Upload folder using huggingface_hub
Browse files- checkpoint-31250/config.json +38 -0
- checkpoint-31250/model.safetensors +3 -0
- checkpoint-31250/optimizer.pt +3 -0
- checkpoint-31250/rng_state.pth +3 -0
- checkpoint-31250/scheduler.pt +3 -0
- checkpoint-31250/special_tokens_map.json +7 -0
- checkpoint-31250/tokenizer.json +0 -0
- checkpoint-31250/tokenizer_config.json +56 -0
- checkpoint-31250/trainer_state.json +468 -0
- checkpoint-31250/training_args.bin +3 -0
- checkpoint-31250/vocab.txt +0 -0
- checkpoint-62500/config.json +38 -0
- checkpoint-62500/model.safetensors +3 -0
- checkpoint-62500/optimizer.pt +3 -0
- checkpoint-62500/rng_state.pth +3 -0
- checkpoint-62500/scheduler.pt +3 -0
- checkpoint-62500/special_tokens_map.json +7 -0
- checkpoint-62500/tokenizer.json +0 -0
- checkpoint-62500/tokenizer_config.json +56 -0
- checkpoint-62500/trainer_state.json +909 -0
- checkpoint-62500/training_args.bin +3 -0
- checkpoint-62500/vocab.txt +0 -0
- checkpoint-93750/config.json +38 -0
- checkpoint-93750/model.safetensors +3 -0
- checkpoint-93750/optimizer.pt +3 -0
- checkpoint-93750/rng_state.pth +3 -0
- checkpoint-93750/scheduler.pt +3 -0
- checkpoint-93750/special_tokens_map.json +7 -0
- checkpoint-93750/tokenizer.json +0 -0
- checkpoint-93750/tokenizer_config.json +56 -0
- checkpoint-93750/trainer_state.json +1343 -0
- checkpoint-93750/training_args.bin +3 -0
- checkpoint-93750/vocab.txt +0 -0
- config.json +38 -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-31250/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3,
|
| 23 |
+
"LABEL_4": 4
|
| 24 |
+
},
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "distilbert",
|
| 27 |
+
"n_heads": 12,
|
| 28 |
+
"n_layers": 6,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qa_dropout": 0.1,
|
| 32 |
+
"seq_classif_dropout": 0.2,
|
| 33 |
+
"sinusoidal_pos_embds": false,
|
| 34 |
+
"tie_weights_": true,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.52.3",
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
checkpoint-31250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85f1ecd0962972de1eeef92221b1b3fad2f58f27b2eabb07459f6dc5101afbff
|
| 3 |
+
size 267841796
|
checkpoint-31250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c4c9c787a0eade7bddfc1c969fffdc98c458dfb75ace151b55b3c3c1d06c2f4
|
| 3 |
+
size 535745722
|
checkpoint-31250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a7e27b867ace957e343ad3872f3a508726475142c53e97c70c9207bf83dce3a
|
| 3 |
+
size 14244
|
checkpoint-31250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12bfed116010fdad90b26ee6c109f3af73b2365a74d88a7161c30072b2669cca
|
| 3 |
+
size 1064
|
checkpoint-31250/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-31250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-31250/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-31250/trainer_state.json
ADDED
|
@@ -0,0 +1,468 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 31250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 5.113226413726807,
|
| 15 |
+
"learning_rate": 1.9893546666666667e-05,
|
| 16 |
+
"loss": 0.3997,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 1.5101436376571655,
|
| 22 |
+
"learning_rate": 1.978688e-05,
|
| 23 |
+
"loss": 0.3954,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 5.25643253326416,
|
| 29 |
+
"learning_rate": 1.9680213333333337e-05,
|
| 30 |
+
"loss": 0.4262,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 4.487380504608154,
|
| 36 |
+
"learning_rate": 1.9573546666666667e-05,
|
| 37 |
+
"loss": 0.4131,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 4.195590019226074,
|
| 43 |
+
"learning_rate": 1.946688e-05,
|
| 44 |
+
"loss": 0.4118,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 3.453535318374634,
|
| 50 |
+
"learning_rate": 1.9360213333333337e-05,
|
| 51 |
+
"loss": 0.4152,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 6.260850429534912,
|
| 57 |
+
"learning_rate": 1.925354666666667e-05,
|
| 58 |
+
"loss": 0.4254,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 3.717860221862793,
|
| 64 |
+
"learning_rate": 1.914688e-05,
|
| 65 |
+
"loss": 0.4134,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 2.7987215518951416,
|
| 71 |
+
"learning_rate": 1.9040213333333336e-05,
|
| 72 |
+
"loss": 0.4318,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 3.57886004447937,
|
| 78 |
+
"learning_rate": 1.893354666666667e-05,
|
| 79 |
+
"loss": 0.4178,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 3.7842671871185303,
|
| 85 |
+
"learning_rate": 1.882688e-05,
|
| 86 |
+
"loss": 0.4143,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 3.6401913166046143,
|
| 92 |
+
"learning_rate": 1.8720213333333336e-05,
|
| 93 |
+
"loss": 0.4283,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 2.6250557899475098,
|
| 99 |
+
"learning_rate": 1.861354666666667e-05,
|
| 100 |
+
"loss": 0.4066,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 4.987699031829834,
|
| 106 |
+
"learning_rate": 1.8506880000000003e-05,
|
| 107 |
+
"loss": 0.4074,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 3.055042266845703,
|
| 113 |
+
"learning_rate": 1.8400213333333336e-05,
|
| 114 |
+
"loss": 0.4102,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 2.8551082611083984,
|
| 120 |
+
"learning_rate": 1.829354666666667e-05,
|
| 121 |
+
"loss": 0.4154,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 4.127549171447754,
|
| 127 |
+
"learning_rate": 1.8186880000000002e-05,
|
| 128 |
+
"loss": 0.4267,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 4.929229736328125,
|
| 134 |
+
"learning_rate": 1.8080213333333336e-05,
|
| 135 |
+
"loss": 0.4123,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 3.787837505340576,
|
| 141 |
+
"learning_rate": 1.797354666666667e-05,
|
| 142 |
+
"loss": 0.4217,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 1.911741018295288,
|
| 148 |
+
"learning_rate": 1.7866880000000002e-05,
|
| 149 |
+
"loss": 0.4122,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 5.90802526473999,
|
| 155 |
+
"learning_rate": 1.7760213333333335e-05,
|
| 156 |
+
"loss": 0.4204,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 3.8967525959014893,
|
| 162 |
+
"learning_rate": 1.765354666666667e-05,
|
| 163 |
+
"loss": 0.4188,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 3.3974881172180176,
|
| 169 |
+
"learning_rate": 1.754688e-05,
|
| 170 |
+
"loss": 0.4131,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 3.672062397003174,
|
| 176 |
+
"learning_rate": 1.7440213333333335e-05,
|
| 177 |
+
"loss": 0.4129,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 4.360637664794922,
|
| 183 |
+
"learning_rate": 1.7333546666666668e-05,
|
| 184 |
+
"loss": 0.4288,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 4.036060810089111,
|
| 190 |
+
"learning_rate": 1.722688e-05,
|
| 191 |
+
"loss": 0.409,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 5.959667682647705,
|
| 197 |
+
"learning_rate": 1.7120213333333335e-05,
|
| 198 |
+
"loss": 0.4177,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 4.0133161544799805,
|
| 204 |
+
"learning_rate": 1.7013546666666668e-05,
|
| 205 |
+
"loss": 0.4261,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 4.409907341003418,
|
| 211 |
+
"learning_rate": 1.690688e-05,
|
| 212 |
+
"loss": 0.4261,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 6.2073163986206055,
|
| 218 |
+
"learning_rate": 1.6800213333333334e-05,
|
| 219 |
+
"loss": 0.4209,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 6.267955780029297,
|
| 225 |
+
"learning_rate": 1.6693546666666667e-05,
|
| 226 |
+
"loss": 0.408,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 4.548535346984863,
|
| 232 |
+
"learning_rate": 1.658688e-05,
|
| 233 |
+
"loss": 0.4178,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 3.5204384326934814,
|
| 239 |
+
"learning_rate": 1.6480213333333334e-05,
|
| 240 |
+
"loss": 0.416,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 4.745266914367676,
|
| 246 |
+
"learning_rate": 1.6373546666666667e-05,
|
| 247 |
+
"loss": 0.4102,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 5.38124418258667,
|
| 253 |
+
"learning_rate": 1.626688e-05,
|
| 254 |
+
"loss": 0.4169,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 3.408917188644409,
|
| 260 |
+
"learning_rate": 1.6160213333333334e-05,
|
| 261 |
+
"loss": 0.414,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 3.1644530296325684,
|
| 267 |
+
"learning_rate": 1.6053546666666667e-05,
|
| 268 |
+
"loss": 0.4037,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 3.7309505939483643,
|
| 274 |
+
"learning_rate": 1.5946880000000003e-05,
|
| 275 |
+
"loss": 0.4118,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 5.22418212890625,
|
| 281 |
+
"learning_rate": 1.5840213333333333e-05,
|
| 282 |
+
"loss": 0.4238,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 3.5867042541503906,
|
| 288 |
+
"learning_rate": 1.5733546666666666e-05,
|
| 289 |
+
"loss": 0.4093,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 3.2802393436431885,
|
| 295 |
+
"learning_rate": 1.5626880000000003e-05,
