": 0.0954,
|
| 301 |
+
"step": 8000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.0026319087604962,
|
| 305 |
+
"eval_accuracy": 0.9674750893025005,
|
| 306 |
+
"eval_f1": 0.8248396895038812,
|
| 307 |
+
"eval_loss": 0.09561280906200409,
|
| 308 |
+
"eval_precision": 0.8563419761737912,
|
| 309 |
+
"eval_recall": 0.7955729166666666,
|
| 310 |
+
"eval_runtime": 202.7481,
|
| 311 |
+
"eval_samples_per_second": 78.704,
|
| 312 |
+
"eval_steps_per_second": 4.922,
|
| 313 |
+
"step": 8000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.0652964030580274,
|
| 317 |
+
"grad_norm": 3.5990114212036133,
|
| 318 |
+
"learning_rate": 2.336758992354932e-05,
|
| 319 |
+
"loss": 0.0747,
|
| 320 |
+
"step": 8500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.0652964030580274,
|
| 324 |
+
"eval_accuracy": 0.9665350629817635,
|
| 325 |
+
"eval_f1": 0.8225913621262458,
|
| 326 |
+
"eval_loss": 0.10118033736944199,
|
| 327 |
+
"eval_precision": 0.8398914518317503,
|
| 328 |
+
"eval_recall": 0.8059895833333334,
|
| 329 |
+
"eval_runtime": 203.5966,
|
| 330 |
+
"eval_samples_per_second": 78.376,
|
| 331 |
+
"eval_steps_per_second": 4.902,
|
| 332 |
+
"step": 8500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1279608973555584,
|
| 336 |
+
"grad_norm": 0.04438179358839989,
|
| 337 |
+
"learning_rate": 2.1800977566111042e-05,
|
| 338 |
+
"loss": 0.0652,
|
| 339 |
+
"step": 9000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.1279608973555584,
|
| 343 |
+
"eval_accuracy": 0.9686657893087673,
|
| 344 |
+
"eval_f1": 0.8306233062330624,
|
| 345 |
+
"eval_loss": 0.10936558991670609,
|
| 346 |
+
"eval_precision": 0.865819209039548,
|
| 347 |
+
"eval_recall": 0.7981770833333334,
|
| 348 |
+
"eval_runtime": 204.1425,
|
| 349 |
+
"eval_samples_per_second": 78.166,
|
| 350 |
+
"eval_steps_per_second": 4.889,
|
| 351 |
+
"step": 9000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.1906253916530893,
|
| 355 |
+
"grad_norm": 3.582298755645752,
|
| 356 |
+
"learning_rate": 2.023436520867277e-05,
|
| 357 |
+
"loss": 0.0751,
|
| 358 |
+
"step": 9500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.1906253916530893,
|
| 362 |
+
"eval_accuracy": 0.9680391050949426,
|
| 363 |
+
"eval_f1": 0.8282828282828283,
|
| 364 |
+
"eval_loss": 0.11079519987106323,
|
| 365 |
+
"eval_precision": 0.8577405857740585,
|
| 366 |
+
"eval_recall": 0.80078125,
|
| 367 |
+
"eval_runtime": 204.4377,
|
| 368 |
+
"eval_samples_per_second": 78.053,
|
| 369 |
+
"eval_steps_per_second": 4.882,
|
| 370 |
+
"step": 9500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.2532898859506203,
|
| 374 |
+
"grad_norm": 2.3587799072265625,
|
| 375 |
+
"learning_rate": 1.866775285123449e-05,
|
| 376 |
+
"loss": 0.0659,
|
| 377 |
+
"step": 10000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.2532898859506203,
|
| 381 |
+
"eval_accuracy": 0.9672870840383531,
|
| 382 |
+
"eval_f1": 0.8298565840938722,
|
| 383 |
+
"eval_loss": 0.12032488733530045,
|
| 384 |
+
"eval_precision": 0.8309399477806788,
|
| 385 |
+
"eval_recall": 0.8287760416666666,
|
| 386 |
+
"eval_runtime": 203.7565,
|
| 387 |
+
"eval_samples_per_second": 78.314,
|
| 388 |
+
"eval_steps_per_second": 4.898,
|
| 389 |
+
"step": 10000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.3159543802481515,
|
| 393 |
+
"grad_norm": 0.08431938290596008,
|
| 394 |
+
"learning_rate": 1.7101140493796218e-05,
|
| 395 |
+
"loss": 0.0703,
|
| 396 |
+
"step": 10500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3159543802481515,
|
| 400 |
+
"eval_accuracy": 0.967412420881118,
|
| 401 |
+
"eval_f1": 0.8208132322536182,
|
| 402 |
+
"eval_loss": 0.10189381241798401,
|
| 403 |
+
"eval_precision": 0.8718887262079063,
|
| 404 |
+
"eval_recall": 0.775390625,
|
| 405 |
+
"eval_runtime": 204.1519,
|
| 406 |
+
"eval_samples_per_second": 78.162,
|
| 407 |
+
"eval_steps_per_second": 4.889,
|
| 408 |
+
"step": 10500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.3786188745456824,
|
| 412 |
+
"grad_norm": 6.7462158203125,
|
| 413 |
+
"learning_rate": 1.553452813635794e-05,
|
| 414 |
+
"loss": 0.0684,
|
| 415 |
+
"step": 11000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.3786188745456824,
|
| 419 |
+
"eval_accuracy": 0.9677884314094128,
|
| 420 |
+
"eval_f1": 0.8313648293963255,
|
| 421 |
+
"eval_loss": 0.10193020105361938,
|
| 422 |
+
"eval_precision": 0.8379629629629629,
|
| 423 |
+
