Upload 11 files
Browse files- config.json +24 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- trainer_state.json +3265 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"transformers_version": "4.57.0",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f7f4cf199c92a11129d96465c2b9d342208b758edc23a3fa7e7044cab17ace5
|
| 3 |
+
size 267832560
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d315b795ca97f699886bdd0ebe44307ee8805739c95dc717990b14d714d30a1
|
| 3 |
+
size 535729227
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cca0542a3dd8c5da6359fc27739343e8934d12717a18e66a002bac55435adaf
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a31715cf6d17f6d0be7f18c25be399f2ad6e1f7648c8c6751c0631f24d049b
|
| 3 |
+
size 1465
|
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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 20000,
|
| 3 |
+
"best_metric": 0.04931970685720444,
|
| 4 |
+
"best_model_checkpoint": "distilbert-base-uncased-name-classifier\\checkpoint-20000",
|
| 5 |
+
"epoch": 0.2199886583625022,
|
| 6 |
+
"eval_steps": 5000,
|
| 7 |
+
"global_step": 45000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0004888636852500049,
|
| 14 |
+
"grad_norm": 2.0584447383880615,
|
| 15 |
+
"learning_rate": 4.997580124758013e-05,
|
| 16 |
+
"loss": 0.1872,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0009777273705000099,
|
| 21 |
+
"grad_norm": 0.7082653045654297,
|
| 22 |
+
"learning_rate": 4.9951358063317626e-05,
|
| 23 |
+
"loss": 0.1214,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0014665910557500146,
|
| 28 |
+
"grad_norm": 5.331765174865723,
|
| 29 |
+
"learning_rate": 4.9926914879055126e-05,
|
| 30 |
+
"loss": 0.0955,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0019554547410000197,
|
| 35 |
+
"grad_norm": 0.34082797169685364,
|
| 36 |
+
"learning_rate": 4.9902471694792625e-05,
|
| 37 |
+
"loss": 0.1009,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0024443184262500244,
|
| 42 |
+
"grad_norm": 0.9952702522277832,
|
| 43 |
+
"learning_rate": 4.987802851053013e-05,
|
| 44 |
+
"loss": 0.0882,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.002933182111500029,
|
| 49 |
+
"grad_norm": 6.666719913482666,
|
| 50 |
+
"learning_rate": 4.9853585326267624e-05,
|
| 51 |
+
"loss": 0.0726,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0034220457967500343,
|
| 56 |
+
"grad_norm": 0.7815108299255371,
|
| 57 |
+
"learning_rate": 4.982914214200512e-05,
|
| 58 |
+
"loss": 0.0898,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0039109094820000394,
|
| 63 |
+
"grad_norm": 0.13366815447807312,
|
| 64 |
+
"learning_rate": 4.980469895774262e-05,
|
| 65 |
+
"loss": 0.0733,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.004399773167250044,
|
| 70 |
+
"grad_norm": 1.9088977575302124,
|
| 71 |
+
"learning_rate": 4.978025577348013e-05,
|
| 72 |
+
"loss": 0.0948,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.004888636852500049,
|
| 77 |
+
"grad_norm": 2.5377371311187744,
|
| 78 |
+
"learning_rate": 4.975581258921763e-05,
|
| 79 |
+
"loss": 0.0688,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.005377500537750054,
|
| 84 |
+
"grad_norm": 1.6006317138671875,
|
| 85 |
+
"learning_rate": 4.973136940495513e-05,
|
| 86 |
+
"loss": 0.0728,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.005866364223000058,
|
| 91 |
+
"grad_norm": 2.8443217277526855,
|
| 92 |
+
"learning_rate": 4.9706926220692626e-05,
|
| 93 |
+
"loss": 0.0623,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0063552279082500635,
|
| 98 |
+
"grad_norm": 3.446730613708496,
|
| 99 |
+
"learning_rate": 4.968248303643012e-05,
|
| 100 |
+
"loss": 0.063,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.006844091593500069,
|
| 105 |
+
"grad_norm": 1.061936855316162,
|
| 106 |
+
"learning_rate": 4.9658039852167625e-05,
|
| 107 |
+
"loss": 0.0722,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.007332955278750074,
|
| 112 |
+
"grad_norm": 2.6640610694885254,
|
| 113 |
+
"learning_rate": 4.9633596667905124e-05,
|
| 114 |
+
"loss": 0.0711,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.007821818964000079,
|
| 119 |
+
"grad_norm": 0.17981141805648804,
|
| 120 |
+
"learning_rate": 4.9609153483642624e-05,
|
| 121 |
+
"loss": 0.0775,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.008310682649250082,
|
| 126 |
+
"grad_norm": 1.0370889902114868,
|
| 127 |
+
"learning_rate": 4.958471029938012e-05,
|
| 128 |
+
"loss": 0.0639,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.008799546334500087,
|
| 133 |
+
"grad_norm": 0.2923545241355896,
|
| 134 |
+
"learning_rate": 4.956026711511762e-05,
|
| 135 |
+
"loss": 0.0729,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.009288410019750093,
|
| 140 |
+
"grad_norm": 0.17301051318645477,
|
| 141 |
+
"learning_rate": 4.953582393085512e-05,
|
| 142 |
+
"loss": 0.0722,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.009777273705000098,
|
| 147 |
+
"grad_norm": 2.0286195278167725,
|
| 148 |
+
"learning_rate": 4.951138074659262e-05,
|
| 149 |
+
"loss": 0.082,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.010266137390250103,
|
| 154 |
+
"grad_norm": 0.19177016615867615,
|
| 155 |
+
"learning_rate": 4.948693756233012e-05,
|
| 156 |
+
"loss": 0.0627,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.010755001075500108,
|
| 161 |
+
"grad_norm": 2.407954692840576,
|
| 162 |
+
"learning_rate": 4.946249437806762e-05,
|
| 163 |
+
"loss": 0.066,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.011243864760750113,
|
| 168 |
+
"grad_norm": 0.1898936778306961,
|
| 169 |
+
"learning_rate": 4.9438051193805126e-05,
|
| 170 |
+
"loss": 0.0547,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.011732728446000117,
|
| 175 |
+
"grad_norm": 0.19650809466838837,
|
| 176 |
+
"learning_rate": 4.9413608009542625e-05,
|
| 177 |
+
"loss": 0.0714,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.012221592131250122,
|
| 182 |
+
"grad_norm": 1.117080807685852,
|
| 183 |
+
"learning_rate": 4.938916482528012e-05,
|
| 184 |
+
"loss": 0.0727,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.012710455816500127,
|
| 189 |
+
"grad_norm": 2.4936904907226562,
|
| 190 |
+
"learning_rate": 4.936472164101762e-05,
|
| 191 |
+
"loss": 0.0737,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.013199319501750132,
|
| 196 |
+
"grad_norm": 2.6669225692749023,
|
| 197 |
+
"learning_rate": 4.934027845675512e-05,
|
| 198 |
+
"loss": 0.0643,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.013688183187000137,
|
| 203 |
+
"grad_norm": 0.05559728294610977,
|
| 204 |
+
"learning_rate": 4.931583527249262e-05,
|
| 205 |
+
"loss": 0.07,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.014177046872250142,
|
| 210 |
+
"grad_norm": 0.14648708701133728,
|
| 211 |
+
"learning_rate": 4.929139208823012e-05,
|
| 212 |
+
"loss": 0.0549,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.014665910557500147,
|
| 217 |
+
"grad_norm": 0.7838676571846008,
|
| 218 |
+
"learning_rate": 4.926694890396762e-05,
|
| 219 |
+
"loss": 0.0741,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.015154774242750151,
|
| 224 |
+
"grad_norm": 2.6852540969848633,
|
| 225 |
+
"learning_rate": 4.924250571970512e-05,
|
| 226 |
+
"loss": 0.0622,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.015643637928000158,
|
| 231 |
+
"grad_norm": 3.0528738498687744,
|
| 232 |
+
"learning_rate": 4.921806253544262e-05,
|
| 233 |
+
"loss": 0.067,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.016132501613250163,
|
| 238 |
+
"grad_norm": 1.3152064085006714,
|
| 239 |
+
"learning_rate": 4.919361935118012e-05,
|
| 240 |
+
"loss": 0.0643,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.016621365298500165,
|
| 245 |
+
"grad_norm": 0.12894883751869202,
|
| 246 |
+
"learning_rate": 4.916917616691762e-05,
|
| 247 |
+
"loss": 0.0613,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.01711022898375017,
|
| 252 |
+
"grad_norm": 0.23248863220214844,
|
| 253 |
+
"learning_rate": 4.914473298265512e-05,
|
| 254 |
+
"loss": 0.0548,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.017599092669000175,
|
| 259 |
+
"grad_norm": 0.23466159403324127,
|
| 260 |
+
"learning_rate": 4.912028979839262e-05,