|
| 296 |
+
"loss": 0.4109,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 4.684053421020508,
|
| 302 |
+
"learning_rate": 1.5520213333333333e-05,
|
| 303 |
+
"loss": 0.416,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 5.455794334411621,
|
| 309 |
+
"learning_rate": 1.5413546666666666e-05,
|
| 310 |
+
"loss": 0.4205,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 3.779735565185547,
|
| 316 |
+
"learning_rate": 1.5306880000000003e-05,
|
| 317 |
+
"loss": 0.4167,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 3.9474680423736572,
|
| 323 |
+
"learning_rate": 1.5200213333333334e-05,
|
| 324 |
+
"loss": 0.4175,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 2.6914544105529785,
|
| 330 |
+
"learning_rate": 1.5093546666666668e-05,
|
| 331 |
+
"loss": 0.4157,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 3.8517110347747803,
|
| 337 |
+
"learning_rate": 1.498688e-05,
|
| 338 |
+
"loss": 0.4087,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 6.001178741455078,
|
| 344 |
+
"learning_rate": 1.4880213333333336e-05,
|
| 345 |
+
"loss": 0.4172,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 4.264939308166504,
|
| 351 |
+
"learning_rate": 1.4773546666666667e-05,
|
| 352 |
+
"loss": 0.4157,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 3.5257503986358643,
|
| 358 |
+
"learning_rate": 1.466688e-05,
|
| 359 |
+
"loss": 0.4145,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 3.0224406719207764,
|
| 365 |
+
"learning_rate": 1.4560213333333335e-05,
|
| 366 |
+
"loss": 0.4102,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 3.4603631496429443,
|
| 372 |
+
"learning_rate": 1.4453546666666667e-05,
|
| 373 |
+
"loss": 0.416,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 3.948413610458374,
|
| 379 |
+
"learning_rate": 1.434688e-05,
|
| 380 |
+
"loss": 0.4068,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 2.924689531326294,
|
| 386 |
+
"learning_rate": 1.4240213333333335e-05,
|
| 387 |
+
"loss": 0.4089,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 2.925736427307129,
|
| 393 |
+
"learning_rate": 1.4133546666666668e-05,
|
| 394 |
+
"loss": 0.4209,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 5.971268653869629,
|
| 400 |
+
"learning_rate": 1.402688e-05,
|
| 401 |
+
"loss": 0.4039,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 4.901790618896484,
|
| 407 |
+
"learning_rate": 1.3920213333333335e-05,
|
| 408 |
+
"loss": 0.4144,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 5.118570327758789,
|
| 414 |
+
"learning_rate": 1.3813546666666668e-05,
|
| 415 |
+
"loss": 0.4057,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 5.00353479385376,
|
| 421 |
+
"learning_rate": 1.370688e-05,
|
| 422 |
+
"loss": 0.4066,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 3.294429063796997,
|
| 428 |
+
"learning_rate": 1.3600213333333334e-05,
|
| 429 |
+
"loss": 0.4061,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 4.73533296585083,
|
| 435 |
+
"learning_rate": 1.3493546666666668e-05,
|
| 436 |
+
"loss": 0.4126,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 2.7575387954711914,
|
| 442 |
+
"learning_rate": 1.3386880000000003e-05,
|
| 443 |
+
"loss": 0.4083,
|
| 444 |
+
"step": 31000
|
| 445 |
+
}
|
| 446 |
+
],
|
| 447 |
+
"logging_steps": 500,
|
| 448 |
+
"max_steps": 93750,
|
| 449 |
+
"num_input_tokens_seen": 0,
|
| 450 |
+
"num_train_epochs": 3,
|
| 451 |
+
"save_steps": 500,
|
| 452 |
+
"stateful_callbacks": {
|
| 453 |
+
"TrainerControl": {
|
| 454 |
+
"args": {
|
| 455 |
+
"should_epoch_stop": false,
|
| 456 |
+
"should_evaluate": false,
|
| 457 |
+
"should_log": false,
|
| 458 |
+
"should_save": true,
|
| 459 |
+
"should_training_stop": false
|
| 460 |
+
},
|
| 461 |
+
"attributes": {}
|
| 462 |
+
}
|
| 463 |
+
},
|
| 464 |
+
"total_flos": 4.784855058786336e+16,
|
| 465 |
+
"train_batch_size": 32,
|
| 466 |
+
"trial_name": null,
|
| 467 |
+
"trial_params": null
|
| 468 |
+
}
|
checkpoint-31250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6205a4827a1926df97c9c45b264c999d8285f1eff2584a51171fad6052ad5c50
|
| 3 |
+
size 5304
|
checkpoint-31250/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-62500/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3,
|
| 23 |
+
"LABEL_4": 4
|
| 24 |
+
},
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "distilbert",
|
| 27 |
+
"n_heads": 12,
|
| 28 |
+
"n_layers": 6,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qa_dropout": 0.1,
|
| 32 |
+
"seq_classif_dropout": 0.2,
|
| 33 |
+
"sinusoidal_pos_embds": false,
|
| 34 |
+
"tie_weights_": true,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.52.3",
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
checkpoint-62500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5763ad5fb22790fc0d1315fce465d271a4c44b6a05d4f5b99423e37f48899992
|
| 3 |
+
size 267841796
|
checkpoint-62500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cc1b0e1176e2aa48d8e5a0734599698cd5a4b017fa493735a3376ab9670a4b3
|
| 3 |
+
size 535745722
|
checkpoint-62500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92b87de59ab83352b23a1e262067a81329c78c75bba85433126f85d9846ef399
|
| 3 |
+
size 14244
|
checkpoint-62500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:485e160cee733ef9c9351f37474fac61e20ed8289a21bde79406c82c076a1c80
|
| 3 |
+
size 1064
|
checkpoint-62500/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-62500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-62500/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-62500/trainer_state.json
ADDED
|
@@ -0,0 +1,909 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 62500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 5.113226413726807,
|
| 15 |
+
"learning_rate": 1.9893546666666667e-05,
|
| 16 |
+
"loss": 0.3997,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 1.5101436376571655,
|
| 22 |
+
"learning_rate": 1.978688e-05,
|
| 23 |
+
"loss": 0.3954,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 5.25643253326416,
|
| 29 |
+
"learning_rate": 1.9680213333333337e-05,
|
| 30 |
+
"loss": 0.4262,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 4.487380504608154,
|
| 36 |
+
"learning_rate": 1.9573546666666667e-05,
|
| 37 |
+
"loss": 0.4131,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 4.195590019226074,
|
| 43 |
+
"learning_rate": 1.946688e-05,
|
| 44 |
+
"loss": 0.4118,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 3.453535318374634,
|
| 50 |
+
"learning_rate": 1.9360213333333337e-05,
|
| 51 |
+
"loss": 0.4152,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 6.260850429534912,
|
| 57 |
+
"learning_rate": 1.925354666666667e-05,
|
| 58 |
+
"loss": 0.4254,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 3.717860221862793,
|
| 64 |
+
"learning_rate": 1.914688e-05,
|
| 65 |
+
"loss": 0.4134,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 2.7987215518951416,
|
| 71 |
+
"learning_rate": 1.9040213333333336e-05,
|
| 72 |
+
"loss": 0.4318,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 3.57886004447937,
|
| 78 |
+
"learning_rate": 1.893354666666667e-05,
|
| 79 |
+
"loss": 0.4178,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 3.7842671871185303,
|
| 85 |
+
"learning_rate": 1.882688e-05,
|
| 86 |
+
"loss": 0.4143,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 3.6401913166046143,
|
| 92 |
+
"learning_rate": 1.8720213333333336e-05,
|
| 93 |
+
"loss": 0.4283,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 2.6250557899475098,
|
| 99 |
+
"learning_rate": 1.861354666666667e-05,
|
| 100 |
+
"loss": 0.4066,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 4.987699031829834,
|
| 106 |
+
"learning_rate": 1.8506880000000003e-05,
|
| 107 |
+
"loss": 0.4074,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 3.055042266845703,
|
| 113 |
+
"learning_rate": 1.8400213333333336e-05,
|
| 114 |
+
"loss": 0.4102,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 2.8551082611083984,
|
| 120 |
+
"learning_rate": 1.829354666666667e-05,
|
| 121 |
+
"loss": 0.4154,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 4.127549171447754,
|
| 127 |
+
"learning_rate": 1.8186880000000002e-05,
|
| 128 |
+
"loss": 0.4267,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 4.929229736328125,
|
| 134 |
+
"learning_rate": 1.8080213333333336e-05,
|
| 135 |
+
"loss": 0.4123,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 3.787837505340576,
|
| 141 |
+
"learning_rate": 1.797354666666667e-05,
|
| 142 |
+
"loss": 0.4217,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 1.911741018295288,
|
| 148 |
+
"learning_rate": 1.7866880000000002e-05,
|
| 149 |
+
"loss": 0.4122,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 5.90802526473999,
|
| 155 |
+
"learning_rate": 1.7760213333333335e-05,
|
| 156 |
+
"loss": 0.4204,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 3.8967525959014893,
|
| 162 |
+
"learning_rate": 1.765354666666667e-05,
|
| 163 |
+
"loss": 0.4188,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 3.3974881172180176,
|
| 169 |
+
"learning_rate": 1.754688e-05,
|
| 170 |
+