"eval_recall": 0.8248697916666666,
|
| 424 |
+
"eval_runtime": 203.1056,
|
| 425 |
+
"eval_samples_per_second": 78.565,
|
| 426 |
+
"eval_steps_per_second": 4.914,
|
| 427 |
+
"step": 11000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.4412833688432134,
|
| 431 |
+
"grad_norm": 2.7681772708892822,
|
| 432 |
+
"learning_rate": 1.3967915778919665e-05,
|
| 433 |
+
"loss": 0.0743,
|
| 434 |
+
"step": 11500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.4412833688432134,
|
| 438 |
+
"eval_accuracy": 0.96822711035909,
|
| 439 |
+
"eval_f1": 0.8265480670543962,
|
| 440 |
+
"eval_loss": 0.10714053362607956,
|
| 441 |
+
"eval_precision": 0.8709444844989185,
|
| 442 |
+
"eval_recall": 0.7864583333333334,
|
| 443 |
+
"eval_runtime": 202.6179,
|
| 444 |
+
"eval_samples_per_second": 78.754,
|
| 445 |
+
"eval_steps_per_second": 4.926,
|
| 446 |
+
"step": 11500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.5039478631407444,
|
| 450 |
+
"grad_norm": 0.034125763922929764,
|
| 451 |
+
"learning_rate": 1.2401303421481388e-05,
|
| 452 |
+
"loss": 0.0702,
|
| 453 |
+
"step": 12000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.5039478631407444,
|
| 457 |
+
"eval_accuracy": 0.9669110735100582,
|
| 458 |
+
"eval_f1": 0.8289047310434219,
|
| 459 |
+
"eval_loss": 0.1072157546877861,
|
| 460 |
+
"eval_precision": 0.8251612903225807,
|
| 461 |
+
"eval_recall": 0.8326822916666666,
|
| 462 |
+
"eval_runtime": 203.402,
|
| 463 |
+
"eval_samples_per_second": 78.451,
|
| 464 |
+
"eval_steps_per_second": 4.907,
|
| 465 |
+
"step": 12000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.5666123574382755,
|
| 469 |
+
"grad_norm": 4.053225994110107,
|
| 470 |
+
"learning_rate": 1.0834691064043113e-05,
|
| 471 |
+
"loss": 0.066,
|
| 472 |
+
"step": 12500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.5666123574382755,
|
| 476 |
+
"eval_accuracy": 0.9660963840320862,
|
| 477 |
+
"eval_f1": 0.8255401483392454,
|
| 478 |
+
"eval_loss": 0.11463014781475067,
|
| 479 |
+
"eval_precision": 0.8178913738019169,
|
| 480 |
+
"eval_recall": 0.8333333333333334,
|
| 481 |
+
"eval_runtime": 203.866,
|
| 482 |
+
"eval_samples_per_second": 78.272,
|
| 483 |
+
"eval_steps_per_second": 4.895,
|
| 484 |
+
"step": 12500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.6292768517358065,
|
| 488 |
+
"grad_norm": 0.39420416951179504,
|
| 489 |
+
"learning_rate": 9.268078706604837e-06,
|
| 490 |
+
"loss": 0.0671,
|
| 491 |
+
"step": 13000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.6292768517358065,
|
| 495 |
+
"eval_accuracy": 0.96822711035909,
|
| 496 |
+
"eval_f1": 0.8290050590219225,
|
| 497 |
+
"eval_loss": 0.10778097808361053,
|
| 498 |
+
"eval_precision": 0.8600419874037789,
|
| 499 |
+
"eval_recall": 0.8001302083333334,
|
| 500 |
+
"eval_runtime": 203.6153,
|
| 501 |
+
"eval_samples_per_second": 78.368,
|
| 502 |
+
"eval_steps_per_second": 4.901,
|
| 503 |
+
"step": 13000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.6919413460333375,
|
| 507 |
+
"grad_norm": 0.04355866089463234,
|
| 508 |
+
"learning_rate": 7.701466349166562e-06,
|
| 509 |
+
"loss": 0.0685,
|
| 510 |
+
"step": 13500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.6919413460333375,
|
| 514 |
+
"eval_accuracy": 0.9673497524597355,
|
| 515 |
+
"eval_f1": 0.8342348075087496,
|
| 516 |
+
"eval_loss": 0.11404383927583694,
|
| 517 |
+
"eval_precision": 0.8158058494088364,
|
| 518 |
+
"eval_recall": 0.853515625,
|
| 519 |
+
"eval_runtime": 204.3626,
|
| 520 |
+
"eval_samples_per_second": 78.082,
|
| 521 |
+
"eval_steps_per_second": 4.883,
|
| 522 |
+
"step": 13500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.7546058403308686,
|
| 526 |
+
"grad_norm": 0.5404762625694275,
|
| 527 |
+
"learning_rate": 6.134853991728287e-06,
|
| 528 |
+
"loss": 0.0764,
|
| 529 |
+
"step": 14000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.7546058403308686,
|
| 533 |
+
"eval_accuracy": 0.9686031208873849,
|
| 534 |
+
"eval_f1": 0.8342705921270261,
|
| 535 |
+
"eval_loss": 0.09265921264886856,
|
| 536 |
+
"eval_precision": 0.8480161398789509,
|
| 537 |
+
"eval_recall": 0.8209635416666666,
|
| 538 |
+
"eval_runtime": 204.1297,
|
| 539 |
+
"eval_samples_per_second": 78.171,
|
| 540 |
+
"eval_steps_per_second": 4.889,
|
| 541 |
+
"step": 14000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.8172703346283996,
|
| 545 |
+
"grad_norm": 0.007777383551001549,
|