|
| 261 |
+
"loss": 0.0588,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.01808795635425018,
|
| 266 |
+
"grad_norm": 8.188297271728516,
|
| 267 |
+
"learning_rate": 4.909584661413012e-05,
|
| 268 |
+
"loss": 0.0678,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.018576820039500185,
|
| 273 |
+
"grad_norm": 0.4742072522640228,
|
| 274 |
+
"learning_rate": 4.9071403429867615e-05,
|
| 275 |
+
"loss": 0.0693,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.01906568372475019,
|
| 280 |
+
"grad_norm": 0.1966550648212433,
|
| 281 |
+
"learning_rate": 4.9046960245605115e-05,
|
| 282 |
+
"loss": 0.0721,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.019554547410000196,
|
| 287 |
+
"grad_norm": 1.3308151960372925,
|
| 288 |
+
"learning_rate": 4.9022517061342614e-05,
|
| 289 |
+
"loss": 0.055,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.0200434110952502,
|
| 294 |
+
"grad_norm": 0.47814884781837463,
|
| 295 |
+
"learning_rate": 4.899807387708012e-05,
|
| 296 |
+
"loss": 0.0679,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.020532274780500206,
|
| 301 |
+
"grad_norm": 3.693378448486328,
|
| 302 |
+
"learning_rate": 4.897363069281762e-05,
|
| 303 |
+
"loss": 0.0642,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.02102113846575021,
|
| 308 |
+
"grad_norm": 0.4725653827190399,
|
| 309 |
+
"learning_rate": 4.894918750855512e-05,
|
| 310 |
+
"loss": 0.0663,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.021510002151000216,
|
| 315 |
+
"grad_norm": 0.5118640661239624,
|
| 316 |
+
"learning_rate": 4.892474432429262e-05,
|
| 317 |
+
"loss": 0.0601,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.02199886583625022,
|
| 322 |
+
"grad_norm": 0.11996106803417206,
|
| 323 |
+
"learning_rate": 4.890030114003011e-05,
|
| 324 |
+
"loss": 0.0645,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.022487729521500226,
|
| 329 |
+
"grad_norm": 0.23428364098072052,
|
| 330 |
+
"learning_rate": 4.887585795576762e-05,
|
| 331 |
+
"loss": 0.0736,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.022976593206750228,
|
| 336 |
+
"grad_norm": 0.7072849273681641,
|
| 337 |
+
"learning_rate": 4.8851414771505116e-05,
|
| 338 |
+
"loss": 0.0765,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.023465456892000233,
|
| 343 |
+
"grad_norm": 0.7515387535095215,
|
| 344 |
+
"learning_rate": 4.8826971587242615e-05,
|
| 345 |
+
"loss": 0.0719,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.02395432057725024,
|
| 350 |
+
"grad_norm": 0.3805476725101471,
|
| 351 |
+
"learning_rate": 4.8802528402980115e-05,
|
| 352 |
+
"loss": 0.0639,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.024443184262500244,
|
| 357 |
+
"grad_norm": 0.07049237191677094,
|
| 358 |
+
"learning_rate": 4.8778085218717614e-05,
|
| 359 |
+
"loss": 0.0689,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.024443184262500244,
|
| 364 |
+
"eval_accuracy": 0.9836947330646725,
|
| 365 |
+
"eval_loss": 0.06599895656108856,
|
| 366 |
+
"eval_runtime": 87.3804,
|
| 367 |
+
"eval_samples_per_second": 8323.505,
|
| 368 |
+
"eval_steps_per_second": 260.116,
|
| 369 |
+
"step": 5000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.02493204794775025,
|
| 373 |
+
"grad_norm": 0.29544833302497864,
|
| 374 |
+
"learning_rate": 4.875364203445511e-05,
|
| 375 |
+
"loss": 0.0665,
|
| 376 |
+
"step": 5100
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.025420911633000254,
|
| 380 |
+
"grad_norm": 0.271820992231369,
|
| 381 |
+
"learning_rate": 4.872919885019261e-05,
|
| 382 |
+
"loss": 0.0658,
|
| 383 |
+
"step": 5200
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.02590977531825026,
|
| 387 |
+
"grad_norm": 1.5426307916641235,
|
| 388 |
+
"learning_rate": 4.870475566593011e-05,
|
| 389 |
+
"loss": 0.0534,
|
| 390 |
+
"step": 5300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.026398639003500264,
|
| 394 |
+
"grad_norm": 2.1278717517852783,
|
| 395 |
+
"learning_rate": 4.868031248166761e-05,
|
| 396 |
+
"loss": 0.0646,
|
| 397 |
+
"step": 5400
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.02688750268875027,
|
| 401 |
+
"grad_norm": 0.08083345741033554,
|
| 402 |
+
"learning_rate": 4.865586929740512e-05,
|
| 403 |
+
"loss": 0.0581,
|
| 404 |
+
"step": 5500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.027376366374000274,
|
| 408 |
+
"grad_norm": 0.15616372227668762,
|
| 409 |
+
"learning_rate": 4.863142611314262e-05,
|
| 410 |
+
"loss": 0.0616,
|
| 411 |
+
"step": 5600
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.02786523005925028,
|
| 415 |
+
"grad_norm": 0.2824023962020874,
|
| 416 |
+
"learning_rate": 4.860698292888011e-05,
|
| 417 |
+
"loss": 0.0617,
|
| 418 |
+
"step": 5700
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.028354093744500285,
|
| 422 |
+
"grad_norm": 0.8543683886528015,
|
| 423 |
+
"learning_rate": 4.858253974461761e-05,
|
| 424 |
+
"loss": 0.0636,
|
| 425 |
+
"step": 5800
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.02884295742975029,
|
| 429 |
+
"grad_norm": 1.1067934036254883,
|
| 430 |
+
"learning_rate": 4.8558096560355115e-05,
|
| 431 |
+
"loss": 0.0601,
|
| 432 |
+
"step": 5900
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.029331821115000295,
|
| 436 |
+
"grad_norm": 0.2358483076095581,
|
| 437 |
+
"learning_rate": 4.8533653376092614e-05,
|
| 438 |
+
"loss": 0.0503,
|
| 439 |
+
"step": 6000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.029820684800250297,
|
| 443 |
+
"grad_norm": 0.5788276195526123,
|
| 444 |
+
"learning_rate": 4.850921019183011e-05,
|
| 445 |
+
"loss": 0.0624,
|
| 446 |
+
"step": 6100
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.030309548485500302,
|
| 450 |
+
"grad_norm": 0.11598861217498779,
|
| 451 |
+
"learning_rate": 4.848476700756761e-05,
|
| 452 |
+
"loss": 0.0577,
|
| 453 |
+
"step": 6200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.030798412170750307,
|
| 457 |
+
"grad_norm": 0.26985904574394226,
|
| 458 |
+
"learning_rate": 4.846032382330511e-05,
|
| 459 |
+
"loss": 0.0634,
|
| 460 |
+
"step": 6300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.031287275856000316,
|
| 464 |
+
"grad_norm": 1.756959319114685,
|
| 465 |
+
"learning_rate": 4.843588063904261e-05,
|
| 466 |
+
"loss": 0.0699,
|
| 467 |
+
"step": 6400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.03177613954125032,
|
| 471 |
+
"grad_norm": 0.1870100051164627,
|
| 472 |
+
"learning_rate": 4.841143745478011e-05,
|
| 473 |
+
"loss": 0.0533,
|
| 474 |
+
"step": 6500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.032265003226500326,
|
| 478 |
+
"grad_norm": 5.463848114013672,
|
| 479 |
+
"learning_rate": 4.838699427051761e-05,
|
| 480 |
+
"loss": 0.0533,
|
| 481 |
+
"step": 6600
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.03275386691175033,
|
| 485 |
+
"grad_norm": 0.15776309370994568,
|
| 486 |
+
"learning_rate": 4.836255108625511e-05,
|
| 487 |
+
"loss": 0.0532,
|
| 488 |
+
"step": 6700
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.03324273059700033,
|
| 492 |
+
"grad_norm": 3.4973597526550293,
|
| 493 |
+
"learning_rate": 4.8338107901992615e-05,
|
| 494 |
+
"loss": 0.0727,
|
| 495 |
+
"step": 6800
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.03373159428225034,
|
| 499 |
+
"grad_norm": 0.1563042551279068,
|
| 500 |
+
"learning_rate": 4.8313664717730115e-05,
|
| 501 |
+
"loss": 0.0663,
|
| 502 |
+
"step": 6900
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.03422045796750034,
|
| 506 |
+
"grad_norm": 0.028401503339409828,
|
| 507 |
+
"learning_rate": 4.828922153346761e-05,
|
| 508 |
+
"loss": 0.0494,
|
| 509 |
+
"step": 7000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.03470932165275035,
|
| 513 |
+
"grad_norm": 0.3135679066181183,
|
| 514 |
+
"learning_rate": 4.8264778349205107e-05,
|
| 515 |
+
"loss": 0.0595,
|
| 516 |
+
"step": 7100
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.03519818533800035,
|
| 520 |
+
"grad_norm": 0.20592054724693298,
|
| 521 |
+
"learning_rate": 4.8240335164942606e-05,
|
| 522 |
+
"loss": 0.0642,
|
| 523 |
+
"step": 7200
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.03568704902325036,
|
| 527 |
+
"grad_norm": 0.5337781310081482,
|
| 528 |