"loss": 0.4131,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 3.672062397003174,
|
| 176 |
+
"learning_rate": 1.7440213333333335e-05,
|
| 177 |
+
"loss": 0.4129,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 4.360637664794922,
|
| 183 |
+
"learning_rate": 1.7333546666666668e-05,
|
| 184 |
+
"loss": 0.4288,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 4.036060810089111,
|
| 190 |
+
"learning_rate": 1.722688e-05,
|
| 191 |
+
"loss": 0.409,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 5.959667682647705,
|
| 197 |
+
"learning_rate": 1.7120213333333335e-05,
|
| 198 |
+
"loss": 0.4177,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 4.0133161544799805,
|
| 204 |
+
"learning_rate": 1.7013546666666668e-05,
|
| 205 |
+
"loss": 0.4261,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 4.409907341003418,
|
| 211 |
+
"learning_rate": 1.690688e-05,
|
| 212 |
+
"loss": 0.4261,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 6.2073163986206055,
|
| 218 |
+
"learning_rate": 1.6800213333333334e-05,
|
| 219 |
+
"loss": 0.4209,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 6.267955780029297,
|
| 225 |
+
"learning_rate": 1.6693546666666667e-05,
|
| 226 |
+
"loss": 0.408,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 4.548535346984863,
|
| 232 |
+
"learning_rate": 1.658688e-05,
|
| 233 |
+
"loss": 0.4178,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 3.5204384326934814,
|
| 239 |
+
"learning_rate": 1.6480213333333334e-05,
|
| 240 |
+
"loss": 0.416,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 4.745266914367676,
|
| 246 |
+
"learning_rate": 1.6373546666666667e-05,
|
| 247 |
+
"loss": 0.4102,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 5.38124418258667,
|
| 253 |
+
"learning_rate": 1.626688e-05,
|
| 254 |
+
"loss": 0.4169,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 3.408917188644409,
|
| 260 |
+
"learning_rate": 1.6160213333333334e-05,
|
| 261 |
+
"loss": 0.414,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 3.1644530296325684,
|
| 267 |
+
"learning_rate": 1.6053546666666667e-05,
|
| 268 |
+
"loss": 0.4037,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 3.7309505939483643,
|
| 274 |
+
"learning_rate": 1.5946880000000003e-05,
|
| 275 |
+
"loss": 0.4118,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 5.22418212890625,
|
| 281 |
+
"learning_rate": 1.5840213333333333e-05,
|
| 282 |
+
"loss": 0.4238,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 3.5867042541503906,
|
| 288 |
+
"learning_rate": 1.5733546666666666e-05,
|
| 289 |
+
"loss": 0.4093,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 3.2802393436431885,
|
| 295 |
+
"learning_rate": 1.5626880000000003e-05,
|
| 296 |
+
"loss": 0.4109,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 4.684053421020508,
|
| 302 |
+
"learning_rate": 1.5520213333333333e-05,
|
| 303 |
+
"loss": 0.416,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 5.455794334411621,
|
| 309 |
+
"learning_rate": 1.5413546666666666e-05,
|
| 310 |
+
"loss": 0.4205,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 3.779735565185547,
|
| 316 |
+
"learning_rate": 1.5306880000000003e-05,
|
| 317 |
+
"loss": 0.4167,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 3.9474680423736572,
|
| 323 |
+
"learning_rate": 1.5200213333333334e-05,
|
| 324 |
+
"loss": 0.4175,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 2.6914544105529785,
|
| 330 |
+
"learning_rate": 1.5093546666666668e-05,
|
| 331 |
+
"loss": 0.4157,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 3.8517110347747803,
|
| 337 |
+
"learning_rate": 1.498688e-05,
|
| 338 |
+
"loss": 0.4087,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 6.001178741455078,
|
| 344 |
+
"learning_rate": 1.4880213333333336e-05,
|
| 345 |
+
"loss": 0.4172,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 4.264939308166504,
|
| 351 |
+
"learning_rate": 1.4773546666666667e-05,
|
| 352 |
+
"loss": 0.4157,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 3.5257503986358643,
|
| 358 |
+
"learning_rate": 1.466688e-05,
|
| 359 |
+
"loss": 0.4145,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 3.0224406719207764,
|
| 365 |
+
"learning_rate": 1.4560213333333335e-05,
|
| 366 |
+
"loss": 0.4102,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 3.4603631496429443,
|
| 372 |
+
"learning_rate": 1.4453546666666667e-05,
|
| 373 |
+
"loss": 0.416,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 3.948413610458374,
|
| 379 |
+
"learning_rate": 1.434688e-05,
|
| 380 |
+
"loss": 0.4068,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 2.924689531326294,
|
| 386 |
+
"learning_rate": 1.4240213333333335e-05,
|
| 387 |
+
"loss": 0.4089,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 2.925736427307129,
|
| 393 |
+
"learning_rate": 1.4133546666666668e-05,
|
| 394 |
+
"loss": 0.4209,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 5.971268653869629,
|
| 400 |
+
"learning_rate": 1.402688e-05,
|
| 401 |
+
"loss": 0.4039,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 4.901790618896484,
|
| 407 |
+
"learning_rate": 1.3920213333333335e-05,
|
| 408 |
+
"loss": 0.4144,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 5.118570327758789,
|
| 414 |
+
"learning_rate": 1.3813546666666668e-05,
|
| 415 |
+
"loss": 0.4057,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 5.00353479385376,
|
| 421 |
+
"learning_rate": 1.370688e-05,
|
| 422 |
+
"loss": 0.4066,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 3.294429063796997,
|
| 428 |
+
"learning_rate": 1.3600213333333334e-05,
|
| 429 |
+
"loss": 0.4061,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 4.73533296585083,
|
| 435 |
+
"learning_rate": 1.3493546666666668e-05,
|
| 436 |
+
"loss": 0.4126,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 2.7575387954711914,
|
| 442 |
+
"learning_rate": 1.3386880000000003e-05,
|
| 443 |
+
"loss": 0.4083,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.008,
|
| 448 |
+
"grad_norm": 3.642165422439575,
|
| 449 |
+
"learning_rate": 1.3280213333333334e-05,
|
| 450 |
+
"loss": 0.3969,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.024,
|
| 455 |
+
"grad_norm": 4.842049598693848,
|
| 456 |
+
"learning_rate": 1.3173546666666667e-05,
|
| 457 |
+
"loss": 0.3725,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.04,
|
| 462 |
+
"grad_norm": 4.598811626434326,
|
| 463 |
+
"learning_rate": 1.3066880000000002e-05,
|
| 464 |
+
"loss": 0.3792,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.056,
|
| 469 |
+
"grad_norm": 5.48545503616333,
|
| 470 |
+
"learning_rate": 1.2960213333333334e-05,
|
| 471 |
+
"loss": 0.3779,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.072,
|
| 476 |
+
"grad_norm": 3.7623953819274902,
|
| 477 |
+
"learning_rate": 1.2853546666666667e-05,
|
| 478 |
+
"loss": 0.3727,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.088,
|
| 483 |
+
"grad_norm": 6.078208923339844,
|
| 484 |
+
"learning_rate": 1.2746880000000002e-05,
|
| 485 |
+
"loss": 0.3642,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.104,
|
| 490 |
+
"grad_norm": 4.3490142822265625,
|
| 491 |
+
"learning_rate": 1.2640213333333335e-05,
|
| 492 |
+
"loss": 0.3814,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.12,
|
| 497 |
+
"grad_norm": 4.757129192352295,
|
| 498 |
+
"learning_rate": 1.2533546666666667e-05,
|
| 499 |
+
"loss": 0.3769,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1360000000000001,
|
| 504 |
+
"grad_norm": 5.54279088973999,
|
| 505 |
+
"learning_rate": 1.2426880000000002e-05,
|
| 506 |
+
"loss": 0.3639,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.152,
|
| 511 |
+
"grad_norm": 4.752306938171387,
|
| 512 |
+
"learning_rate": 1.2320213333333335e-05,
|
| 513 |
+
"loss": 0.3696,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.168,
|
| 518 |
+
"grad_norm": 4.217135429382324,
|
| 519 |
+
"learning_rate": 1.2213546666666666e-05,
|
| 520 |
+
"loss": 0.3735,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.184,
|
| 525 |
+
"grad_norm": 3.0427017211914062,
|
| 526 |
+
"learning_rate": 1.2106880000000001e-05,
|
| 527 |
+
"loss": 0.3774,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.2,
|
| 532 |
+
"grad_norm": 4.772624492645264,
|
| 533 |
+
"learning_rate": 1.2000213333333334e-05,
|
| 534 |
+
"loss": 0.3728,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.216,
|
| 539 |
+
"grad_norm": 4.131636142730713,
|
| 540 |
+
"learning_rate": 1.1893546666666666e-05,
|
| 541 |
+
"loss": 0.3869,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.232,
|
| 546 |
+
"grad_norm": 3.5569746494293213,
|
| 547 |
+
"learning_rate": 1.1786880000000001e-05,
|
| 548 |
+
"loss": 0.3769,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.248,
|
| 553 |
+
"grad_norm": 4.9384942054748535,
|
| 554 |
+
"learning_rate": 1.1680213333333334e-05,
|
| 555 |
+
"loss": 0.3695,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.264,
|
| 560 |
+
"grad_norm": 3.6120994091033936,
|
| 561 |
+
"learning_rate": 1.1573546666666669e-05,
|
| 562 |
+
"loss": 0.3857,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.28,