| 546 |
+
"learning_rate": 4.568241634290012e-06,
|
| 547 |
+
"loss": 0.0595,
|
| 548 |
+
"step": 14500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.8172703346283996,
|
| 552 |
+
"eval_accuracy": 0.9686031208873849,
|
| 553 |
+
"eval_f1": 0.8305715251944539,
|
| 554 |
+
"eval_loss": 0.1116061583161354,
|
| 555 |
+
"eval_precision": 0.8641801548205489,
|
| 556 |
+
"eval_recall": 0.7994791666666666,
|
| 557 |
+
"eval_runtime": 202.5714,
|
| 558 |
+
"eval_samples_per_second": 78.772,
|
| 559 |
+
"eval_steps_per_second": 4.927,
|
| 560 |
+
"step": 14500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.8799348289259306,
|
| 564 |
+
"grad_norm": 0.01570739783346653,
|
| 565 |
+
"learning_rate": 3.0016292768517358e-06,
|
| 566 |
+
"loss": 0.061,
|
| 567 |
+
"step": 15000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.8799348289259306,
|
| 571 |
+
"eval_accuracy": 0.9694178103653569,
|
| 572 |
+
"eval_f1": 0.8346883468834688,
|
| 573 |
+
"eval_loss": 0.10894181579351425,
|
| 574 |
+
"eval_precision": 0.8700564971751412,
|
| 575 |
+
"eval_recall": 0.8020833333333334,
|
| 576 |
+
"eval_runtime": 203.1137,
|
| 577 |
+
"eval_samples_per_second": 78.562,
|
| 578 |
+
"eval_steps_per_second": 4.914,
|
| 579 |
+
"step": 15000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.9425993232234617,
|
| 583 |
+
"grad_norm": 0.0377582423388958,
|
| 584 |
+
"learning_rate": 1.4350169194134604e-06,
|
| 585 |
+
"loss": 0.0621,
|
| 586 |
+
"step": 15500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.9425993232234617,
|
| 590 |
+
"eval_accuracy": 0.9694804787867394,
|
| 591 |
+
"eval_f1": 0.8368509212730318,
|
| 592 |
+
"eval_loss": 0.10401601344347,
|
| 593 |
+
"eval_precision": 0.8619737750172533,
|
| 594 |
+
"eval_recall": 0.8131510416666666,
|
| 595 |
+
"eval_runtime": 203.9357,
|
| 596 |
+
"eval_samples_per_second": 78.245,
|
| 597 |
+
"eval_steps_per_second": 4.894,
|
| 598 |
+
"step": 15500
|
| 599 |
+
}
|
| 600 |
+
],
|
| 601 |
+
"logging_steps": 500,
|
| 602 |
+
"max_steps": 15958,
|
| 603 |
+
"num_input_tokens_seen": 0,
|
| 604 |
+
"num_train_epochs": 2,
|
| 605 |
+
"save_steps": 500,
|
| 606 |
+
"stateful_callbacks": {
|
| 607 |
+
"TrainerControl": {
|
| 608 |
+
"args": {
|
| 609 |
+
"should_epoch_stop": false,
|
| 610 |
+
"should_evaluate": false,
|
| 611 |
+
"should_log": false,
|
| 612 |
+
"should_save": true,
|
| 613 |
+
"should_training_stop": false
|
| 614 |
+
},
|
| 615 |
+
"attributes": {}
|
| 616 |
+
}
|
| 617 |
+
},
|
| 618 |
+
"total_flos": 3.285085512749875e+16,
|
| 619 |
+
"train_batch_size": 16,
|
| 620 |
+
"trial_name": null,
|
| 621 |
+
"trial_params": null
|
| 622 |
+
}
|
checkpoint-15500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8710c561bb6596428b74e25c6eca6c89dd4541d27877a50c7f28ef5cfcf454f5
|
| 3 |
+
size 5240
|
checkpoint-15500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-15958/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
checkpoint-15958/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d37c063285013596d93bc1fd21c0a4d28fff2498ce0010e1c36a6e049cff9f28
|
| 3 |
+
size 267832560
|
checkpoint-15958/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b238f0ecebb37eb8d26c0c4df8a9d536e0decdcf91e19a01ea208d526329f9ab
|
| 3 |
+
size 535727290
|
checkpoint-15958/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:960a0a86793cffe19ff4567114cd13fb60c863a01f91c353e563d0f41075aab8
|
| 3 |
+
size 14244
|
checkpoint-15958/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b8b055e499eadb3c8c4bf16b1f2756b1542c3f57188643aed74e7637f916d85
|
| 3 |
+
size 1064
|
checkpoint-15958/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 |
+
}
|
checkpoint-15958/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-15958/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-15958/trainer_state.json
ADDED
|
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15958,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06266449429753101,
|
| 13 |
+
"grad_norm": 6.711787223815918,
|
| 14 |
+
"learning_rate": 4.843338764256173e-05,
|
| 15 |
+
"loss": 0.1549,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06266449429753101,
|
| 20 |
+
"eval_accuracy": 0.9584508366234255,
|
| 21 |
+
"eval_f1": 0.7559808612440191,
|
| 22 |
+
"eval_loss": 0.12494000792503357,
|
| 23 |
+
"eval_precision": 0.869602032176122,
|
| 24 |
+
"eval_recall": 0.6686197916666666,
|
| 25 |
+
"eval_runtime": 204.5919,