+
"learning_rate": 4.821589198068011e-05,
|
| 529 |
+
"loss": 0.0748,
|
| 530 |
+
"step": 7300
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.03617591270850036,
|
| 534 |
+
"grad_norm": 1.6454081535339355,
|
| 535 |
+
"learning_rate": 4.819144879641761e-05,
|
| 536 |
+
"loss": 0.0749,
|
| 537 |
+
"step": 7400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.03666477639375037,
|
| 541 |
+
"grad_norm": 1.9347577095031738,
|
| 542 |
+
"learning_rate": 4.816700561215511e-05,
|
| 543 |
+
"loss": 0.0634,
|
| 544 |
+
"step": 7500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.03715364007900037,
|
| 548 |
+
"grad_norm": 11.990884780883789,
|
| 549 |
+
"learning_rate": 4.814256242789261e-05,
|
| 550 |
+
"loss": 0.0599,
|
| 551 |
+
"step": 7600
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.03764250376425038,
|
| 555 |
+
"grad_norm": 1.3684093952178955,
|
| 556 |
+
"learning_rate": 4.811811924363011e-05,
|
| 557 |
+
"loss": 0.0663,
|
| 558 |
+
"step": 7700
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.03813136744950038,
|
| 562 |
+
"grad_norm": 0.09122494608163834,
|
| 563 |
+
"learning_rate": 4.809367605936761e-05,
|
| 564 |
+
"loss": 0.0497,
|
| 565 |
+
"step": 7800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.03862023113475039,
|
| 569 |
+
"grad_norm": 0.16003599762916565,
|
| 570 |
+
"learning_rate": 4.806923287510511e-05,
|
| 571 |
+
"loss": 0.0629,
|
| 572 |
+
"step": 7900
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.03910909482000039,
|
| 576 |
+
"grad_norm": 0.9405515789985657,
|
| 577 |
+
"learning_rate": 4.804478969084261e-05,
|
| 578 |
+
"loss": 0.0522,
|
| 579 |
+
"step": 8000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.03959795850525039,
|
| 583 |
+
"grad_norm": 0.39271441102027893,
|
| 584 |
+
"learning_rate": 4.8020346506580107e-05,
|
| 585 |
+
"loss": 0.0559,
|
| 586 |
+
"step": 8100
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.0400868221905004,
|
| 590 |
+
"grad_norm": 0.5967023968696594,
|
| 591 |
+
"learning_rate": 4.7995903322317606e-05,
|
| 592 |
+
"loss": 0.0618,
|
| 593 |
+
"step": 8200
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.0405756858757504,
|
| 597 |
+
"grad_norm": 0.174581840634346,
|
| 598 |
+
"learning_rate": 4.7971460138055105e-05,
|
| 599 |
+
"loss": 0.0539,
|
| 600 |
+
"step": 8300
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.04106454956100041,
|
| 604 |
+
"grad_norm": 0.10510542243719101,
|
| 605 |
+
"learning_rate": 4.7947016953792604e-05,
|
| 606 |
+
"loss": 0.0663,
|
| 607 |
+
"step": 8400
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.04155341324625041,
|
| 611 |
+
"grad_norm": 0.6411457061767578,
|
| 612 |
+
"learning_rate": 4.7922573769530104e-05,
|
| 613 |
+
"loss": 0.0403,
|
| 614 |
+
"step": 8500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.04204227693150042,
|
| 618 |
+
"grad_norm": 1.2521724700927734,
|
| 619 |
+
"learning_rate": 4.789813058526761e-05,
|
| 620 |
+
"loss": 0.0741,
|
| 621 |
+
"step": 8600
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.042531140616750424,
|
| 625 |
+
"grad_norm": 1.2106397151947021,
|
| 626 |
+
"learning_rate": 4.787368740100511e-05,
|
| 627 |
+
"loss": 0.0584,
|
| 628 |
+
"step": 8700
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.04302000430200043,
|
| 632 |
+
"grad_norm": 0.7551843523979187,
|
| 633 |
+
"learning_rate": 4.784924421674261e-05,
|
| 634 |
+
"loss": 0.0528,
|
| 635 |
+
"step": 8800
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.043508867987250434,
|
| 639 |
+
"grad_norm": 0.21862377226352692,
|
| 640 |
+
"learning_rate": 4.78248010324801e-05,
|
| 641 |
+
"loss": 0.0593,
|
| 642 |
+
"step": 8900
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.04399773167250044,
|
| 646 |
+
"grad_norm": 0.12667258083820343,
|
| 647 |
+
"learning_rate": 4.78003578482176e-05,
|
| 648 |
+
"loss": 0.0576,
|
| 649 |
+
"step": 9000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.044486595357750444,
|
| 653 |
+
"grad_norm": 0.7162678837776184,
|
| 654 |
+
"learning_rate": 4.7775914663955106e-05,
|
| 655 |
+
"loss": 0.0564,
|
| 656 |
+
"step": 9100
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.04497545904300045,
|
| 660 |
+
"grad_norm": 0.18503494560718536,
|
| 661 |
+
"learning_rate": 4.7751471479692606e-05,
|
| 662 |
+
"loss": 0.0526,
|
| 663 |
+
"step": 9200
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.045464322728250454,
|
| 667 |
+
"grad_norm": 0.13932786881923676,
|
| 668 |
+
"learning_rate": 4.7727028295430105e-05,
|
| 669 |
+
"loss": 0.058,
|
| 670 |
+
"step": 9300
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.045953186413500456,
|
| 674 |
+
"grad_norm": 0.14639222621917725,
|
| 675 |
+
"learning_rate": 4.7702585111167604e-05,
|
| 676 |
+
"loss": 0.0665,
|
| 677 |
+
"step": 9400
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.046442050098750465,
|
| 681 |
+
"grad_norm": 0.9166637659072876,
|
| 682 |
+
"learning_rate": 4.7678141926905104e-05,
|
| 683 |
+
"loss": 0.0457,
|
| 684 |
+
"step": 9500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.046930913784000466,
|
| 688 |
+
"grad_norm": 0.08465907722711563,
|
| 689 |
+
"learning_rate": 4.76536987426426e-05,
|
| 690 |
+
"loss": 0.0603,
|
| 691 |
+
"step": 9600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.047419777469250475,
|
| 695 |
+
"grad_norm": 0.9469019770622253,
|
| 696 |
+
"learning_rate": 4.76292555583801e-05,
|
| 697 |
+
"loss": 0.0552,
|
| 698 |
+
"step": 9700
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.04790864115450048,
|
| 702 |
+
"grad_norm": 0.1213444396853447,
|
| 703 |
+
"learning_rate": 4.76048123741176e-05,
|
| 704 |
+
"loss": 0.06,
|
| 705 |
+
"step": 9800
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.048397504839750485,
|
| 709 |
+
"grad_norm": 1.072907567024231,
|
| 710 |
+
"learning_rate": 4.75803691898551e-05,
|
| 711 |
+
"loss": 0.0562,
|
| 712 |
+
"step": 9900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.04888636852500049,
|
| 716 |
+
"grad_norm": 0.14865364134311676,
|
| 717 |
+
"learning_rate": 4.755592600559261e-05,
|
| 718 |
+
"loss": 0.0499,
|
| 719 |
+
"step": 10000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.04888636852500049,
|
| 723 |
+
"eval_accuracy": 0.9846475579222643,
|
| 724 |
+
"eval_loss": 0.05621802434325218,
|
| 725 |
+
"eval_runtime": 87.8291,
|
| 726 |
+
"eval_samples_per_second": 8280.982,
|
| 727 |
+
"eval_steps_per_second": 258.787,
|
| 728 |
+
"step": 10000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.049375232210250496,
|
| 732 |
+
"grad_norm": 3.8485326766967773,
|
| 733 |
+
"learning_rate": 4.7531482821330106e-05,
|
| 734 |
+
"loss": 0.0526,
|
| 735 |
+
"step": 10100
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.0498640958955005,
|
| 739 |
+
"grad_norm": 0.6063100695610046,
|
| 740 |
+
"learning_rate": 4.75070396370676e-05,
|
| 741 |
+
"loss": 0.0617,
|
| 742 |
+
"step": 10200
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.050352959580750506,
|
| 746 |
+
"grad_norm": 0.09689105302095413,
|
| 747 |
+
"learning_rate": 4.74825964528051e-05,
|
| 748 |
+
"loss": 0.0628,
|
| 749 |
+
"step": 10300
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.05084182326600051,
|
| 753 |
+
"grad_norm": 0.621361255645752,
|
| 754 |
+
"learning_rate": 4.7458153268542604e-05,
|
| 755 |
+
"loss": 0.0669,
|
| 756 |
+
"step": 10400
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.051330686951250516,
|
| 760 |
+
"grad_norm": 10.222880363464355,
|
| 761 |
+
"learning_rate": 4.7433710084280104e-05,
|
| 762 |
+
"loss": 0.0615,
|
| 763 |
+
"step": 10500
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.05181955063650052,
|
| 767 |
+
"grad_norm": 0.3349328339099884,
|
| 768 |
+
"learning_rate": 4.74092669000176e-05,
|
| 769 |
+
"loss": 0.0563,
|
| 770 |
+
"step": 10600
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.052308414321750527,
|
| 774 |
+
"grad_norm": 0.5585213303565979,
|
| 775 |
+
"learning_rate": 4.73848237157551e-05,
|
| 776 |
+
"loss": 0.0528,
|
| 777 |
+
"step": 10700
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.05279727800700053,
|
| 781 |
+
"grad_norm": 5.204141139984131,
|
| 782 |
+
"learning_rate": 4.73603805314926e-05,