|
| 567 |
+
"grad_norm": 6.383695602416992,
|
| 568 |
+
"learning_rate": 1.146688e-05,
|
| 569 |
+
"loss": 0.3734,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.296,
|
| 574 |
+
"grad_norm": 3.982789993286133,
|
| 575 |
+
"learning_rate": 1.1360213333333334e-05,
|
| 576 |
+
"loss": 0.3786,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.312,
|
| 581 |
+
"grad_norm": 6.952799320220947,
|
| 582 |
+
"learning_rate": 1.1253546666666669e-05,
|
| 583 |
+
"loss": 0.3781,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.328,
|
| 588 |
+
"grad_norm": 5.625407695770264,
|
| 589 |
+
"learning_rate": 1.114688e-05,
|
| 590 |
+
"loss": 0.3836,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.3439999999999999,
|
| 595 |
+
"grad_norm": 3.1417617797851562,
|
| 596 |
+
"learning_rate": 1.1040213333333333e-05,
|
| 597 |
+
"loss": 0.3759,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3599999999999999,
|
| 602 |
+
"grad_norm": 3.6484148502349854,
|
| 603 |
+
"learning_rate": 1.0933546666666668e-05,
|
| 604 |
+
"loss": 0.3723,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.376,
|
| 609 |
+
"grad_norm": 8.22464656829834,
|
| 610 |
+
"learning_rate": 1.0826880000000002e-05,
|
| 611 |
+
"loss": 0.3774,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.392,
|
| 616 |
+
"grad_norm": 4.700166702270508,
|
| 617 |
+
"learning_rate": 1.0720213333333333e-05,
|
| 618 |
+
"loss": 0.3677,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.408,
|
| 623 |
+
"grad_norm": 4.609044551849365,
|
| 624 |
+
"learning_rate": 1.0613546666666668e-05,
|
| 625 |
+
"loss": 0.3748,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.424,
|
| 630 |
+
"grad_norm": 3.7087044715881348,
|
| 631 |
+
"learning_rate": 1.0506880000000001e-05,
|
| 632 |
+
"loss": 0.3802,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.44,
|
| 637 |
+
"grad_norm": 1.8805216550827026,
|
| 638 |
+
"learning_rate": 1.0400213333333333e-05,
|
| 639 |
+
"loss": 0.3652,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.456,
|
| 644 |
+
"grad_norm": 6.790294647216797,
|
| 645 |
+
"learning_rate": 1.0293546666666668e-05,
|
| 646 |
+
"loss": 0.3823,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.472,
|
| 651 |
+
"grad_norm": 4.213987827301025,
|
| 652 |
+
"learning_rate": 1.0186880000000001e-05,
|
| 653 |
+
"loss": 0.3807,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.488,
|
| 658 |
+
"grad_norm": 3.743255138397217,
|
| 659 |
+
"learning_rate": 1.0080213333333336e-05,
|
| 660 |
+
"loss": 0.3813,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.504,
|
| 665 |
+
"grad_norm": 3.1213364601135254,
|
| 666 |
+
"learning_rate": 9.973546666666667e-06,
|
| 667 |
+
"loss": 0.3803,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.52,
|
| 672 |
+
"grad_norm": 5.112852573394775,
|
| 673 |
+
"learning_rate": 9.86688e-06,
|
| 674 |
+
"loss": 0.3743,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.536,
|
| 679 |
+
"grad_norm": 3.404827117919922,
|
| 680 |
+
"learning_rate": 9.760213333333334e-06,
|
| 681 |
+
"loss": 0.384,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.552,
|
| 686 |
+
"grad_norm": 5.493263244628906,
|
| 687 |
+
"learning_rate": 9.653546666666667e-06,
|
| 688 |
+
"loss": 0.3715,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.568,
|
| 693 |
+
"grad_norm": 4.558899402618408,
|
| 694 |
+
"learning_rate": 9.54688e-06,
|
| 695 |
+
"loss": 0.382,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.584,
|
| 700 |
+
"grad_norm": 5.206460952758789,
|
| 701 |
+
"learning_rate": 9.440213333333335e-06,
|
| 702 |
+
"loss": 0.3645,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6,
|
| 707 |
+
"grad_norm": 2.7753446102142334,
|
| 708 |
+
"learning_rate": 9.333546666666667e-06,
|
| 709 |
+
"loss": 0.3757,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.616,
|
| 714 |
+
"grad_norm": 9.405357360839844,
|
| 715 |
+
"learning_rate": 9.22688e-06,
|
| 716 |
+
"loss": 0.3734,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6320000000000001,
|
| 721 |
+
"grad_norm": 3.231565237045288,
|
| 722 |
+
"learning_rate": 9.120213333333335e-06,
|
| 723 |
+
"loss": 0.3795,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6480000000000001,
|
| 728 |
+
"grad_norm": 7.080390453338623,
|
| 729 |
+
"learning_rate": 9.013546666666666e-06,
|
| 730 |
+
"loss": 0.3757,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.6640000000000001,
|
| 735 |
+
"grad_norm": 4.521383285522461,
|
| 736 |
+
"learning_rate": 8.906880000000001e-06,
|
| 737 |
+
"loss": 0.3757,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6800000000000002,
|
| 742 |
+
"grad_norm": 4.189393997192383,
|
| 743 |
+
"learning_rate": 8.800213333333335e-06,
|
| 744 |
+
"loss": 0.3837,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.696,
|
| 749 |
+
"grad_norm": 4.038729667663574,
|
| 750 |
+
"learning_rate": 8.693546666666668e-06,
|
| 751 |
+
"loss": 0.3746,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.712,
|
| 756 |
+
"grad_norm": 5.04473352432251,
|
| 757 |
+
"learning_rate": 8.586880000000001e-06,
|
| 758 |
+
"loss": 0.3811,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.728,
|
| 763 |
+
"grad_norm": 3.034491539001465,
|
| 764 |
+
"learning_rate": 8.480213333333334e-06,
|
| 765 |
+
"loss": 0.3687,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.744,
|
| 770 |
+
"grad_norm": 4.781718730926514,
|
| 771 |
+
"learning_rate": 8.373546666666667e-06,
|
| 772 |
+
"loss": 0.3712,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.76,
|
| 777 |
+
"grad_norm": 3.6381618976593018,
|
| 778 |
+
"learning_rate": 8.26688e-06,
|
| 779 |
+
"loss": 0.3854,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.776,
|
| 784 |
+
"grad_norm": 4.6414103507995605,
|
| 785 |
+
"learning_rate": 8.160213333333334e-06,
|
| 786 |
+
"loss": 0.3774,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.792,
|
| 791 |
+
"grad_norm": 3.813014268875122,
|
| 792 |
+
"learning_rate": 8.053546666666667e-06,
|
| 793 |
+
"loss": 0.3799,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.808,
|
| 798 |
+
"grad_norm": 3.00891375541687,
|
| 799 |
+
"learning_rate": 7.94688e-06,
|
| 800 |
+
"loss": 0.3797,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8239999999999998,
|
| 805 |
+
"grad_norm": 3.0977120399475098,
|
| 806 |
+
"learning_rate": 7.840213333333334e-06,
|
| 807 |
+
"loss": 0.3789,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8399999999999999,
|
| 812 |
+
"grad_norm": 3.6573853492736816,
|
| 813 |
+
"learning_rate": 7.733546666666667e-06,
|
| 814 |
+
"loss": 0.3756,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.8559999999999999,
|
| 819 |
+
"grad_norm": 2.03202223777771,
|
| 820 |
+
"learning_rate": 7.626880000000001e-06,
|
| 821 |
+
"loss": 0.3776,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.8719999999999999,
|
| 826 |
+
"grad_norm": 4.345327854156494,
|
| 827 |
+
"learning_rate": 7.520213333333334e-06,
|
| 828 |
+
"loss": 0.3811,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.888,
|
| 833 |
+
"grad_norm": 6.366291522979736,
|
| 834 |
+
"learning_rate": 7.413546666666667e-06,
|
| 835 |
+
"loss": 0.3666,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.904,
|
| 840 |
+
"grad_norm": 5.347266674041748,
|
| 841 |
+
"learning_rate": 7.306880000000001e-06,
|
| 842 |
+
"loss": 0.3768,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.92,
|
| 847 |
+
"grad_norm": 3.8422532081604004,
|
| 848 |
+
"learning_rate": 7.200213333333334e-06,
|
| 849 |
+
"loss": 0.3774,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.936,
|
| 854 |
+
"grad_norm": 4.547689914703369,
|
| 855 |
+
"learning_rate": 7.093546666666668e-06,
|
| 856 |
+
"loss": 0.3723,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.952,
|
| 861 |
+
"grad_norm": 4.095975399017334,
|
| 862 |
+
"learning_rate": 6.98688e-06,
|
| 863 |
+
"loss": 0.3799,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.968,
|
| 868 |
+
"grad_norm": 4.994481563568115,
|
| 869 |
+
"learning_rate": 6.880213333333334e-06,
|
| 870 |
+
"loss": 0.3643,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.984,
|
| 875 |
+
"grad_norm": 4.072275161743164,
|
| 876 |
+
"learning_rate": 6.7735466666666676e-06,
|
| 877 |
+
"loss": 0.3716,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"grad_norm": 5.04338264465332,
|
| 883 |
+
"learning_rate": 6.66688e-06,
|
| 884 |
+
"loss": 0.3807,
|
| 885 |
+
"step": 62500
|
| 886 |
+
}
|
| 887 |
+
],
|
| 888 |
+
"logging_steps": 500,
|
| 889 |
+
"max_steps": 93750,
|
| 890 |
+
"num_input_tokens_seen": 0,
|
| 891 |
+
"num_train_epochs": 3,
|
| 892 |
+
"save_steps": 500,
|
| 893 |
+
"stateful_callbacks": {
|
| 894 |
+
"TrainerControl": {
|
| 895 |
+
"args": {
|
| 896 |
+
"should_epoch_stop": false,
|
| 897 |
+
"should_evaluate": false,
|
| 898 |
+
"should_log": false,
|
| 899 |
+
"should_save": true,
|
| 900 |
+
"should_training_stop": false
|
| 901 |
+
},
|
| 902 |
+
"attributes": {}
|
| 903 |
+
}
|
| 904 |
+
},
|
| 905 |
+
"total_flos": 9.569967614854368e+16,
|
| 906 |
+
"train_batch_size": 32,
|
| 907 |
+
"trial_name": null,
|
| 908 |
+