|
| 26 |
+
"eval_samples_per_second": 77.994,
|
| 27 |
+
"eval_steps_per_second": 4.878,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.12532898859506203,
|
| 32 |
+
"grad_norm": 0.12083161622285843,
|
| 33 |
+
"learning_rate": 4.686677528512345e-05,
|
| 34 |
+
"loss": 0.1262,
|
| 35 |
+
"step": 1000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.12532898859506203,
|
| 39 |
+
"eval_accuracy": 0.9637149840195526,
|
| 40 |
+
"eval_f1": 0.7963418923672178,
|
| 41 |
+
"eval_loss": 0.11912646889686584,
|
| 42 |
+
"eval_precision": 0.8661055853098699,
|
| 43 |
+
"eval_recall": 0.7369791666666666,
|
| 44 |
+
"eval_runtime": 205.4957,
|
| 45 |
+
"eval_samples_per_second": 77.651,
|
| 46 |
+
"eval_steps_per_second": 4.857,
|
| 47 |
+
"step": 1000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.18799348289259304,
|
| 51 |
+
"grad_norm": 0.09569524973630905,
|
| 52 |
+
"learning_rate": 4.5300162927685175e-05,
|
| 53 |
+
"loss": 0.1183,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.18799348289259304,
|
| 58 |
+
"eval_accuracy": 0.9611455787428714,
|
| 59 |
+
"eval_f1": 0.782761037140855,
|
| 60 |
+
"eval_loss": 0.11601153016090393,
|
| 61 |
+
"eval_precision": 0.8474962063732928,
|
| 62 |
+
"eval_recall": 0.7272135416666666,
|
| 63 |
+
"eval_runtime": 206.7776,
|
| 64 |
+
"eval_samples_per_second": 77.17,
|
| 65 |
+
"eval_steps_per_second": 4.826,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25065797719012406,
|
| 70 |
+
"grad_norm": 1.9072543382644653,
|
| 71 |
+
"learning_rate": 4.37335505702469e-05,
|
| 72 |
+
"loss": 0.1255,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25065797719012406,
|
| 77 |
+
"eval_accuracy": 0.9617722629566962,
|
| 78 |
+
"eval_f1": 0.774741506646972,
|
| 79 |
+
"eval_loss": 0.10784206539392471,
|
| 80 |
+
"eval_precision": 0.8950511945392492,
|
| 81 |
+
"eval_recall": 0.6829427083333334,
|
| 82 |
+
"eval_runtime": 206.8947,
|
| 83 |
+
"eval_samples_per_second": 77.126,
|
| 84 |
+
"eval_steps_per_second": 4.824,
|
| 85 |
+
"step": 2000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.3133224714876551,
|
| 89 |
+
"grad_norm": 5.620913982391357,
|
| 90 |
+
"learning_rate": 4.216693821280863e-05,
|
| 91 |
+
"loss": 0.1191,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.3133224714876551,
|
| 96 |
+
"eval_accuracy": 0.9618349313780786,
|
| 97 |
+
"eval_f1": 0.7779803135253373,
|
| 98 |
+
"eval_loss": 0.13490551710128784,
|
| 99 |
+
"eval_precision": 0.884009942004971,
|
| 100 |
+
"eval_recall": 0.6946614583333334,
|
| 101 |
+
"eval_runtime": 205.7712,
|
| 102 |
+
"eval_samples_per_second": 77.547,
|
| 103 |
+
"eval_steps_per_second": 4.85,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.3759869657851861,
|
| 108 |
+
"grad_norm": 0.9537498950958252,
|
| 109 |
+
"learning_rate": 4.060032585537035e-05,
|
| 110 |
+
"loss": 0.1049,
|
| 111 |
+
"step": 3000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.3759869657851861,
|
| 115 |
+
"eval_accuracy": 0.9654696998182616,
|
| 116 |
+
"eval_f1": 0.8042628774422735,
|
| 117 |
+
"eval_loss": 0.11072225123643875,
|
| 118 |
+
"eval_precision": 0.8850664581704457,
|
| 119 |
+
"eval_recall": 0.7369791666666666,
|
| 120 |
+
"eval_runtime": 205.4633,
|
| 121 |
+
"eval_samples_per_second": 77.663,
|
| 122 |
+
"eval_steps_per_second": 4.857,
|
| 123 |
+
"step": 3000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.43865146008271716,
|
| 127 |
+
"grad_norm": 2.1389715671539307,
|
| 128 |
+
"learning_rate": 3.903371349793207e-05,
|
| 129 |
+
"loss": 0.1099,
|
| 130 |
+
"step": 3500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.43865146008271716,
|
| 134 |
+
"eval_accuracy": 0.9629002945415805,
|
| 135 |
+
"eval_f1": 0.811344805608668,
|
| 136 |
+
"eval_loss": 0.106051966547966,
|
| 137 |
+
"eval_precision": 0.7946317103620475,
|
| 138 |
+
"eval_recall": 0.8287760416666666,
|
| 139 |
+
"eval_runtime": 205.7322,
|
| 140 |
+
"eval_samples_per_second": 77.562,
|
| 141 |
+
"eval_steps_per_second": 4.851,
|
| 142 |
+
"step": 3500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5013159543802481,
|
| 146 |
+
"grad_norm": 1.8641178607940674,
|
| 147 |
+
"learning_rate": 3.74671011404938e-05,
|
| 148 |
+
"loss": 0.1103,
|
| 149 |
+
"step": 4000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5013159543802481,
|
| 153 |
+
"eval_accuracy": 0.9650936892899667,
|
| 154 |
+
"eval_f1": 0.8098327074086719,