|
| 783 |
+
"loss": 0.0604,
|
| 784 |
+
"step": 10800
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.05328614169225053,
|
| 788 |
+
"grad_norm": 0.14890030026435852,
|
| 789 |
+
"learning_rate": 4.73359373472301e-05,
|
| 790 |
+
"loss": 0.0491,
|
| 791 |
+
"step": 10900
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.05377500537750054,
|
| 795 |
+
"grad_norm": 2.608534336090088,
|
| 796 |
+
"learning_rate": 4.73114941629676e-05,
|
| 797 |
+
"loss": 0.0561,
|
| 798 |
+
"step": 11000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.05426386906275054,
|
| 802 |
+
"grad_norm": 0.7208146452903748,
|
| 803 |
+
"learning_rate": 4.72870509787051e-05,
|
| 804 |
+
"loss": 0.0632,
|
| 805 |
+
"step": 11100
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.05475273274800055,
|
| 809 |
+
"grad_norm": 0.3688182830810547,
|
| 810 |
+
"learning_rate": 4.72626077944426e-05,
|
| 811 |
+
"loss": 0.053,
|
| 812 |
+
"step": 11200
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.05524159643325055,
|
| 816 |
+
"grad_norm": 0.1328779011964798,
|
| 817 |
+
"learning_rate": 4.7238164610180105e-05,
|
| 818 |
+
"loss": 0.0467,
|
| 819 |
+
"step": 11300
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.05573046011850056,
|
| 823 |
+
"grad_norm": 0.1506895273923874,
|
| 824 |
+
"learning_rate": 4.72137214259176e-05,
|
| 825 |
+
"loss": 0.0559,
|
| 826 |
+
"step": 11400
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.05621932380375056,
|
| 830 |
+
"grad_norm": 0.2648990750312805,
|
| 831 |
+
"learning_rate": 4.71892782416551e-05,
|
| 832 |
+
"loss": 0.0628,
|
| 833 |
+
"step": 11500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.05670818748900057,
|
| 837 |
+
"grad_norm": 0.11509310454130173,
|
| 838 |
+
"learning_rate": 4.7164835057392596e-05,
|
| 839 |
+
"loss": 0.0553,
|
| 840 |
+
"step": 11600
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.05719705117425057,
|
| 844 |
+
"grad_norm": 0.2020263820886612,
|
| 845 |
+
"learning_rate": 4.7140391873130096e-05,
|
| 846 |
+
"loss": 0.0618,
|
| 847 |
+
"step": 11700
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.05768591485950058,
|
| 851 |
+
"grad_norm": 0.20277683436870575,
|
| 852 |
+
"learning_rate": 4.71159486888676e-05,
|
| 853 |
+
"loss": 0.0597,
|
| 854 |
+
"step": 11800
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.05817477854475058,
|
| 858 |
+
"grad_norm": 0.07775338739156723,
|
| 859 |
+
"learning_rate": 4.70915055046051e-05,
|
| 860 |
+
"loss": 0.0438,
|
| 861 |
+
"step": 11900
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.05866364223000059,
|
| 865 |
+
"grad_norm": 0.2883436381816864,
|
| 866 |
+
"learning_rate": 4.70670623203426e-05,
|
| 867 |
+
"loss": 0.0698,
|
| 868 |
+
"step": 12000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.05915250591525059,
|
| 872 |
+
"grad_norm": 0.23519305884838104,
|
| 873 |
+
"learning_rate": 4.704261913608009e-05,
|
| 874 |
+
"loss": 0.0512,
|
| 875 |
+
"step": 12100
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.05964136960050059,
|
| 879 |
+
"grad_norm": 1.4591866731643677,
|
| 880 |
+
"learning_rate": 4.70181759518176e-05,
|
| 881 |
+
"loss": 0.062,
|
| 882 |
+
"step": 12200
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.0601302332857506,
|
| 886 |
+
"grad_norm": 1.140668511390686,
|
| 887 |
+
"learning_rate": 4.69937327675551e-05,
|
| 888 |
+
"loss": 0.071,
|
| 889 |
+
"step": 12300
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.060619096971000604,
|
| 893 |
+
"grad_norm": 0.09165971726179123,
|
| 894 |
+
"learning_rate": 4.69692895832926e-05,
|
| 895 |
+
"loss": 0.0562,
|
| 896 |
+
"step": 12400
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.06110796065625061,
|
| 900 |
+
"grad_norm": 0.792263925075531,
|
| 901 |
+
"learning_rate": 4.69448463990301e-05,
|
| 902 |
+
"loss": 0.0648,
|
| 903 |
+
"step": 12500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.061596824341500614,
|
| 907 |
+
"grad_norm": 1.3877601623535156,
|
| 908 |
+
"learning_rate": 4.6920403214767596e-05,
|
| 909 |
+
"loss": 0.0608,
|
| 910 |
+
"step": 12600
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.06208568802675062,
|
| 914 |
+
"grad_norm": 0.7223020195960999,
|
| 915 |
+
"learning_rate": 4.6895960030505096e-05,
|
| 916 |
+
"loss": 0.061,
|
| 917 |
+
"step": 12700
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.06257455171200063,
|
| 921 |
+
"grad_norm": 2.5541040897369385,
|
| 922 |
+
"learning_rate": 4.6871516846242595e-05,
|
| 923 |
+
"loss": 0.0571,
|
| 924 |
+
"step": 12800
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.06306341539725063,
|
| 928 |
+
"grad_norm": 0.94892418384552,
|
| 929 |
+
"learning_rate": 4.6847073661980094e-05,
|
| 930 |
+
"loss": 0.0529,
|
| 931 |
+
"step": 12900
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.06355227908250063,
|
| 935 |
+
"grad_norm": 0.31644731760025024,
|
| 936 |
+
"learning_rate": 4.6822630477717594e-05,
|
| 937 |
+
"loss": 0.0635,
|
| 938 |
+
"step": 13000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.06404114276775064,
|
| 942 |
+
"grad_norm": 0.1212763786315918,
|
| 943 |
+
"learning_rate": 4.679818729345509e-05,
|
| 944 |
+
"loss": 0.04,
|
| 945 |
+
"step": 13100
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.06453000645300065,
|
| 949 |
+
"grad_norm": 4.629736423492432,
|
| 950 |
+
"learning_rate": 4.67737441091926e-05,
|
| 951 |
+
"loss": 0.0538,
|
| 952 |
+
"step": 13200
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.06501887013825065,
|
| 956 |
+
"grad_norm": 0.0852920413017273,
|
| 957 |
+
"learning_rate": 4.67493009249301e-05,
|
| 958 |
+
"loss": 0.0409,
|
| 959 |
+
"step": 13300
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.06550773382350066,
|
| 963 |
+
"grad_norm": 11.453609466552734,
|
| 964 |
+
"learning_rate": 4.672485774066759e-05,
|
| 965 |
+
"loss": 0.0641,
|
| 966 |
+
"step": 13400
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.06599659750875066,
|
| 970 |
+
"grad_norm": 0.45184290409088135,
|
| 971 |
+
"learning_rate": 4.670041455640509e-05,
|
| 972 |
+
"loss": 0.0647,
|
| 973 |
+
"step": 13500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.06648546119400066,
|
| 977 |
+
"grad_norm": 0.15610294044017792,
|
| 978 |
+
"learning_rate": 4.6675971372142596e-05,
|
| 979 |
+
"loss": 0.0558,
|
| 980 |
+
"step": 13600
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.06697432487925067,
|
| 984 |
+
"grad_norm": 0.3123125731945038,
|
| 985 |
+
"learning_rate": 4.6651528187880096e-05,
|
| 986 |
+
"loss": 0.0653,
|
| 987 |
+
"step": 13700
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.06746318856450068,
|
| 991 |
+
"grad_norm": 0.16336284577846527,
|
| 992 |
+
"learning_rate": 4.6627085003617595e-05,
|
| 993 |
+
"loss": 0.0761,
|
| 994 |
+
"step": 13800
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.06795205224975068,
|
| 998 |
+
"grad_norm": 1.843958854675293,
|
| 999 |
+
"learning_rate": 4.6602641819355094e-05,
|
| 1000 |
+
"loss": 0.058,
|
| 1001 |
+
"step": 13900
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.06844091593500068,
|
| 1005 |
+
"grad_norm": 1.828652024269104,
|
| 1006 |
+
"learning_rate": 4.6578198635092593e-05,
|
| 1007 |
+
"loss": 0.0506,
|
| 1008 |
+
"step": 14000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.0689297796202507,
|
| 1012 |
+
"grad_norm": 0.1550147831439972,
|
| 1013 |
+
"learning_rate": 4.655375545083009e-05,
|
| 1014 |
+
"loss": 0.0496,
|
| 1015 |
+
"step": 14100
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.0694186433055007,
|
| 1019 |
+
"grad_norm": 0.5400820970535278,
|
| 1020 |
+
"learning_rate": 4.652931226656759e-05,
|
| 1021 |
+
"loss": 0.0533,
|
| 1022 |
+
"step": 14200
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.0699075069907507,
|
| 1026 |
+
"grad_norm": 0.6133051514625549,
|
| 1027 |
+
"learning_rate": 4.650486908230509e-05,
|
| 1028 |
+
"loss": 0.0579,
|
| 1029 |
+
"step": 14300
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.0703963706760007,
|
| 1033 |
+
"grad_norm": 0.8691978454589844,
|
| 1034 |
+
"learning_rate": 4.648042589804259e-05,
|
| 1035 |
+
"loss": 0.0506,
|
| 1036 |
+
"step": 14400