"trial_params": null
|
| 909 |
+
}
|
checkpoint-62500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6205a4827a1926df97c9c45b264c999d8285f1eff2584a51171fad6052ad5c50
|
| 3 |
+
size 5304
|
checkpoint-62500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-93750/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3,
|
| 23 |
+
"LABEL_4": 4
|
| 24 |
+
},
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "distilbert",
|
| 27 |
+
"n_heads": 12,
|
| 28 |
+
"n_layers": 6,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qa_dropout": 0.1,
|
| 32 |
+
"seq_classif_dropout": 0.2,
|
| 33 |
+
"sinusoidal_pos_embds": false,
|
| 34 |
+
"tie_weights_": true,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.52.3",
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
checkpoint-93750/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f43eae07f9dac8a98c715861ba2f9dc02cd4b533afcb5e4d27ce1d395f3cad97
|
| 3 |
+
size 267841796
|
checkpoint-93750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8adedb44f64592496796ca50c26a58b6aada261c5e0c1c4dd60d5588a35c7901
|
| 3 |
+
size 535745722
|
checkpoint-93750/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67763ce835b877b58ca7055aacd04aff2ba7b2e2d427977c1e373b06bf34b036
|
| 3 |
+
size 14244
|
checkpoint-93750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aa9f6360c774b04b1e30012daf15b29cbb06b91062247942c67d066b7d43b58
|
| 3 |
+
size 1064
|
checkpoint-93750/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-93750/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-93750/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-93750/trainer_state.json
ADDED
|
@@ -0,0 +1,1343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 93750,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 5.113226413726807,
|
| 15 |
+
"learning_rate": 1.9893546666666667e-05,
|
| 16 |
+
"loss": 0.3997,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 1.5101436376571655,
|
| 22 |
+
"learning_rate": 1.978688e-05,
|
| 23 |
+
"loss": 0.3954,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 5.25643253326416,
|
| 29 |
+
"learning_rate": 1.9680213333333337e-05,
|
| 30 |
+
"loss": 0.4262,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 4.487380504608154,
|
| 36 |
+
"learning_rate": 1.9573546666666667e-05,
|
| 37 |
+
"loss": 0.4131,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 4.195590019226074,
|
| 43 |
+
"learning_rate": 1.946688e-05,
|
| 44 |
+
"loss": 0.4118,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 3.453535318374634,
|
| 50 |
+
"learning_rate": 1.9360213333333337e-05,
|
| 51 |
+
"loss": 0.4152,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 6.260850429534912,
|
| 57 |
+
"learning_rate": 1.925354666666667e-05,
|
| 58 |
+
"loss": 0.4254,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 3.717860221862793,
|
| 64 |
+
"learning_rate": 1.914688e-05,
|
| 65 |
+
"loss": 0.4134,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 2.7987215518951416,
|
| 71 |
+
"learning_rate": 1.9040213333333336e-05,
|
| 72 |
+
"loss": 0.4318,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 3.57886004447937,
|
| 78 |
+
"learning_rate": 1.893354666666667e-05,
|
| 79 |
+
"loss": 0.4178,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 3.7842671871185303,
|
| 85 |
+
"learning_rate": 1.882688e-05,
|
| 86 |
+
"loss": 0.4143,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 3.6401913166046143,
|
| 92 |
+
"learning_rate": 1.8720213333333336e-05,
|
| 93 |
+
"loss": 0.4283,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 2.6250557899475098,
|
| 99 |
+
"learning_rate": 1.861354666666667e-05,
|
| 100 |
+
"loss": 0.4066,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 4.987699031829834,
|
| 106 |
+
"learning_rate": 1.8506880000000003e-05,
|
| 107 |
+
"loss": 0.4074,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 3.055042266845703,
|
| 113 |
+
"learning_rate": 1.8400213333333336e-05,
|
| 114 |
+
"loss": 0.4102,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 2.8551082611083984,
|
| 120 |
+
"learning_rate": 1.829354666666667e-05,
|
| 121 |
+
"loss": 0.4154,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 4.127549171447754,
|
| 127 |
+
"learning_rate": 1.8186880000000002e-05,
|
| 128 |
+
"loss": 0.4267,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 4.929229736328125,
|
| 134 |
+
"learning_rate": 1.8080213333333336e-05,
|
| 135 |
+
"loss": 0.4123,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 3.787837505340576,
|
| 141 |
+
"learning_rate": 1.797354666666667e-05,
|
| 142 |
+
"loss": 0.4217,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 1.911741018295288,
|
| 148 |
+
"learning_rate": 1.7866880000000002e-05,
|
| 149 |
+
"loss": 0.4122,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 5.90802526473999,
|
| 155 |
+
"learning_rate": 1.7760213333333335e-05,
|
| 156 |
+
"loss": 0.4204,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 3.8967525959014893,
|
| 162 |
+
"learning_rate": 1.765354666666667e-05,
|
| 163 |
+
"loss": 0.4188,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 3.3974881172180176,
|
| 169 |
+
"learning_rate": 1.754688e-05,
|
| 170 |
+
"loss": 0.4131,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 3.672062397003174,
|
| 176 |
+
"learning_rate": 1.7440213333333335e-05,
|
| 177 |
+
"loss": 0.4129,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 4.360637664794922,
|
| 183 |
+
"learning_rate": 1.7333546666666668e-05,
|
| 184 |
+
"loss": 0.4288,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 4.036060810089111,
|
| 190 |
+
"learning_rate": 1.722688e-05,
|
| 191 |
+
"loss": 0.409,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 5.959667682647705,
|
| 197 |
+
"learning_rate": 1.7120213333333335e-05,
|
| 198 |
+
"loss": 0.4177,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 4.0133161544799805,
|
| 204 |
+
"learning_rate": 1.7013546666666668e-05,
|
| 205 |
+
"loss": 0.4261,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 4.409907341003418,
|
| 211 |
+
"learning_rate": 1.690688e-05,
|
| 212 |
+
"loss": 0.4261,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 6.2073163986206055,
|
| 218 |
+
"learning_rate": 1.6800213333333334e-05,
|
| 219 |
+
"loss": 0.4209,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 6.267955780029297,
|
| 225 |
+
"learning_rate": 1.6693546666666667e-05,
|
| 226 |
+
"loss": 0.408,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 4.548535346984863,
|
| 232 |
+
"learning_rate": 1.658688e-05,
|
| 233 |
+
"loss": 0.4178,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 3.5204384326934814,
|
| 239 |
+
"learning_rate": 1.6480213333333334e-05,
|
| 240 |
+
"loss": 0.416,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 4.745266914367676,
|
| 246 |
+
"learning_rate": 1.6373546666666667e-05,
|
| 247 |
+
"loss": 0.4102,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 5.38124418258667,
|
| 253 |
+
"learning_rate": 1.626688e-05,
|
| 254 |
+
"loss": 0.4169,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 3.408917188644409,
|
| 260 |
+
"learning_rate": 1.6160213333333334e-05,
|
| 261 |
+
"loss": 0.414,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 3.1644530296325684,
|
| 267 |
+
"learning_rate": 1.6053546666666667e-05,
|
| 268 |
+
"loss": 0.4037,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 3.7309505939483643,
|
| 274 |
+
"learning_rate": 1.5946880000000003e-05,
|
| 275 |
+
"loss": 0.4118,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 5.22418212890625,
|
| 281 |
+
"learning_rate": 1.5840213333333333e-05,
|
| 282 |
+
"loss": 0.4238,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 3.5867042541503906,
|
| 288 |
+
"learning_rate": 1.5733546666666666e-05,
|
| 289 |
+
"loss": 0.4093,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 3.2802393436431885,
|
| 295 |
+
"learning_rate": 1.5626880000000003e-05,
|
| 296 |
+
"loss": 0.4109,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 4.684053421020508,
|
| 302 |
+
"learning_rate": 1.5520213333333333e-05,
|
| 303 |
+
"loss": 0.416,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 5.455794334411621,
|
| 309 |
+
"learning_rate": 1.5413546666666666e-05,
|
| 310 |
+
"loss": 0.4205,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 3.779735565185547,
|
| 316 |
+
"learning_rate": 1.5306880000000003e-05,
|
| 317 |
+
"loss": 0.4167,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 3.9474680423736572,
|
| 323 |
+
"learning_rate": 1.5200213333333334e-05,
|
| 324 |
+
"loss": 0.4175,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 2.6914544105529785,
|
| 330 |
+
"learning_rate": 1.5093546666666668e-05,
|
| 331 |
+
"loss": 0.4157,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 3.8517110347747803,
|
| 337 |
+
"learning_rate": 1.498688e-05,
|
| 338 |
+
"loss": 0.4087,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 6.001178741455078,
|
| 344 |
+
"learning_rate": 1.4880213333333336e-05,
|
| 345 |
+
"loss": 0.4172,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 4.264939308166504,
|
| 351 |
+
"learning_rate": 1.4773546666666667e-05,
|
| 352 |