|
| 155 |
+
"eval_loss": 0.10791335254907608,
|
| 156 |
+
"eval_precision": 0.8513998564249821,
|
| 157 |
+
"eval_recall": 0.7721354166666666,
|
| 158 |
+
"eval_runtime": 203.6878,
|
| 159 |
+
"eval_samples_per_second": 78.34,
|
| 160 |
+
"eval_steps_per_second": 4.9,
|
| 161 |
+
"step": 4000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.5639804486777792,
|
| 165 |
+
"grad_norm": 0.3474537134170532,
|
| 166 |
+
"learning_rate": 3.5900488783055526e-05,
|
| 167 |
+
"loss": 0.1143,
|
| 168 |
+
"step": 4500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.5639804486777792,
|
| 172 |
+
"eval_accuracy": 0.9654696998182616,
|
| 173 |
+
"eval_f1": 0.8197579326136736,
|
| 174 |
+
"eval_loss": 0.09943240135908127,
|
| 175 |
+
"eval_precision": 0.8238001314924391,
|
| 176 |
+
"eval_recall": 0.8157552083333334,
|
| 177 |
+
"eval_runtime": 203.9291,
|
| 178 |
+
"eval_samples_per_second": 78.248,
|
| 179 |
+
"eval_steps_per_second": 4.894,
|
| 180 |
+
"step": 4500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.6266449429753101,
|
| 184 |
+
"grad_norm": 0.30341413617134094,
|
| 185 |
+
"learning_rate": 3.4333876425617245e-05,
|
| 186 |
+
"loss": 0.1113,
|
| 187 |
+
"step": 5000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.6266449429753101,
|
| 191 |
+
"eval_accuracy": 0.9659710471893213,
|
| 192 |
+
"eval_f1": 0.8135942327497425,
|
| 193 |
+
"eval_loss": 0.0937616229057312,
|
| 194 |
+
"eval_precision": 0.8605664488017429,
|
| 195 |
+
"eval_recall": 0.771484375,
|
| 196 |
+
"eval_runtime": 204.8838,
|
| 197 |
+
"eval_samples_per_second": 77.883,
|
| 198 |
+
"eval_steps_per_second": 4.871,
|
| 199 |
+
"step": 5000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6893094372728412,
|
| 203 |
+
"grad_norm": 0.12893885374069214,
|
| 204 |
+
"learning_rate": 3.276726406817897e-05,
|
| 205 |
+
"loss": 0.0996,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6893094372728412,
|
| 210 |
+
"eval_accuracy": 0.9642163313906122,
|
| 211 |
+
"eval_f1": 0.8130932896890344,
|
| 212 |
+
"eval_loss": 0.09818771481513977,
|
| 213 |
+
"eval_precision": 0.8176431863067808,
|
| 214 |
+
"eval_recall": 0.80859375,
|
| 215 |
+
"eval_runtime": 205.4245,
|
| 216 |
+
"eval_samples_per_second": 77.678,
|
| 217 |
+
"eval_steps_per_second": 4.858,
|
| 218 |
+
"step": 5500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.7519739315703722,
|
| 222 |
+
"grad_norm": 0.8224383592605591,
|
| 223 |
+
"learning_rate": 3.12006517107407e-05,
|
| 224 |
+
"loss": 0.0922,
|
| 225 |
+
"step": 6000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.7519739315703722,
|
| 229 |
+
"eval_accuracy": 0.9662843892962336,
|
| 230 |
+
"eval_f1": 0.8153740562800275,
|
| 231 |
+
"eval_loss": 0.09692925959825516,
|
| 232 |
+
"eval_precision": 0.8621190130624092,
|
| 233 |
+
"eval_recall": 0.7734375,
|
| 234 |
+
"eval_runtime": 204.8207,
|
| 235 |
+
"eval_samples_per_second": 77.907,
|
| 236 |
+
"eval_steps_per_second": 4.873,
|
| 237 |
+
"step": 6000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.8146384258679032,
|
| 241 |
+
"grad_norm": 1.5743597745895386,
|
| 242 |
+
"learning_rate": 2.9634039353302424e-05,
|
| 243 |
+
"loss": 0.1027,
|
| 244 |
+
"step": 6500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.8146384258679032,
|
| 248 |
+
"eval_accuracy": 0.9654070313968791,
|
| 249 |
+
"eval_f1": 0.8201954397394137,
|
| 250 |
+
"eval_loss": 0.10549037158489227,
|
| 251 |
+
"eval_precision": 0.8207301173402868,
|
| 252 |
+
"eval_recall": 0.8196614583333334,
|
| 253 |
+
"eval_runtime": 204.7577,
|
| 254 |
+
"eval_samples_per_second": 77.931,
|
| 255 |
+
"eval_steps_per_second": 4.874,
|
| 256 |
+
"step": 6500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.8773029201654343,
|
| 260 |
+
"grad_norm": 0.1999007612466812,
|
| 261 |
+
"learning_rate": 2.8067426995864144e-05,
|
| 262 |
+
"loss": 0.103,
|
| 263 |
+
"step": 7000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.8773029201654343,
|
| 267 |
+
"eval_accuracy": 0.9650310208685843,
|
| 268 |
+
"eval_f1": 0.7985559566787004,
|
| 269 |
+
"eval_loss": 0.10736460983753204,
|
| 270 |
+
"eval_precision": 0.8962722852512156,
|
| 271 |
+
"eval_recall": 0.7200520833333334,
|
| 272 |
+
"eval_runtime": 204.3013,
|
| 273 |
+
"eval_samples_per_second": 78.105,
|
| 274 |
+
"eval_steps_per_second": 4.885,
|
| 275 |
+
"step": 7000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9399674144629653,