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.07088523436125072,
|
| 1040 |
+
"grad_norm": 0.5965583920478821,
|
| 1041 |
+
"learning_rate": 4.64559827137801e-05,
|
| 1042 |
+
"loss": 0.0578,
|
| 1043 |
+
"step": 14500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.07137409804650072,
|
| 1047 |
+
"grad_norm": 0.10829576104879379,
|
| 1048 |
+
"learning_rate": 4.643153952951759e-05,
|
| 1049 |
+
"loss": 0.0502,
|
| 1050 |
+
"step": 14600
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.07186296173175072,
|
| 1054 |
+
"grad_norm": 2.9022679328918457,
|
| 1055 |
+
"learning_rate": 4.640709634525509e-05,
|
| 1056 |
+
"loss": 0.0537,
|
| 1057 |
+
"step": 14700
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.07235182541700072,
|
| 1061 |
+
"grad_norm": 0.186618834733963,
|
| 1062 |
+
"learning_rate": 4.638265316099259e-05,
|
| 1063 |
+
"loss": 0.065,
|
| 1064 |
+
"step": 14800
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.07284068910225072,
|
| 1068 |
+
"grad_norm": 1.755435585975647,
|
| 1069 |
+
"learning_rate": 4.635820997673009e-05,
|
| 1070 |
+
"loss": 0.0595,
|
| 1071 |
+
"step": 14900
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.07332955278750074,
|
| 1075 |
+
"grad_norm": 0.09724017232656479,
|
| 1076 |
+
"learning_rate": 4.6333766792467593e-05,
|
| 1077 |
+
"loss": 0.0572,
|
| 1078 |
+
"step": 15000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.07332955278750074,
|
| 1082 |
+
"eval_accuracy": 0.9857282510507884,
|
| 1083 |
+
"eval_loss": 0.055753011256456375,
|
| 1084 |
+
"eval_runtime": 87.7118,
|
| 1085 |
+
"eval_samples_per_second": 8292.05,
|
| 1086 |
+
"eval_steps_per_second": 259.133,
|
| 1087 |
+
"step": 15000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.07381841647275074,
|
| 1091 |
+
"grad_norm": 0.10130947083234787,
|
| 1092 |
+
"learning_rate": 4.630932360820509e-05,
|
| 1093 |
+
"loss": 0.0652,
|
| 1094 |
+
"step": 15100
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.07430728015800074,
|
| 1098 |
+
"grad_norm": 0.3545862138271332,
|
| 1099 |
+
"learning_rate": 4.628488042394259e-05,
|
| 1100 |
+
"loss": 0.057,
|
| 1101 |
+
"step": 15200
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.07479614384325074,
|
| 1105 |
+
"grad_norm": 1.8813221454620361,
|
| 1106 |
+
"learning_rate": 4.6260437239680085e-05,
|
| 1107 |
+
"loss": 0.0513,
|
| 1108 |
+
"step": 15300
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.07528500752850076,
|
| 1112 |
+
"grad_norm": 4.248858451843262,
|
| 1113 |
+
"learning_rate": 4.623599405541759e-05,
|
| 1114 |
+
"loss": 0.0578,
|
| 1115 |
+
"step": 15400
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.07577387121375076,
|
| 1119 |
+
"grad_norm": 0.11920436471700668,
|
| 1120 |
+
"learning_rate": 4.621155087115509e-05,
|
| 1121 |
+
"loss": 0.0737,
|
| 1122 |
+
"step": 15500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.07626273489900076,
|
| 1126 |
+
"grad_norm": 0.5360930562019348,
|
| 1127 |
+
"learning_rate": 4.618710768689259e-05,
|
| 1128 |
+
"loss": 0.0545,
|
| 1129 |
+
"step": 15600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.07675159858425076,
|
| 1133 |
+
"grad_norm": 0.30603697896003723,
|
| 1134 |
+
"learning_rate": 4.616266450263009e-05,
|
| 1135 |
+
"loss": 0.0604,
|
| 1136 |
+
"step": 15700
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.07724046226950078,
|
| 1140 |
+
"grad_norm": 0.2817041873931885,
|
| 1141 |
+
"learning_rate": 4.613822131836759e-05,
|
| 1142 |
+
"loss": 0.0662,
|
| 1143 |
+
"step": 15800
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.07772932595475078,
|
| 1147 |
+
"grad_norm": 0.23898492753505707,
|
| 1148 |
+
"learning_rate": 4.611377813410509e-05,
|
| 1149 |
+
"loss": 0.0557,
|
| 1150 |
+
"step": 15900
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.07821818964000078,
|
| 1154 |
+
"grad_norm": 4.95891809463501,
|
| 1155 |
+
"learning_rate": 4.608933494984259e-05,
|
| 1156 |
+
"loss": 0.069,
|
| 1157 |
+
"step": 16000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.07870705332525078,
|
| 1161 |
+
"grad_norm": 0.797389805316925,
|
| 1162 |
+
"learning_rate": 4.6064891765580086e-05,
|
| 1163 |
+
"loss": 0.068,
|
| 1164 |
+
"step": 16100
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.07919591701050079,
|
| 1168 |
+
"grad_norm": 0.13244754076004028,
|
| 1169 |
+
"learning_rate": 4.6040448581317585e-05,
|
| 1170 |
+
"loss": 0.0584,
|
| 1171 |
+
"step": 16200
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.0796847806957508,
|
| 1175 |
+
"grad_norm": 0.21337753534317017,
|
| 1176 |
+
"learning_rate": 4.601600539705509e-05,
|
| 1177 |
+
"loss": 0.047,
|
| 1178 |
+
"step": 16300
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.0801736443810008,
|
| 1182 |
+
"grad_norm": 0.1518852561712265,
|
| 1183 |
+
"learning_rate": 4.599156221279259e-05,
|
| 1184 |
+
"loss": 0.0556,
|
| 1185 |
+
"step": 16400
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.0806625080662508,
|
| 1189 |
+
"grad_norm": 0.6992989182472229,
|
| 1190 |
+
"learning_rate": 4.596711902853009e-05,
|
| 1191 |
+
"loss": 0.0521,
|
| 1192 |
+
"step": 16500
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.0811513717515008,
|
| 1196 |
+
"grad_norm": 6.529197692871094,
|
| 1197 |
+
"learning_rate": 4.594267584426758e-05,
|
| 1198 |
+
"loss": 0.0582,
|
| 1199 |
+
"step": 16600
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.08164023543675082,
|
| 1203 |
+
"grad_norm": 0.8226706981658936,
|
| 1204 |
+
"learning_rate": 4.591823266000508e-05,
|
| 1205 |
+
"loss": 0.0621,
|
| 1206 |
+
"step": 16700
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.08212909912200082,
|
| 1210 |
+
"grad_norm": 0.8117640018463135,
|
| 1211 |
+
"learning_rate": 4.589378947574259e-05,
|
| 1212 |
+
"loss": 0.0589,
|
| 1213 |
+
"step": 16800
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.08261796280725082,
|
| 1217 |
+
"grad_norm": 4.143149375915527,
|
| 1218 |
+
"learning_rate": 4.586934629148009e-05,
|
| 1219 |
+
"loss": 0.0502,
|
| 1220 |
+
"step": 16900
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.08310682649250083,
|
| 1224 |
+
"grad_norm": 0.6768002510070801,
|
| 1225 |
+
"learning_rate": 4.584490310721759e-05,
|
| 1226 |
+
"loss": 0.0531,
|
| 1227 |
+
"step": 17000
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.08359569017775084,
|
| 1231 |
+
"grad_norm": 0.9531612992286682,
|
| 1232 |
+
"learning_rate": 4.5820459922955086e-05,
|
| 1233 |
+
"loss": 0.0581,
|
| 1234 |
+
"step": 17100
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.08408455386300084,
|
| 1238 |
+
"grad_norm": 2.3488306999206543,
|
| 1239 |
+
"learning_rate": 4.5796016738692585e-05,
|
| 1240 |
+
"loss": 0.0524,
|
| 1241 |
+
"step": 17200
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.08457341754825085,
|
| 1245 |
+
"grad_norm": 0.054539360105991364,
|
| 1246 |
+
"learning_rate": 4.5771573554430085e-05,
|
| 1247 |
+
"loss": 0.0571,
|
| 1248 |
+
"step": 17300
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.08506228123350085,
|
| 1252 |
+
"grad_norm": 0.20826134085655212,
|
| 1253 |
+
"learning_rate": 4.5747130370167584e-05,
|
| 1254 |
+
"loss": 0.0732,
|
| 1255 |
+
"step": 17400
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.08555114491875085,
|
| 1259 |
+
"grad_norm": 0.5423992276191711,
|
| 1260 |
+
"learning_rate": 4.572268718590508e-05,
|
| 1261 |
+
"loss": 0.0648,
|
| 1262 |
+
"step": 17500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.08604000860400086,
|
| 1266 |
+
"grad_norm": 0.6129695177078247,
|
| 1267 |
+
"learning_rate": 4.569824400164258e-05,
|
| 1268 |
+
"loss": 0.0529,
|
| 1269 |
+
"step": 17600
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.08652887228925087,
|
| 1273 |
+
"grad_norm": 1.0215038061141968,
|
| 1274 |
+
"learning_rate": 4.567380081738009e-05,
|
| 1275 |
+
"loss": 0.0556,
|
| 1276 |
+
"step": 17700
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.08701773597450087,
|
| 1280 |
+
"grad_norm": 0.10388552397489548,
|
| 1281 |
+
"learning_rate": 4.564935763311758e-05,
|
| 1282 |
+
"loss": 0.0546,
|
| 1283 |
+
"step": 17800
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.08750659965975087,
|
| 1287 |
+
"grad_norm": 0.15670034289360046,
|
| 1288 |