+
"loss": 0.4157,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 3.5257503986358643,
|
| 358 |
+
"learning_rate": 1.466688e-05,
|
| 359 |
+
"loss": 0.4145,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 3.0224406719207764,
|
| 365 |
+
"learning_rate": 1.4560213333333335e-05,
|
| 366 |
+
"loss": 0.4102,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 3.4603631496429443,
|
| 372 |
+
"learning_rate": 1.4453546666666667e-05,
|
| 373 |
+
"loss": 0.416,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 3.948413610458374,
|
| 379 |
+
"learning_rate": 1.434688e-05,
|
| 380 |
+
"loss": 0.4068,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 2.924689531326294,
|
| 386 |
+
"learning_rate": 1.4240213333333335e-05,
|
| 387 |
+
"loss": 0.4089,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 2.925736427307129,
|
| 393 |
+
"learning_rate": 1.4133546666666668e-05,
|
| 394 |
+
"loss": 0.4209,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 5.971268653869629,
|
| 400 |
+
"learning_rate": 1.402688e-05,
|
| 401 |
+
"loss": 0.4039,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 4.901790618896484,
|
| 407 |
+
"learning_rate": 1.3920213333333335e-05,
|
| 408 |
+
"loss": 0.4144,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 5.118570327758789,
|
| 414 |
+
"learning_rate": 1.3813546666666668e-05,
|
| 415 |
+
"loss": 0.4057,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 5.00353479385376,
|
| 421 |
+
"learning_rate": 1.370688e-05,
|
| 422 |
+
"loss": 0.4066,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 3.294429063796997,
|
| 428 |
+
"learning_rate": 1.3600213333333334e-05,
|
| 429 |
+
"loss": 0.4061,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 4.73533296585083,
|
| 435 |
+
"learning_rate": 1.3493546666666668e-05,
|
| 436 |
+
"loss": 0.4126,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 2.7575387954711914,
|
| 442 |
+
"learning_rate": 1.3386880000000003e-05,
|
| 443 |
+
"loss": 0.4083,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.008,
|
| 448 |
+
"grad_norm": 3.642165422439575,
|
| 449 |
+
"learning_rate": 1.3280213333333334e-05,
|
| 450 |
+
"loss": 0.3969,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.024,
|
| 455 |
+
"grad_norm": 4.842049598693848,
|
| 456 |
+
"learning_rate": 1.3173546666666667e-05,
|
| 457 |
+
"loss": 0.3725,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.04,
|
| 462 |
+
"grad_norm": 4.598811626434326,
|
| 463 |
+
"learning_rate": 1.3066880000000002e-05,
|
| 464 |
+
"loss": 0.3792,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.056,
|
| 469 |
+
"grad_norm": 5.48545503616333,
|
| 470 |
+
"learning_rate": 1.2960213333333334e-05,
|
| 471 |
+
"loss": 0.3779,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.072,
|
| 476 |
+
"grad_norm": 3.7623953819274902,
|
| 477 |
+
"learning_rate": 1.2853546666666667e-05,
|
| 478 |
+
"loss": 0.3727,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.088,
|
| 483 |
+
"grad_norm": 6.078208923339844,
|
| 484 |
+
"learning_rate": 1.2746880000000002e-05,
|
| 485 |
+
"loss": 0.3642,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.104,
|
| 490 |
+
"grad_norm": 4.3490142822265625,
|
| 491 |
+
"learning_rate": 1.2640213333333335e-05,
|
| 492 |
+
"loss": 0.3814,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.12,
|
| 497 |
+
"grad_norm": 4.757129192352295,
|
| 498 |
+
"learning_rate": 1.2533546666666667e-05,
|
| 499 |
+
"loss": 0.3769,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1360000000000001,
|
| 504 |
+
"grad_norm": 5.54279088973999,
|
| 505 |
+
"learning_rate": 1.2426880000000002e-05,
|
| 506 |
+
"loss": 0.3639,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.152,
|
| 511 |
+
"grad_norm": 4.752306938171387,
|
| 512 |
+
"learning_rate": 1.2320213333333335e-05,
|
| 513 |
+
"loss": 0.3696,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.168,
|
| 518 |
+
"grad_norm": 4.217135429382324,
|
| 519 |
+
"learning_rate": 1.2213546666666666e-05,
|
| 520 |
+
"loss": 0.3735,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.184,
|
| 525 |
+
"grad_norm": 3.0427017211914062,
|
| 526 |
+
"learning_rate": 1.2106880000000001e-05,
|
| 527 |
+
"loss": 0.3774,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.2,
|
| 532 |
+
"grad_norm": 4.772624492645264,
|
| 533 |
+
"learning_rate": 1.2000213333333334e-05,
|
| 534 |
+
"loss": 0.3728,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.216,
|
| 539 |
+
"grad_norm": 4.131636142730713,
|
| 540 |
+
"learning_rate": 1.1893546666666666e-05,
|
| 541 |
+
"loss": 0.3869,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.232,
|
| 546 |
+
"grad_norm": 3.5569746494293213,
|
| 547 |
+
"learning_rate": 1.1786880000000001e-05,
|
| 548 |
+
"loss": 0.3769,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.248,
|
| 553 |
+
"grad_norm": 4.9384942054748535,
|
| 554 |
+
"learning_rate": 1.1680213333333334e-05,
|
| 555 |
+
"loss": 0.3695,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.264,
|
| 560 |
+
"grad_norm": 3.6120994091033936,
|
| 561 |
+
"learning_rate": 1.1573546666666669e-05,
|
| 562 |
+
"loss": 0.3857,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.28,
|
| 567 |
+
"grad_norm": 6.383695602416992,
|
| 568 |
+
"learning_rate": 1.146688e-05,
|
| 569 |
+
"loss": 0.3734,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.296,
|
| 574 |
+
"grad_norm": 3.982789993286133,
|
| 575 |
+
"learning_rate": 1.1360213333333334e-05,
|
| 576 |
+
"loss": 0.3786,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.312,
|
| 581 |
+
"grad_norm": 6.952799320220947,
|
| 582 |
+
"learning_rate": 1.1253546666666669e-05,
|
| 583 |
+
"loss": 0.3781,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.328,
|
| 588 |
+
"grad_norm": 5.625407695770264,
|
| 589 |
+
"learning_rate": 1.114688e-05,
|
| 590 |
+
"loss": 0.3836,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.3439999999999999,
|
| 595 |
+
"grad_norm": 3.1417617797851562,
|
| 596 |
+
"learning_rate": 1.1040213333333333e-05,
|
| 597 |
+
"loss": 0.3759,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3599999999999999,
|
| 602 |
+
"grad_norm": 3.6484148502349854,
|
| 603 |
+
"learning_rate": 1.0933546666666668e-05,
|
| 604 |
+
"loss": 0.3723,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.376,
|
| 609 |
+
"grad_norm": 8.22464656829834,
|
| 610 |
+
"learning_rate": 1.0826880000000002e-05,
|
| 611 |
+
"loss": 0.3774,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.392,
|
| 616 |
+
"grad_norm": 4.700166702270508,
|
| 617 |
+
"learning_rate": 1.0720213333333333e-05,
|
| 618 |
+
"loss": 0.3677,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.408,
|
| 623 |
+
"grad_norm": 4.609044551849365,
|
| 624 |
+
"learning_rate": 1.0613546666666668e-05,
|
| 625 |
+
"loss": 0.3748,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.424,
|
| 630 |
+
"grad_norm": 3.7087044715881348,
|
| 631 |
+
"learning_rate": 1.0506880000000001e-05,
|
| 632 |
+
"loss": 0.3802,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.44,
|
| 637 |
+
"grad_norm": 1.8805216550827026,
|
| 638 |
+
"learning_rate": 1.0400213333333333e-05,
|
| 639 |
+
"loss": 0.3652,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.456,
|
| 644 |
+
"grad_norm": 6.790294647216797,
|
| 645 |
+
"learning_rate": 1.0293546666666668e-05,
|
| 646 |
+
"loss": 0.3823,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.472,
|
| 651 |
+
"grad_norm": 4.213987827301025,
|
| 652 |
+
"learning_rate": 1.0186880000000001e-05,
|
| 653 |
+
"loss": 0.3807,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.488,
|
| 658 |
+
"grad_norm": 3.743255138397217,
|
| 659 |
+
"learning_rate": 1.0080213333333336e-05,
|
| 660 |
+
"loss": 0.3813,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.504,
|
| 665 |
+
"grad_norm": 3.1213364601135254,
|
| 666 |
+
"learning_rate": 9.973546666666667e-06,
|
| 667 |
+
"loss": 0.3803,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.52,
|
| 672 |
+
"grad_norm": 5.112852573394775,
|
| 673 |
+
"learning_rate": 9.86688e-06,
|
| 674 |
+
"loss": 0.3743,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.536,
|
| 679 |
+
"grad_norm": 3.404827117919922,
|
| 680 |
+
"learning_rate": 9.760213333333334e-06,
|
| 681 |
+
"loss": 0.384,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.552,
|
| 686 |
+
"grad_norm": 5.493263244628906,
|
| 687 |
+
"learning_rate": 9.653546666666667e-06,
|
| 688 |
+
"loss": 0.3715,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.568,
|
| 693 |
+
"grad_norm": 4.558899402618408,
|
| 694 |
+
"learning_rate": 9.54688e-06,
|
| 695 |
+
"loss": 0.382,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.584,
|
| 700 |
+
"grad_norm": 5.206460952758789,
|
| 701 |
+
"learning_rate": 9.440213333333335e-06,
|
| 702 |
+
"loss": 0.3645,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6,
|
| 707 |
+
"grad_norm": 2.7753446102142334,
|
| 708 |
+
"learning_rate": 9.333546666666667e-06,
|
| 709 |
+
"loss": 0.3757,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.616,
|
| 714 |
+
"grad_norm": 9.405357360839844,
|
| 715 |
+
"learning_rate": 9.22688e-06,
|
| 716 |