|
| 279 |
+
"grad_norm": 0.1346016526222229,
|
| 280 |
+
"learning_rate": 2.650081463842587e-05,
|
| 281 |
+
"loss": 0.0961,
|
| 282 |
+
"step": 7500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9399674144629653,
|
| 286 |
+
"eval_accuracy": 0.9674750893025005,
|
| 287 |
+
"eval_f1": 0.8284297520661157,
|
| 288 |
+
"eval_loss": 0.10356267541646957,
|
| 289 |
+
"eval_precision": 0.8415043653458697,
|
| 290 |
+
"eval_recall": 0.8157552083333334,
|
| 291 |
+
"eval_runtime": 204.3737,
|
| 292 |
+
"eval_samples_per_second": 78.078,
|
| 293 |
+
"eval_steps_per_second": 4.883,
|
| 294 |
+
"step": 7500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.0026319087604962,
|
| 298 |
+
"grad_norm": 0.2624149024486542,
|
| 299 |
+
"learning_rate": 2.4934202280987593e-05,
|
| 300 |
+
"loss": 0.0954,
|
| 301 |
+
"step": 8000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.0026319087604962,
|
| 305 |
+
"eval_accuracy": 0.9674750893025005,
|
| 306 |
+
"eval_f1": 0.8248396895038812,
|
| 307 |
+
"eval_loss": 0.09561280906200409,
|
| 308 |
+
"eval_precision": 0.8563419761737912,
|
| 309 |
+
"eval_recall": 0.7955729166666666,
|
| 310 |
+
"eval_runtime": 202.7481,
|
| 311 |
+
"eval_samples_per_second": 78.704,
|
| 312 |
+
"eval_steps_per_second": 4.922,
|
| 313 |
+
"step": 8000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.0652964030580274,
|
| 317 |
+
"grad_norm": 3.5990114212036133,
|
| 318 |
+
"learning_rate": 2.336758992354932e-05,
|
| 319 |
+
"loss": 0.0747,
|
| 320 |
+
"step": 8500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.0652964030580274,
|
| 324 |
+
"eval_accuracy": 0.9665350629817635,
|
| 325 |
+
"eval_f1": 0.8225913621262458,
|
| 326 |
+
"eval_loss": 0.10118033736944199,
|
| 327 |
+
"eval_precision": 0.8398914518317503,
|
| 328 |
+
"eval_recall": 0.8059895833333334,
|
| 329 |
+
"eval_runtime": 203.5966,
|
| 330 |
+
"eval_samples_per_second": 78.376,
|
| 331 |
+
"eval_steps_per_second": 4.902,
|
| 332 |
+
"step": 8500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1279608973555584,
|
| 336 |
+
"grad_norm": 0.04438179358839989,
|
| 337 |
+
"learning_rate": 2.1800977566111042e-05,
|
| 338 |
+
"loss": 0.0652,
|
| 339 |
+
"step": 9000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.1279608973555584,
|
| 343 |
+
"eval_accuracy": 0.9686657893087673,
|
| 344 |
+
"eval_f1": 0.8306233062330624,
|
| 345 |
+
"eval_loss": 0.10936558991670609,
|
| 346 |
+
"eval_precision": 0.865819209039548,
|
| 347 |
+
"eval_recall": 0.7981770833333334,
|
| 348 |
+
"eval_runtime": 204.1425,
|
| 349 |
+
"eval_samples_per_second": 78.166,
|
| 350 |
+
"eval_steps_per_second": 4.889,
|
| 351 |
+
"step": 9000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.1906253916530893,
|
| 355 |
+
"grad_norm": 3.582298755645752,
|
| 356 |
+
"learning_rate": 2.023436520867277e-05,
|
| 357 |
+
"loss": 0.0751,
|
| 358 |
+
"step": 9500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.1906253916530893,
|
| 362 |
+
"eval_accuracy": 0.9680391050949426,
|
| 363 |
+
"eval_f1": 0.8282828282828283,
|
| 364 |
+
"eval_loss": 0.11079519987106323,
|
| 365 |
+
"eval_precision": 0.8577405857740585,
|
| 366 |
+
"eval_recall": 0.80078125,
|
| 367 |
+
"eval_runtime": 204.4377,
|
| 368 |
+
"eval_samples_per_second": 78.053,
|
| 369 |
+
"eval_steps_per_second": 4.882,
|
| 370 |
+
"step": 9500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.2532898859506203,
|
| 374 |
+
"grad_norm": 2.3587799072265625,
|
| 375 |
+
"learning_rate": 1.866775285123449e-05,
|
| 376 |
+
"loss": 0.0659,
|
| 377 |
+
"step": 10000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.2532898859506203,
|
| 381 |
+
"eval_accuracy": 0.9672870840383531,
|
| 382 |
+
"eval_f1": 0.8298565840938722,
|
| 383 |
+
"eval_loss": 0.12032488733530045,
|
| 384 |
+
"eval_precision": 0.8309399477806788,
|
| 385 |
+
"eval_recall": 0.8287760416666666,
|
| 386 |
+
"eval_runtime": 203.7565,
|
| 387 |
+
"eval_samples_per_second": 78.314,
|
| 388 |
+
"eval_steps_per_second": 4.898,
|
| 389 |
+
"step": 10000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.3159543802481515,
|
| 393 |
+
"grad_norm": 0.08431938290596008,
|
| 394 |
+
"learning_rate": 1.7101140493796218e-05,
|
| 395 |
+
"loss": 0.0703,
|
| 396 |
+
"step": 10500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3159543802481515,
|
| 400 |
+
"eval_accuracy": 0.967412420881118,
|
| 401 |
+