+
"learning_rate": 4.562491444885508e-05,
|
| 1289 |
+
"loss": 0.0672,
|
| 1290 |
+
"step": 17900
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.08799546334500088,
|
| 1294 |
+
"grad_norm": 0.07073372602462769,
|
| 1295 |
+
"learning_rate": 4.560047126459258e-05,
|
| 1296 |
+
"loss": 0.0497,
|
| 1297 |
+
"step": 18000
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.08848432703025089,
|
| 1301 |
+
"grad_norm": 0.05959007889032364,
|
| 1302 |
+
"learning_rate": 4.5576028080330086e-05,
|
| 1303 |
+
"loss": 0.065,
|
| 1304 |
+
"step": 18100
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.08897319071550089,
|
| 1308 |
+
"grad_norm": 0.11457733064889908,
|
| 1309 |
+
"learning_rate": 4.5551584896067585e-05,
|
| 1310 |
+
"loss": 0.0608,
|
| 1311 |
+
"step": 18200
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.08946205440075089,
|
| 1315 |
+
"grad_norm": 2.1078646183013916,
|
| 1316 |
+
"learning_rate": 4.5527141711805085e-05,
|
| 1317 |
+
"loss": 0.0519,
|
| 1318 |
+
"step": 18300
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.0899509180860009,
|
| 1322 |
+
"grad_norm": 0.24909722805023193,
|
| 1323 |
+
"learning_rate": 4.5502698527542584e-05,
|
| 1324 |
+
"loss": 0.0609,
|
| 1325 |
+
"step": 18400
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.09043978177125091,
|
| 1329 |
+
"grad_norm": 0.17300719022750854,
|
| 1330 |
+
"learning_rate": 4.5478255343280076e-05,
|
| 1331 |
+
"loss": 0.0623,
|
| 1332 |
+
"step": 18500
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.09092864545650091,
|
| 1336 |
+
"grad_norm": 0.5368871092796326,
|
| 1337 |
+
"learning_rate": 4.545381215901758e-05,
|
| 1338 |
+
"loss": 0.0528,
|
| 1339 |
+
"step": 18600
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.09141750914175091,
|
| 1343 |
+
"grad_norm": 0.6745831370353699,
|
| 1344 |
+
"learning_rate": 4.542936897475508e-05,
|
| 1345 |
+
"loss": 0.053,
|
| 1346 |
+
"step": 18700
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.09190637282700091,
|
| 1350 |
+
"grad_norm": 0.21600577235221863,
|
| 1351 |
+
"learning_rate": 4.540492579049258e-05,
|
| 1352 |
+
"loss": 0.0526,
|
| 1353 |
+
"step": 18800
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.09239523651225093,
|
| 1357 |
+
"grad_norm": 0.2621341943740845,
|
| 1358 |
+
"learning_rate": 4.538048260623008e-05,
|
| 1359 |
+
"loss": 0.0529,
|
| 1360 |
+
"step": 18900
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.09288410019750093,
|
| 1364 |
+
"grad_norm": 0.12512639164924622,
|
| 1365 |
+
"learning_rate": 4.5356039421967587e-05,
|
| 1366 |
+
"loss": 0.0498,
|
| 1367 |
+
"step": 19000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.09337296388275093,
|
| 1371 |
+
"grad_norm": 1.9644027948379517,
|
| 1372 |
+
"learning_rate": 4.533159623770508e-05,
|
| 1373 |
+
"loss": 0.0501,
|
| 1374 |
+
"step": 19100
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.09386182756800093,
|
| 1378 |
+
"grad_norm": 0.29438772797584534,
|
| 1379 |
+
"learning_rate": 4.530715305344258e-05,
|
| 1380 |
+
"loss": 0.0529,
|
| 1381 |
+
"step": 19200
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.09435069125325095,
|
| 1385 |
+
"grad_norm": 1.3171613216400146,
|
| 1386 |
+
"learning_rate": 4.528270986918008e-05,
|
| 1387 |
+
"loss": 0.0549,
|
| 1388 |
+
"step": 19300
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.09483955493850095,
|
| 1392 |
+
"grad_norm": 0.423486590385437,
|
| 1393 |
+
"learning_rate": 4.525826668491758e-05,
|
| 1394 |
+
"loss": 0.0653,
|
| 1395 |
+
"step": 19400
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.09532841862375095,
|
| 1399 |
+
"grad_norm": 2.262716770172119,
|
| 1400 |
+
"learning_rate": 4.523382350065508e-05,
|
| 1401 |
+
"loss": 0.0513,
|
| 1402 |
+
"step": 19500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.09581728230900095,
|
| 1406 |
+
"grad_norm": 0.17267495393753052,
|
| 1407 |
+
"learning_rate": 4.520938031639258e-05,
|
| 1408 |
+
"loss": 0.0675,
|
| 1409 |
+
"step": 19600
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.09630614599425097,
|
| 1413 |
+
"grad_norm": 0.2510879337787628,
|
| 1414 |
+
"learning_rate": 4.518493713213008e-05,
|
| 1415 |
+
"loss": 0.0441,
|
| 1416 |
+
"step": 19700
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.09679500967950097,
|
| 1420 |
+
"grad_norm": 1.377731204032898,
|
| 1421 |
+
"learning_rate": 4.5160493947867574e-05,
|
| 1422 |
+
"loss": 0.0686,
|
| 1423 |
+
"step": 19800
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.09728387336475097,
|
| 1427 |
+
"grad_norm": 0.5991084575653076,
|
| 1428 |
+
"learning_rate": 4.513605076360508e-05,
|
| 1429 |
+
"loss": 0.057,
|
| 1430 |
+
"step": 19900
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.09777273705000097,
|
| 1434 |
+
"grad_norm": 0.48753178119659424,
|
| 1435 |
+
"learning_rate": 4.511160757934258e-05,
|
| 1436 |
+
"loss": 0.0698,
|
| 1437 |
+
"step": 20000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.09777273705000097,
|
| 1441 |
+
"eval_accuracy": 0.9863799667542495,
|
| 1442 |
+
"eval_loss": 0.04931970685720444,
|
| 1443 |
+
"eval_runtime": 89.5005,
|
| 1444 |
+
"eval_samples_per_second": 8126.33,
|
| 1445 |
+
"eval_steps_per_second": 253.954,
|
| 1446 |
+
"step": 20000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.09826160073525098,
|
| 1450 |
+
"grad_norm": 0.060726962983608246,
|
| 1451 |
+
"learning_rate": 4.508716439508008e-05,
|
| 1452 |
+
"loss": 0.0446,
|
| 1453 |
+
"step": 20100
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.09875046442050099,
|
| 1457 |
+
"grad_norm": 0.4069385230541229,
|
| 1458 |
+
"learning_rate": 4.506272121081758e-05,
|
| 1459 |
+
"loss": 0.0486,
|
| 1460 |
+
"step": 20200
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.09923932810575099,
|
| 1464 |
+
"grad_norm": 0.45975765585899353,
|
| 1465 |
+
"learning_rate": 4.503827802655508e-05,
|
| 1466 |
+
"loss": 0.0563,
|
| 1467 |
+
"step": 20300
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.099728191791001,
|
| 1471 |
+
"grad_norm": 0.15748950839042664,
|
| 1472 |
+
"learning_rate": 4.501383484229258e-05,
|
| 1473 |
+
"loss": 0.0567,
|
| 1474 |
+
"step": 20400
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.100217055476251,
|
| 1478 |
+
"grad_norm": 0.07134643942117691,
|
| 1479 |
+
"learning_rate": 4.4989391658030076e-05,
|
| 1480 |
+
"loss": 0.0612,
|
| 1481 |
+
"step": 20500
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.10070591916150101,
|
| 1485 |
+
"grad_norm": 1.8180408477783203,
|
| 1486 |
+
"learning_rate": 4.4964948473767576e-05,
|
| 1487 |
+
"loss": 0.0564,
|
| 1488 |
+
"step": 20600
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.10119478284675101,
|
| 1492 |
+
"grad_norm": 0.8957489132881165,
|
| 1493 |
+
"learning_rate": 4.4940505289505075e-05,
|
| 1494 |
+
"loss": 0.0476,
|
| 1495 |
+
"step": 20700
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.10168364653200102,
|
| 1499 |
+
"grad_norm": 0.7452836632728577,
|
| 1500 |
+
"learning_rate": 4.491606210524258e-05,
|
| 1501 |
+
"loss": 0.0643,
|
| 1502 |
+
"step": 20800
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.10217251021725102,
|
| 1506 |
+
"grad_norm": 0.5802486538887024,
|
| 1507 |
+
"learning_rate": 4.489161892098008e-05,
|
| 1508 |
+
"loss": 0.0573,
|
| 1509 |
+
"step": 20900
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.10266137390250103,
|
| 1513 |
+
"grad_norm": 0.558313250541687,
|
| 1514 |
+
"learning_rate": 4.486717573671757e-05,
|
| 1515 |
+
"loss": 0.0512,
|
| 1516 |
+
"step": 21000
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.10315023758775103,
|
| 1520 |
+
"grad_norm": 0.1745966672897339,
|
| 1521 |
+
"learning_rate": 4.484273255245507e-05,
|
| 1522 |
+
"loss": 0.0601,
|
| 1523 |
+
"step": 21100
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.10363910127300104,
|
| 1527 |
+
"grad_norm": 0.151627779006958,
|
| 1528 |
+
"learning_rate": 4.481828936819257e-05,
|
| 1529 |
+
"loss": 0.055,
|
| 1530 |
+
"step": 21200
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.10412796495825104,
|
| 1534 |
+
"grad_norm": 0.22826308012008667,
|
| 1535 |
+
"learning_rate": 4.479384618393008e-05,
|
| 1536 |
+
"loss": 0.0663,
|
| 1537 |