+
"loss": 0.3734,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6320000000000001,
|
| 721 |
+
"grad_norm": 3.231565237045288,
|
| 722 |
+
"learning_rate": 9.120213333333335e-06,
|
| 723 |
+
"loss": 0.3795,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6480000000000001,
|
| 728 |
+
"grad_norm": 7.080390453338623,
|
| 729 |
+
"learning_rate": 9.013546666666666e-06,
|
| 730 |
+
"loss": 0.3757,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.6640000000000001,
|
| 735 |
+
"grad_norm": 4.521383285522461,
|
| 736 |
+
"learning_rate": 8.906880000000001e-06,
|
| 737 |
+
"loss": 0.3757,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6800000000000002,
|
| 742 |
+
"grad_norm": 4.189393997192383,
|
| 743 |
+
"learning_rate": 8.800213333333335e-06,
|
| 744 |
+
"loss": 0.3837,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.696,
|
| 749 |
+
"grad_norm": 4.038729667663574,
|
| 750 |
+
"learning_rate": 8.693546666666668e-06,
|
| 751 |
+
"loss": 0.3746,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.712,
|
| 756 |
+
"grad_norm": 5.04473352432251,
|
| 757 |
+
"learning_rate": 8.586880000000001e-06,
|
| 758 |
+
"loss": 0.3811,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.728,
|
| 763 |
+
"grad_norm": 3.034491539001465,
|
| 764 |
+
"learning_rate": 8.480213333333334e-06,
|
| 765 |
+
"loss": 0.3687,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.744,
|
| 770 |
+
"grad_norm": 4.781718730926514,
|
| 771 |
+
"learning_rate": 8.373546666666667e-06,
|
| 772 |
+
"loss": 0.3712,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.76,
|
| 777 |
+
"grad_norm": 3.6381618976593018,
|
| 778 |
+
"learning_rate": 8.26688e-06,
|
| 779 |
+
"loss": 0.3854,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.776,
|
| 784 |
+
"grad_norm": 4.6414103507995605,
|
| 785 |
+
"learning_rate": 8.160213333333334e-06,
|
| 786 |
+
"loss": 0.3774,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.792,
|
| 791 |
+
"grad_norm": 3.813014268875122,
|
| 792 |
+
"learning_rate": 8.053546666666667e-06,
|
| 793 |
+
"loss": 0.3799,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.808,
|
| 798 |
+
"grad_norm": 3.00891375541687,
|
| 799 |
+
"learning_rate": 7.94688e-06,
|
| 800 |
+
"loss": 0.3797,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8239999999999998,
|
| 805 |
+
"grad_norm": 3.0977120399475098,
|
| 806 |
+
"learning_rate": 7.840213333333334e-06,
|
| 807 |
+
"loss": 0.3789,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8399999999999999,
|
| 812 |
+
"grad_norm": 3.6573853492736816,
|
| 813 |
+
"learning_rate": 7.733546666666667e-06,
|
| 814 |
+
"loss": 0.3756,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.8559999999999999,
|
| 819 |
+
"grad_norm": 2.03202223777771,
|
| 820 |
+
"learning_rate": 7.626880000000001e-06,
|
| 821 |
+
"loss": 0.3776,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.8719999999999999,
|
| 826 |
+
"grad_norm": 4.345327854156494,
|
| 827 |
+
"learning_rate": 7.520213333333334e-06,
|
| 828 |
+
"loss": 0.3811,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.888,
|
| 833 |
+
"grad_norm": 6.366291522979736,
|
| 834 |
+
"learning_rate": 7.413546666666667e-06,
|
| 835 |
+
"loss": 0.3666,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.904,
|
| 840 |
+
"grad_norm": 5.347266674041748,
|
| 841 |
+
"learning_rate": 7.306880000000001e-06,
|
| 842 |
+
"loss": 0.3768,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.92,
|
| 847 |
+
"grad_norm": 3.8422532081604004,
|
| 848 |
+
"learning_rate": 7.200213333333334e-06,
|
| 849 |
+
"loss": 0.3774,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.936,
|
| 854 |
+
"grad_norm": 4.547689914703369,
|
| 855 |
+
"learning_rate": 7.093546666666668e-06,
|
| 856 |
+
"loss": 0.3723,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.952,
|
| 861 |
+
"grad_norm": 4.095975399017334,
|
| 862 |
+
"learning_rate": 6.98688e-06,
|
| 863 |
+
"loss": 0.3799,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.968,
|
| 868 |
+
"grad_norm": 4.994481563568115,
|
| 869 |
+
"learning_rate": 6.880213333333334e-06,
|
| 870 |
+
"loss": 0.3643,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.984,
|
| 875 |
+
"grad_norm": 4.072275161743164,
|
| 876 |
+
"learning_rate": 6.7735466666666676e-06,
|
| 877 |
+
"loss": 0.3716,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"grad_norm": 5.04338264465332,
|
| 883 |
+
"learning_rate": 6.66688e-06,
|
| 884 |
+
"loss": 0.3807,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.016,
|
| 889 |
+
"grad_norm": 7.1472649574279785,
|
| 890 |
+
"learning_rate": 6.560213333333334e-06,
|
| 891 |
+
"loss": 0.3362,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.032,
|
| 896 |
+
"grad_norm": 4.0547871589660645,
|
| 897 |
+
"learning_rate": 6.453546666666667e-06,
|
| 898 |
+
"loss": 0.3295,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.048,
|
| 903 |
+
"grad_norm": 4.892108917236328,
|
| 904 |
+
"learning_rate": 6.3468800000000005e-06,
|
| 905 |
+
"loss": 0.3486,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.064,
|
| 910 |
+
"grad_norm": 8.338379859924316,
|
| 911 |
+
"learning_rate": 6.240213333333334e-06,
|
| 912 |
+
"loss": 0.3398,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.08,
|
| 917 |
+
"grad_norm": 5.013506889343262,
|
| 918 |
+
"learning_rate": 6.133546666666668e-06,
|
| 919 |
+
"loss": 0.3429,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.096,
|
| 924 |
+
"grad_norm": 4.657933712005615,
|
| 925 |
+
"learning_rate": 6.02688e-06,
|
| 926 |
+
"loss": 0.3413,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.112,
|
| 931 |
+
"grad_norm": 9.017631530761719,
|
| 932 |
+
"learning_rate": 5.920213333333333e-06,
|
| 933 |
+
"loss": 0.3355,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.128,
|
| 938 |
+
"grad_norm": 6.127545356750488,
|
| 939 |
+
"learning_rate": 5.8135466666666674e-06,
|
| 940 |
+
"loss": 0.3426,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.144,
|
| 945 |
+
"grad_norm": 6.996552467346191,
|
| 946 |
+
"learning_rate": 5.70688e-06,
|
| 947 |
+
"loss": 0.3466,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.16,
|
| 952 |
+
"grad_norm": 6.633913993835449,
|
| 953 |
+
"learning_rate": 5.600213333333334e-06,
|
| 954 |
+
"loss": 0.3431,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.176,
|
| 959 |
+
"grad_norm": 5.091945648193359,
|
| 960 |
+
"learning_rate": 5.493546666666667e-06,
|
| 961 |
+
"loss": 0.3339,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.192,
|
| 966 |
+
"grad_norm": 4.924545764923096,
|
| 967 |
+
"learning_rate": 5.3868799999999995e-06,
|
| 968 |
+
"loss": 0.3346,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.208,
|
| 973 |
+
"grad_norm": 4.668349742889404,
|
| 974 |
+
"learning_rate": 5.2802133333333336e-06,
|
| 975 |
+
"loss": 0.3481,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.224,
|
| 980 |
+
"grad_norm": 5.762850284576416,
|
| 981 |
+
"learning_rate": 5.173546666666667e-06,
|
| 982 |
+
"loss": 0.3417,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.24,
|
| 987 |
+
"grad_norm": 5.485198020935059,
|
| 988 |
+
"learning_rate": 5.066880000000001e-06,
|
| 989 |
+
"loss": 0.3326,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.2560000000000002,
|
| 994 |
+
"grad_norm": 7.124167442321777,
|
| 995 |
+
"learning_rate": 4.960213333333333e-06,
|
| 996 |
+
"loss": 0.3366,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.2720000000000002,
|
| 1001 |
+
"grad_norm": 5.406363487243652,
|
| 1002 |
+
"learning_rate": 4.853546666666667e-06,
|
| 1003 |
+
"loss": 0.3466,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.288,
|
| 1008 |
+
"grad_norm": 4.88458251953125,
|
| 1009 |
+
"learning_rate": 4.7468800000000005e-06,
|
| 1010 |
+
"loss": 0.3408,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.304,
|
| 1015 |
+
"grad_norm": 6.530459880828857,
|
| 1016 |
+
"learning_rate": 4.640213333333334e-06,
|
| 1017 |
+
"loss": 0.3484,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.32,
|
| 1022 |
+
"grad_norm": 6.04323148727417,
|
| 1023 |
+
"learning_rate": 4.533546666666667e-06,
|
| 1024 |
+
"loss": 0.3332,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.336,
|
| 1029 |
+
"grad_norm": 4.244800090789795,
|
| 1030 |
+
"learning_rate": 4.42688e-06,
|
| 1031 |
+
"loss": 0.3388,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.352,
|
| 1036 |
+
"grad_norm": 5.711612224578857,
|
| 1037 |
+
"learning_rate": 4.3202133333333334e-06,
|
| 1038 |
+
"loss": 0.3275,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.368,
|
| 1043 |
+
"grad_norm": 4.669798851013184,
|
| 1044 |
+
"learning_rate": 4.213546666666667e-06,
|
| 1045 |
+
"loss": 0.342,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.384,
|
| 1050 |
+
"grad_norm": 4.899361610412598,
|
| 1051 |
+
"learning_rate": 4.106880000000001e-06,
|
| 1052 |
+
"loss": 0.3313,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.4,
|
| 1057 |
+
"grad_norm": 9.277628898620605,
|
| 1058 |
+
"learning_rate": 4.000213333333334e-06,
|
| 1059 |
+
"loss": 0.3425,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.416,
|