"eval_f1": 0.8208132322536182,
|
| 402 |
+
"eval_loss": 0.10189381241798401,
|
| 403 |
+
"eval_precision": 0.8718887262079063,
|
| 404 |
+
"eval_recall": 0.775390625,
|
| 405 |
+
"eval_runtime": 204.1519,
|
| 406 |
+
"eval_samples_per_second": 78.162,
|
| 407 |
+
"eval_steps_per_second": 4.889,
|
| 408 |
+
"step": 10500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.3786188745456824,
|
| 412 |
+
"grad_norm": 6.7462158203125,
|
| 413 |
+
"learning_rate": 1.553452813635794e-05,
|
| 414 |
+
"loss": 0.0684,
|
| 415 |
+
"step": 11000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.3786188745456824,
|
| 419 |
+
"eval_accuracy": 0.9677884314094128,
|
| 420 |
+
"eval_f1": 0.8313648293963255,
|
| 421 |
+
"eval_loss": 0.10193020105361938,
|
| 422 |
+
"eval_precision": 0.8379629629629629,
|
| 423 |
+
"eval_recall": 0.8248697916666666,
|
| 424 |
+
"eval_runtime": 203.1056,
|
| 425 |
+
"eval_samples_per_second": 78.565,
|
| 426 |
+
"eval_steps_per_second": 4.914,
|
| 427 |
+
"step": 11000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.4412833688432134,
|
| 431 |
+
"grad_norm": 2.7681772708892822,
|
| 432 |
+
"learning_rate": 1.3967915778919665e-05,
|
| 433 |
+
"loss": 0.0743,
|
| 434 |
+
"step": 11500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.4412833688432134,
|
| 438 |
+
"eval_accuracy": 0.96822711035909,
|
| 439 |
+
"eval_f1": 0.8265480670543962,
|
| 440 |
+
"eval_loss": 0.10714053362607956,
|
| 441 |
+
"eval_precision": 0.8709444844989185,
|
| 442 |
+
"eval_recall": 0.7864583333333334,
|
| 443 |
+
"eval_runtime": 202.6179,
|
| 444 |
+
"eval_samples_per_second": 78.754,
|
| 445 |
+
"eval_steps_per_second": 4.926,
|
| 446 |
+
"step": 11500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.5039478631407444,
|
| 450 |
+
"grad_norm": 0.034125763922929764,
|
| 451 |
+
"learning_rate": 1.2401303421481388e-05,
|
| 452 |
+
"loss": 0.0702,
|
| 453 |
+
"step": 12000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.5039478631407444,
|
| 457 |
+
"eval_accuracy": 0.9669110735100582,
|
| 458 |
+
"eval_f1": 0.8289047310434219,
|
| 459 |
+
"eval_loss": 0.1072157546877861,
|
| 460 |
+
"eval_precision": 0.8251612903225807,
|
| 461 |
+
"eval_recall": 0.8326822916666666,
|
| 462 |
+
"eval_runtime": 203.402,
|
| 463 |
+
"eval_samples_per_second": 78.451,
|
| 464 |
+
"eval_steps_per_second": 4.907,
|
| 465 |
+
"step": 12000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.5666123574382755,
|
| 469 |
+
"grad_norm": 4.053225994110107,
|
| 470 |
+
"learning_rate": 1.0834691064043113e-05,
|
| 471 |
+
"loss": 0.066,
|
| 472 |
+
"step": 12500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.5666123574382755,
|
| 476 |
+
"eval_accuracy": 0.9660963840320862,
|
| 477 |
+
"eval_f1": 0.8255401483392454,
|
| 478 |
+
"eval_loss": 0.11463014781475067,
|
| 479 |
+
"eval_precision": 0.8178913738019169,
|
| 480 |
+
"eval_recall": 0.8333333333333334,
|
| 481 |
+
"eval_runtime": 203.866,
|
| 482 |
+
"eval_samples_per_second": 78.272,
|
| 483 |
+
"eval_steps_per_second": 4.895,
|
| 484 |
+
"step": 12500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.6292768517358065,
|
| 488 |
+
"grad_norm": 0.39420416951179504,
|
| 489 |
+
"learning_rate": 9.268078706604837e-06,
|
| 490 |
+
"loss": 0.0671,
|
| 491 |
+
"step": 13000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.6292768517358065,
|
| 495 |
+
"eval_accuracy": 0.96822711035909,
|
| 496 |
+
"eval_f1": 0.8290050590219225,
|
| 497 |
+
"eval_loss": 0.10778097808361053,
|
| 498 |
+
"eval_precision": 0.8600419874037789,
|
| 499 |
+
"eval_recall": 0.8001302083333334,
|
| 500 |
+
"eval_runtime": 203.6153,
|
| 501 |
+
"eval_samples_per_second": 78.368,
|
| 502 |
+
"eval_steps_per_second": 4.901,
|
| 503 |
+
"step": 13000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.6919413460333375,
|
| 507 |
+
"grad_norm": 0.04355866089463234,
|
| 508 |
+
"learning_rate": 7.701466349166562e-06,
|
| 509 |
+
"loss": 0.0685,
|
| 510 |
+
"step": 13500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.6919413460333375,
|
| 514 |
+
"eval_accuracy": 0.9673497524597355,
|
| 515 |
+
"eval_f1": 0.8342348075087496,
|
| 516 |
+
"eval_loss": 0.11404383927583694,
|
| 517 |
+
"eval_precision": 0.8158058494088364,
|
| 518 |
+
"eval_recall": 0.853515625,
|
| 519 |
+
"eval_runtime": 204.3626,
|
| 520 |
+
"eval_samples_per_second": 78.082,
|
| 521 |
+
"eval_steps_per_second": 4.883,
|
| 522 |
+