+
"step": 21300
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.10461682864350105,
|
| 1541 |
+
"grad_norm": 1.1712322235107422,
|
| 1542 |
+
"learning_rate": 4.476940299966758e-05,
|
| 1543 |
+
"loss": 0.0554,
|
| 1544 |
+
"step": 21400
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.10510569232875105,
|
| 1548 |
+
"grad_norm": 0.4323095679283142,
|
| 1549 |
+
"learning_rate": 4.4744959815405076e-05,
|
| 1550 |
+
"loss": 0.0489,
|
| 1551 |
+
"step": 21500
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.10559455601400106,
|
| 1555 |
+
"grad_norm": 1.9872769117355347,
|
| 1556 |
+
"learning_rate": 4.4720516631142576e-05,
|
| 1557 |
+
"loss": 0.053,
|
| 1558 |
+
"step": 21600
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.10608341969925106,
|
| 1562 |
+
"grad_norm": 0.8765336871147156,
|
| 1563 |
+
"learning_rate": 4.4696073446880075e-05,
|
| 1564 |
+
"loss": 0.0502,
|
| 1565 |
+
"step": 21700
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.10657228338450106,
|
| 1569 |
+
"grad_norm": 0.24051639437675476,
|
| 1570 |
+
"learning_rate": 4.4671630262617574e-05,
|
| 1571 |
+
"loss": 0.0446,
|
| 1572 |
+
"step": 21800
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.10706114706975108,
|
| 1576 |
+
"grad_norm": 0.10694507509469986,
|
| 1577 |
+
"learning_rate": 4.4647187078355074e-05,
|
| 1578 |
+
"loss": 0.0439,
|
| 1579 |
+
"step": 21900
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.10755001075500108,
|
| 1583 |
+
"grad_norm": 0.3620724678039551,
|
| 1584 |
+
"learning_rate": 4.462274389409257e-05,
|
| 1585 |
+
"loss": 0.0693,
|
| 1586 |
+
"step": 22000
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.10803887444025108,
|
| 1590 |
+
"grad_norm": 0.09434635192155838,
|
| 1591 |
+
"learning_rate": 4.459830070983007e-05,
|
| 1592 |
+
"loss": 0.0391,
|
| 1593 |
+
"step": 22100
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.10852773812550108,
|
| 1597 |
+
"grad_norm": 1.2601689100265503,
|
| 1598 |
+
"learning_rate": 4.457385752556758e-05,
|
| 1599 |
+
"loss": 0.0492,
|
| 1600 |
+
"step": 22200
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.1090166018107511,
|
| 1604 |
+
"grad_norm": 1.0507802963256836,
|
| 1605 |
+
"learning_rate": 4.454941434130507e-05,
|
| 1606 |
+
"loss": 0.0532,
|
| 1607 |
+
"step": 22300
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.1095054654960011,
|
| 1611 |
+
"grad_norm": 0.23753391206264496,
|
| 1612 |
+
"learning_rate": 4.452497115704257e-05,
|
| 1613 |
+
"loss": 0.0558,
|
| 1614 |
+
"step": 22400
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.1099943291812511,
|
| 1618 |
+
"grad_norm": 1.9314781427383423,
|
| 1619 |
+
"learning_rate": 4.450052797278007e-05,
|
| 1620 |
+
"loss": 0.0524,
|
| 1621 |
+
"step": 22500
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.1104831928665011,
|
| 1625 |
+
"grad_norm": 0.0501798614859581,
|
| 1626 |
+
"learning_rate": 4.4476084788517576e-05,
|
| 1627 |
+
"loss": 0.057,
|
| 1628 |
+
"step": 22600
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.11097205655175112,
|
| 1632 |
+
"grad_norm": 2.1326324939727783,
|
| 1633 |
+
"learning_rate": 4.4451641604255075e-05,
|
| 1634 |
+
"loss": 0.0606,
|
| 1635 |
+
"step": 22700
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.11146092023700112,
|
| 1639 |
+
"grad_norm": 0.7677115797996521,
|
| 1640 |
+
"learning_rate": 4.4427198419992574e-05,
|
| 1641 |
+
"loss": 0.0819,
|
| 1642 |
+
"step": 22800
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.11194978392225112,
|
| 1646 |
+
"grad_norm": 0.7734199166297913,
|
| 1647 |
+
"learning_rate": 4.4402755235730074e-05,
|
| 1648 |
+
"loss": 0.0567,
|
| 1649 |
+
"step": 22900
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.11243864760750112,
|
| 1653 |
+
"grad_norm": 0.24596163630485535,
|
| 1654 |
+
"learning_rate": 4.4378312051467566e-05,
|
| 1655 |
+
"loss": 0.0603,
|
| 1656 |
+
"step": 23000
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 0.11292751129275112,
|
| 1660 |
+
"grad_norm": 0.7795409560203552,
|
| 1661 |
+
"learning_rate": 4.435386886720507e-05,
|
| 1662 |
+
"loss": 0.0661,
|
| 1663 |
+
"step": 23100
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.11341637497800114,
|
| 1667 |
+
"grad_norm": 0.17799228429794312,
|
| 1668 |
+
"learning_rate": 4.432942568294257e-05,
|
| 1669 |
+
"loss": 0.0524,
|
| 1670 |
+
"step": 23200
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.11390523866325114,
|
| 1674 |
+
"grad_norm": 1.1686981916427612,
|
| 1675 |
+
"learning_rate": 4.430498249868007e-05,
|
| 1676 |
+
"loss": 0.0593,
|
| 1677 |
+
"step": 23300
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.11439410234850114,
|
| 1681 |
+
"grad_norm": 1.1257573366165161,
|
| 1682 |
+
"learning_rate": 4.428053931441757e-05,
|
| 1683 |
+
"loss": 0.0554,
|
| 1684 |
+
"step": 23400
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 0.11488296603375114,
|
| 1688 |
+
"grad_norm": 1.0275357961654663,
|
| 1689 |
+
"learning_rate": 4.425609613015507e-05,
|
| 1690 |
+
"loss": 0.06,
|
| 1691 |
+
"step": 23500
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 0.11537182971900116,
|
| 1695 |
+
"grad_norm": 0.130942240357399,
|
| 1696 |
+
"learning_rate": 4.423165294589257e-05,
|
| 1697 |
+
"loss": 0.066,
|
| 1698 |
+
"step": 23600
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.11586069340425116,
|
| 1702 |
+
"grad_norm": 0.9909563660621643,
|
| 1703 |
+
"learning_rate": 4.420720976163007e-05,
|
| 1704 |
+
"loss": 0.0626,
|
| 1705 |
+
"step": 23700
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.11634955708950116,
|
| 1709 |
+
"grad_norm": 0.3424215316772461,
|
| 1710 |
+
"learning_rate": 4.418276657736757e-05,
|
| 1711 |
+
"loss": 0.0534,
|
| 1712 |
+
"step": 23800
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.11683842077475116,
|
| 1716 |
+
"grad_norm": 0.7943697571754456,
|
| 1717 |
+
"learning_rate": 4.415832339310507e-05,
|
| 1718 |
+
"loss": 0.0573,
|
| 1719 |
+
"step": 23900
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.11732728446000118,
|
| 1723 |
+
"grad_norm": 0.11096975207328796,
|
| 1724 |
+
"learning_rate": 4.413388020884257e-05,
|
| 1725 |
+
"loss": 0.0582,
|
| 1726 |
+
"step": 24000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.11781614814525118,
|
| 1730 |
+
"grad_norm": 0.05640365183353424,
|
| 1731 |
+
"learning_rate": 4.410943702458007e-05,
|
| 1732 |
+
"loss": 0.0473,
|
| 1733 |
+
"step": 24100
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.11830501183050118,
|
| 1737 |
+
"grad_norm": 0.21789075434207916,
|
| 1738 |
+
"learning_rate": 4.4084993840317565e-05,
|
| 1739 |
+
"loss": 0.0568,
|
| 1740 |
+
"step": 24200
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.11879387551575118,
|
| 1744 |
+
"grad_norm": 1.5143808126449585,
|
| 1745 |
+
"learning_rate": 4.4060550656055064e-05,
|
| 1746 |
+
"loss": 0.0518,
|
| 1747 |
+
"step": 24300
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.11928273920100119,
|
| 1751 |
+
"grad_norm": 0.13033248484134674,
|
| 1752 |
+
"learning_rate": 4.4036107471792563e-05,
|
| 1753 |
+
"loss": 0.0525,
|
| 1754 |
+
"step": 24400
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.1197716028862512,
|
| 1758 |
+
"grad_norm": 0.3291008770465851,
|
| 1759 |
+
"learning_rate": 4.401166428753007e-05,
|
| 1760 |
+
"loss": 0.0484,
|
| 1761 |
+
"step": 24500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.1202604665715012,
|
| 1765 |
+
"grad_norm": 0.14064234495162964,
|
| 1766 |
+
"learning_rate": 4.398722110326757e-05,
|
| 1767 |
+
"loss": 0.0694,
|
| 1768 |
+
"step": 24600
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.1207493302567512,
|
| 1772 |
+
"grad_norm": 0.320850133895874,
|
| 1773 |
+
"learning_rate": 4.396277791900507e-05,
|
| 1774 |
+
"loss": 0.073,
|
| 1775 |
+
"step": 24700
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.12123819394200121,
|
| 1779 |
+
"grad_norm": 7.313945293426514,
|
| 1780 |
+
"learning_rate": 4.393833473474257e-05,
|
| 1781 |
+
"loss": 0.052,
|
| 1782 |
+
"step": 24800
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.12172705762725122,
|
| 1786 |
+
"grad_norm": 0.19710104167461395,
|
| 1787 |
+
"learning_rate": 4.391389155048007e-05,