| 1064 |
+
"grad_norm": 5.854104518890381,
|
| 1065 |
+
"learning_rate": 3.893546666666667e-06,
|
| 1066 |
+
"loss": 0.3431,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.432,
|
| 1071 |
+
"grad_norm": 6.2259840965271,
|
| 1072 |
+
"learning_rate": 3.7868800000000004e-06,
|
| 1073 |
+
"loss": 0.3423,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.448,
|
| 1078 |
+
"grad_norm": 8.048876762390137,
|
| 1079 |
+
"learning_rate": 3.680213333333333e-06,
|
| 1080 |
+
"loss": 0.3267,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.464,
|
| 1085 |
+
"grad_norm": 6.951491832733154,
|
| 1086 |
+
"learning_rate": 3.573546666666667e-06,
|
| 1087 |
+
"loss": 0.3367,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.48,
|
| 1092 |
+
"grad_norm": 3.6338391304016113,
|
| 1093 |
+
"learning_rate": 3.46688e-06,
|
| 1094 |
+
"loss": 0.3426,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.496,
|
| 1099 |
+
"grad_norm": 4.368555545806885,
|
| 1100 |
+
"learning_rate": 3.3602133333333337e-06,
|
| 1101 |
+
"loss": 0.339,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.512,
|
| 1106 |
+
"grad_norm": 3.3475539684295654,
|
| 1107 |
+
"learning_rate": 3.253546666666667e-06,
|
| 1108 |
+
"loss": 0.3339,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.528,
|
| 1113 |
+
"grad_norm": 4.421470642089844,
|
| 1114 |
+
"learning_rate": 3.1468800000000006e-06,
|
| 1115 |
+
"loss": 0.3407,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.544,
|
| 1120 |
+
"grad_norm": 5.3636794090271,
|
| 1121 |
+
"learning_rate": 3.0402133333333334e-06,
|
| 1122 |
+
"loss": 0.3429,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.56,
|
| 1127 |
+
"grad_norm": 1.9447581768035889,
|
| 1128 |
+
"learning_rate": 2.9335466666666666e-06,
|
| 1129 |
+
"loss": 0.3391,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.576,
|
| 1134 |
+
"grad_norm": 4.480677604675293,
|
| 1135 |
+
"learning_rate": 2.8268800000000003e-06,
|
| 1136 |
+
"loss": 0.3326,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.592,
|
| 1141 |
+
"grad_norm": 6.740524768829346,
|
| 1142 |
+
"learning_rate": 2.7202133333333335e-06,
|
| 1143 |
+
"loss": 0.3332,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.608,
|
| 1148 |
+
"grad_norm": 4.42558479309082,
|
| 1149 |
+
"learning_rate": 2.613546666666667e-06,
|
| 1150 |
+
"loss": 0.3372,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.624,
|
| 1155 |
+
"grad_norm": 3.5945699214935303,
|
| 1156 |
+
"learning_rate": 2.5068800000000004e-06,
|
| 1157 |
+
"loss": 0.3341,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.64,
|
| 1162 |
+
"grad_norm": 2.3197174072265625,
|
| 1163 |
+
"learning_rate": 2.4002133333333336e-06,
|
| 1164 |
+
"loss": 0.3344,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.656,
|
| 1169 |
+
"grad_norm": 2.672572374343872,
|
| 1170 |
+
"learning_rate": 2.293546666666667e-06,
|
| 1171 |
+
"loss": 0.3456,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.672,
|
| 1176 |
+
"grad_norm": 4.4337382316589355,
|
| 1177 |
+
"learning_rate": 2.18688e-06,
|
| 1178 |
+
"loss": 0.3378,
|
| 1179 |
+
"step": 83500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.6879999999999997,
|
| 1183 |
+
"grad_norm": 4.7641425132751465,
|
| 1184 |
+
"learning_rate": 2.0802133333333337e-06,
|
| 1185 |
+
"loss": 0.3341,
|
| 1186 |
+
"step": 84000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.7039999999999997,
|
| 1190 |
+
"grad_norm": 5.17092227935791,
|
| 1191 |
+
"learning_rate": 1.973546666666667e-06,
|
| 1192 |
+
"loss": 0.3323,
|
| 1193 |
+
"step": 84500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.7199999999999998,
|
| 1197 |
+
"grad_norm": 2.958045721054077,
|
| 1198 |
+
"learning_rate": 1.8668800000000002e-06,
|
| 1199 |
+
"loss": 0.3398,
|
| 1200 |
+
"step": 85000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.7359999999999998,
|
| 1204 |
+
"grad_norm": 5.389096260070801,
|
| 1205 |
+
"learning_rate": 1.7602133333333336e-06,
|
| 1206 |
+
"loss": 0.3365,
|
| 1207 |
+
"step": 85500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.752,
|
| 1211 |
+
"grad_norm": 4.923801422119141,
|
| 1212 |
+
"learning_rate": 1.6535466666666668e-06,
|
| 1213 |
+
"loss": 0.3385,
|
| 1214 |
+
"step": 86000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.768,
|
| 1218 |
+
"grad_norm": 6.432462692260742,
|
| 1219 |
+
"learning_rate": 1.54688e-06,
|
| 1220 |
+
"loss": 0.337,
|
| 1221 |
+
"step": 86500
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.784,
|
| 1225 |
+
"grad_norm": 8.82355785369873,
|
| 1226 |
+
"learning_rate": 1.4402133333333335e-06,
|
| 1227 |
+
"loss": 0.3425,
|
| 1228 |
+
"step": 87000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.8,
|
| 1232 |
+
"grad_norm": 5.106661796569824,
|
| 1233 |
+
"learning_rate": 1.333546666666667e-06,
|
| 1234 |
+
"loss": 0.3291,
|
| 1235 |
+
"step": 87500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.816,
|
| 1239 |
+
"grad_norm": 3.596604824066162,
|
| 1240 |
+
"learning_rate": 1.2268800000000001e-06,
|
| 1241 |
+
"loss": 0.3382,
|
| 1242 |
+
"step": 88000
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.832,
|
| 1246 |
+
"grad_norm": 2.9298431873321533,
|
| 1247 |
+
"learning_rate": 1.1202133333333334e-06,
|
| 1248 |
+
"loss": 0.3347,
|
| 1249 |
+
"step": 88500
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.848,
|
| 1253 |
+
"grad_norm": 4.9863762855529785,
|
| 1254 |
+
"learning_rate": 1.0135466666666668e-06,
|
| 1255 |
+
"loss": 0.3367,
|
| 1256 |
+
"step": 89000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.864,
|
| 1260 |
+
"grad_norm": 4.462283611297607,
|
| 1261 |
+
"learning_rate": 9.068800000000001e-07,
|
| 1262 |
+
"loss": 0.3343,
|
| 1263 |
+
"step": 89500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.88,
|
| 1267 |
+
"grad_norm": 7.131375312805176,
|
| 1268 |
+
"learning_rate": 8.002133333333334e-07,
|
| 1269 |
+
"loss": 0.3313,
|
| 1270 |
+
"step": 90000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.896,
|
| 1274 |
+
"grad_norm": 3.781033992767334,
|
| 1275 |
+
"learning_rate": 6.935466666666667e-07,
|
| 1276 |
+
"loss": 0.3434,
|
| 1277 |
+
"step": 90500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.912,
|
| 1281 |
+
"grad_norm": 6.145064353942871,
|
| 1282 |
+
"learning_rate": 5.8688e-07,
|
| 1283 |
+
"loss": 0.3361,
|
| 1284 |
+
"step": 91000
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.928,
|
| 1288 |
+
"grad_norm": 3.502265214920044,
|
| 1289 |
+
"learning_rate": 4.802133333333334e-07,
|
| 1290 |
+
"loss": 0.3313,
|
| 1291 |
+
"step": 91500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.944,
|
| 1295 |
+
"grad_norm": 4.486534118652344,
|
| 1296 |
+
"learning_rate": 3.735466666666667e-07,
|
| 1297 |
+
"loss": 0.3324,
|
| 1298 |
+
"step": 92000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.96,
|
| 1302 |
+
"grad_norm": 6.918281078338623,
|
| 1303 |
+
"learning_rate": 2.6688e-07,
|
| 1304 |
+
"loss": 0.3373,
|
| 1305 |
+
"step": 92500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.976,
|
| 1309 |
+
"grad_norm": 6.636358737945557,
|
| 1310 |
+
"learning_rate": 1.6021333333333332e-07,
|
| 1311 |
+
"loss": 0.3408,
|
| 1312 |
+
"step": 93000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.992,
|
| 1316 |
+
"grad_norm": 4.87343692779541,
|
| 1317 |
+
"learning_rate": 5.354666666666667e-08,
|
| 1318 |
+
"loss": 0.3422,
|
| 1319 |
+
"step": 93500
|
| 1320 |
+
}
|
| 1321 |
+
],
|
| 1322 |
+
"logging_steps": 500,
|
| 1323 |
+
"max_steps": 93750,
|
| 1324 |
+
"num_input_tokens_seen": 0,
|
| 1325 |
+
"num_train_epochs": 3,
|
| 1326 |
+
"save_steps": 500,
|
| 1327 |
+
"stateful_callbacks": {
|
| 1328 |
+
"TrainerControl": {
|
| 1329 |
+
"args": {
|
| 1330 |
+
"should_epoch_stop": false,
|
| 1331 |
+
"should_evaluate": false,
|
| 1332 |
+
"should_log": false,
|
| 1333 |
+
"should_save": true,
|
| 1334 |
+
"should_training_stop": true
|
| 1335 |
+
},
|
| 1336 |
+
"attributes": {}
|
| 1337 |
+
}
|
| 1338 |
+
},
|
| 1339 |
+
"total_flos": 1.4345167767525408e+17,
|
| 1340 |
+
"train_batch_size": 32,
|
| 1341 |
+
"trial_name": null,
|
| 1342 |
+
"trial_params": null
|
| 1343 |
+
}
|
checkpoint-93750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6205a4827a1926df97c9c45b264c999d8285f1eff2584a51171fad6052ad5c50
|
| 3 |
+
size 5304
|
checkpoint-93750/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3,
|
| 23 |
+
"LABEL_4": 4
|
| 24 |
+
},
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "distilbert",
|
| 27 |
+
"n_heads": 12,
|
| 28 |
+
"n_layers": 6,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qa_dropout": 0.1,
|
| 32 |
+
"seq_classif_dropout": 0.2,
|
| 33 |
+
"sinusoidal_pos_embds": false,
|
| 34 |
+
"tie_weights_": true,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.52.3",
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f43eae07f9dac8a98c715861ba2f9dc02cd4b533afcb5e4d27ce1d395f3cad97
|
| 3 |
+
size 267841796
|
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 sha256:6205a4827a1926df97c9c45b264c999d8285f1eff2584a51171fad6052ad5c50
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|