"step": 13500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.7546058403308686,
|
| 526 |
+
"grad_norm": 0.5404762625694275,
|
| 527 |
+
"learning_rate": 6.134853991728287e-06,
|
| 528 |
+
"loss": 0.0764,
|
| 529 |
+
"step": 14000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.7546058403308686,
|
| 533 |
+
"eval_accuracy": 0.9686031208873849,
|
| 534 |
+
"eval_f1": 0.8342705921270261,
|
| 535 |
+
"eval_loss": 0.09265921264886856,
|
| 536 |
+
"eval_precision": 0.8480161398789509,
|
| 537 |
+
"eval_recall": 0.8209635416666666,
|
| 538 |
+
"eval_runtime": 204.1297,
|
| 539 |
+
"eval_samples_per_second": 78.171,
|
| 540 |
+
"eval_steps_per_second": 4.889,
|
| 541 |
+
"step": 14000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.8172703346283996,
|
| 545 |
+
"grad_norm": 0.007777383551001549,
|
| 546 |
+
"learning_rate": 4.568241634290012e-06,
|
| 547 |
+
"loss": 0.0595,
|
| 548 |
+
"step": 14500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.8172703346283996,
|
| 552 |
+
"eval_accuracy": 0.9686031208873849,
|
| 553 |
+
"eval_f1": 0.8305715251944539,
|
| 554 |
+
"eval_loss": 0.1116061583161354,
|
| 555 |
+
"eval_precision": 0.8641801548205489,
|
| 556 |
+
"eval_recall": 0.7994791666666666,
|
| 557 |
+
"eval_runtime": 202.5714,
|
| 558 |
+
"eval_samples_per_second": 78.772,
|
| 559 |
+
"eval_steps_per_second": 4.927,
|
| 560 |
+
"step": 14500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.8799348289259306,
|
| 564 |
+
"grad_norm": 0.01570739783346653,
|
| 565 |
+
"learning_rate": 3.0016292768517358e-06,
|
| 566 |
+
"loss": 0.061,
|
| 567 |
+
"step": 15000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.8799348289259306,
|
| 571 |
+
"eval_accuracy": 0.9694178103653569,
|
| 572 |
+
"eval_f1": 0.8346883468834688,
|
| 573 |
+
"eval_loss": 0.10894181579351425,
|
| 574 |
+
"eval_precision": 0.8700564971751412,
|
| 575 |
+
"eval_recall": 0.8020833333333334,
|
| 576 |
+
"eval_runtime": 203.1137,
|
| 577 |
+
"eval_samples_per_second": 78.562,
|
| 578 |
+
"eval_steps_per_second": 4.914,
|
| 579 |
+
"step": 15000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.9425993232234617,
|
| 583 |
+
"grad_norm": 0.0377582423388958,
|
| 584 |
+
"learning_rate": 1.4350169194134604e-06,
|
| 585 |
+
"loss": 0.0621,
|
| 586 |
+
"step": 15500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.9425993232234617,
|
| 590 |
+
"eval_accuracy": 0.9694804787867394,
|
| 591 |
+
"eval_f1": 0.8368509212730318,
|
| 592 |
+
"eval_loss": 0.10401601344347,
|
| 593 |
+
"eval_precision": 0.8619737750172533,
|
| 594 |
+
"eval_recall": 0.8131510416666666,
|
| 595 |
+
"eval_runtime": 203.9357,
|
| 596 |
+
"eval_samples_per_second": 78.245,
|
| 597 |
+
"eval_steps_per_second": 4.894,
|
| 598 |
+
"step": 15500
|
| 599 |
+
}
|
| 600 |
+
],
|
| 601 |
+
"logging_steps": 500,
|
| 602 |
+
"max_steps": 15958,
|
| 603 |
+
"num_input_tokens_seen": 0,
|
| 604 |
+
"num_train_epochs": 2,
|
| 605 |
+
"save_steps": 500,
|
| 606 |
+
"stateful_callbacks": {
|
| 607 |
+
"TrainerControl": {
|
| 608 |
+
"args": {
|
| 609 |
+
"should_epoch_stop": false,
|
| 610 |
+
"should_evaluate": false,
|
| 611 |
+
"should_log": false,
|
| 612 |
+
"should_save": true,
|
| 613 |
+
"should_training_stop": true
|
| 614 |
+
},
|
| 615 |
+
"attributes": {}
|
| 616 |
+
}
|
| 617 |
+
},
|
| 618 |
+
"total_flos": 3.382051648566067e+16,
|
| 619 |
+
"train_batch_size": 16,
|
| 620 |
+
"trial_name": null,
|
| 621 |
+
"trial_params": null
|
| 622 |
+
}
|
checkpoint-15958/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8710c561bb6596428b74e25c6eca6c89dd4541d27877a50c7f28ef5cfcf454f5
|
| 3 |
+
size 5240
|
checkpoint-15958/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
logs/events.out.tfevents.1757646327.algo-1.92.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8b89cc288429993d420c2b8a42dc6d1abd8af5b72c263b14b9f5a2e29953abe
|
| 3 |
+
size 26485
|
logs/events.out.tfevents.1757663250.algo-1.92.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c15983de8fac52089bfcc812ba9f71a177003c06f65b7420bf4aac2de04b49
|
| 3 |
+
size 560
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d37c063285013596d93bc1fd21c0a4d28fff2498ce0010e1c36a6e049cff9f28
|
| 3 |
+
size 267832560
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8710c561bb6596428b74e25c6eca6c89dd4541d27877a50c7f28ef5cfcf454f5
|
| 3 |
+
size 5240
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|