|
| 1788 |
+
"loss": 0.0511,
|
| 1789 |
+
"step": 24900
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.12221592131250122,
|
| 1793 |
+
"grad_norm": 0.08815807104110718,
|
| 1794 |
+
"learning_rate": 4.3889448366217566e-05,
|
| 1795 |
+
"loss": 0.0581,
|
| 1796 |
+
"step": 25000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.12221592131250122,
|
| 1800 |
+
"eval_accuracy": 0.9854766392918572,
|
| 1801 |
+
"eval_loss": 0.06387843191623688,
|
| 1802 |
+
"eval_runtime": 87.5746,
|
| 1803 |
+
"eval_samples_per_second": 8305.042,
|
| 1804 |
+
"eval_steps_per_second": 259.539,
|
| 1805 |
+
"step": 25000
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 0.12270478499775123,
|
| 1809 |
+
"grad_norm": 0.19257056713104248,
|
| 1810 |
+
"learning_rate": 4.3865005181955065e-05,
|
| 1811 |
+
"loss": 0.0553,
|
| 1812 |
+
"step": 25100
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 0.12319364868300123,
|
| 1816 |
+
"grad_norm": 1.0255241394042969,
|
| 1817 |
+
"learning_rate": 4.3840561997692565e-05,
|
| 1818 |
+
"loss": 0.0552,
|
| 1819 |
+
"step": 25200
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.12368251236825124,
|
| 1823 |
+
"grad_norm": 0.19426164031028748,
|
| 1824 |
+
"learning_rate": 4.3816118813430064e-05,
|
| 1825 |
+
"loss": 0.0527,
|
| 1826 |
+
"step": 25300
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.12417137605350125,
|
| 1830 |
+
"grad_norm": 4.577849864959717,
|
| 1831 |
+
"learning_rate": 4.379167562916756e-05,
|
| 1832 |
+
"loss": 0.0494,
|
| 1833 |
+
"step": 25400
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.12466023973875125,
|
| 1837 |
+
"grad_norm": 0.14611122012138367,
|
| 1838 |
+
"learning_rate": 4.376723244490506e-05,
|
| 1839 |
+
"loss": 0.0491,
|
| 1840 |
+
"step": 25500
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.12514910342400126,
|
| 1844 |
+
"grad_norm": 0.3980867266654968,
|
| 1845 |
+
"learning_rate": 4.374278926064256e-05,
|
| 1846 |
+
"loss": 0.0573,
|
| 1847 |
+
"step": 25600
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.12563796710925126,
|
| 1851 |
+
"grad_norm": 12.226862907409668,
|
| 1852 |
+
"learning_rate": 4.371834607638006e-05,
|
| 1853 |
+
"loss": 0.0665,
|
| 1854 |
+
"step": 25700
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.12612683079450127,
|
| 1858 |
+
"grad_norm": 0.5252171158790588,
|
| 1859 |
+
"learning_rate": 4.369390289211757e-05,
|
| 1860 |
+
"loss": 0.0561,
|
| 1861 |
+
"step": 25800
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.12661569447975127,
|
| 1865 |
+
"grad_norm": 0.13088272511959076,
|
| 1866 |
+
"learning_rate": 4.366945970785507e-05,
|
| 1867 |
+
"loss": 0.056,
|
| 1868 |
+
"step": 25900
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.12710455816500127,
|
| 1872 |
+
"grad_norm": 0.11612076312303543,
|
| 1873 |
+
"learning_rate": 4.3645016523592566e-05,
|
| 1874 |
+
"loss": 0.0529,
|
| 1875 |
+
"step": 26000
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.12759342185025127,
|
| 1879 |
+
"grad_norm": 2.1254241466522217,
|
| 1880 |
+
"learning_rate": 4.362057333933006e-05,
|
| 1881 |
+
"loss": 0.0713,
|
| 1882 |
+
"step": 26100
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.12808228553550127,
|
| 1886 |
+
"grad_norm": 0.2002074420452118,
|
| 1887 |
+
"learning_rate": 4.359613015506756e-05,
|
| 1888 |
+
"loss": 0.0595,
|
| 1889 |
+
"step": 26200
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.12857114922075127,
|
| 1893 |
+
"grad_norm": 17.567867279052734,
|
| 1894 |
+
"learning_rate": 4.3571686970805064e-05,
|
| 1895 |
+
"loss": 0.0475,
|
| 1896 |
+
"step": 26300
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.1290600129060013,
|
| 1900 |
+
"grad_norm": 6.713310241699219,
|
| 1901 |
+
"learning_rate": 4.354724378654256e-05,
|
| 1902 |
+
"loss": 0.0554,
|
| 1903 |
+
"step": 26400
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.1295488765912513,
|
| 1907 |
+
"grad_norm": 1.5497812032699585,
|
| 1908 |
+
"learning_rate": 4.352280060228006e-05,
|
| 1909 |
+
"loss": 0.0499,
|
| 1910 |
+
"step": 26500
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.1300377402765013,
|
| 1914 |
+
"grad_norm": 1.3904762268066406,
|
| 1915 |
+
"learning_rate": 4.349835741801756e-05,
|
| 1916 |
+
"loss": 0.0571,
|
| 1917 |
+
"step": 26600
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.1305266039617513,
|
| 1921 |
+
"grad_norm": 0.06898930668830872,
|
| 1922 |
+
"learning_rate": 4.347391423375506e-05,
|
| 1923 |
+
"loss": 0.0506,
|
| 1924 |
+
"step": 26700
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.1310154676470013,
|
| 1928 |
+
"grad_norm": 1.3017206192016602,
|
| 1929 |
+
"learning_rate": 4.344947104949256e-05,
|
| 1930 |
+
"loss": 0.0607,
|
| 1931 |
+
"step": 26800
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.1315043313322513,
|
| 1935 |
+
"grad_norm": 0.3089110851287842,
|
| 1936 |
+
"learning_rate": 4.342502786523006e-05,
|
| 1937 |
+
"loss": 0.0533,
|
| 1938 |
+
"step": 26900
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.1319931950175013,
|
| 1942 |
+
"grad_norm": 0.12219520658254623,
|
| 1943 |
+
"learning_rate": 4.340058468096756e-05,
|
| 1944 |
+
"loss": 0.056,
|
| 1945 |
+
"step": 27000
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.13248205870275132,
|
| 1949 |
+
"grad_norm": 1.3822331428527832,
|
| 1950 |
+
"learning_rate": 4.337614149670506e-05,
|
| 1951 |
+
"loss": 0.0671,
|
| 1952 |
+
"step": 27100
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.13297092238800132,
|
| 1956 |
+
"grad_norm": 0.12018796801567078,
|
| 1957 |
+
"learning_rate": 4.3351698312442565e-05,
|
| 1958 |
+
"loss": 0.0508,
|
| 1959 |
+
"step": 27200
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.13345978607325135,
|
| 1963 |
+
"grad_norm": 0.43314507603645325,
|
| 1964 |
+
"learning_rate": 4.3327255128180064e-05,
|
| 1965 |
+
"loss": 0.0491,
|
| 1966 |
+
"step": 27300
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 0.13394864975850135,
|
| 1970 |
+
"grad_norm": 0.13789387047290802,
|
| 1971 |
+
"learning_rate": 4.3302811943917557e-05,
|
| 1972 |
+
"loss": 0.0575,
|
| 1973 |
+
"step": 27400
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 0.13443751344375135,
|
| 1977 |
+
"grad_norm": 0.16118775308132172,
|
| 1978 |
+
"learning_rate": 4.3278368759655056e-05,
|
| 1979 |
+
"loss": 0.0587,
|
| 1980 |
+
"step": 27500
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 0.13492637712900135,
|
| 1984 |
+
"grad_norm": 325.5366516113281,
|
| 1985 |
+
"learning_rate": 4.325392557539256e-05,
|
| 1986 |
+
"loss": 0.0515,
|
| 1987 |
+
"step": 27600
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 0.13541524081425135,
|
| 1991 |
+
"grad_norm": 0.1395142376422882,
|
| 1992 |
+
"learning_rate": 4.322948239113006e-05,
|
| 1993 |
+
"loss": 0.0653,
|
| 1994 |
+
"step": 27700
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.13590410449950135,
|
| 1998 |
+
"grad_norm": 0.17250843346118927,
|
| 1999 |
+
"learning_rate": 4.320503920686756e-05,
|
| 2000 |
+
"loss": 0.0425,
|
| 2001 |
+
"step": 27800
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.13639296818475136,
|
| 2005 |
+
"grad_norm": 0.15068072080612183,
|
| 2006 |
+
"learning_rate": 4.318059602260506e-05,
|
| 2007 |
+
"loss": 0.0586,
|
| 2008 |
+
"step": 27900
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 0.13688183187000136,
|
| 2012 |
+
"grad_norm": 0.17689694464206696,
|
| 2013 |
+
"learning_rate": 4.315615283834256e-05,
|
| 2014 |
+
"loss": 0.0519,
|
| 2015 |
+
"step": 28000
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 0.1373706955552514,
|
| 2019 |
+
"grad_norm": 0.1103501245379448,
|
| 2020 |
+
"learning_rate": 4.313170965408006e-05,
|
| 2021 |
+
"loss": 0.0519,
|
| 2022 |
+
"step": 28100
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 0.1378595592405014,
|
| 2026 |
+
"grad_norm": 7.250685214996338,
|
| 2027 |
+
"learning_rate": 4.310726646981756e-05,
|
| 2028 |
+
"loss": 0.059,
|
| 2029 |
+
"step": 28200
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 0.1383484229257514,
|
| 2033 |
+
"grad_norm": 0.15736211836338043,
|
| 2034 |
+
"learning_rate": 4.308282328555506e-05,
|
| 2035 |
+
"loss": 0.0581,
|
| 2036 |
+
"step": 28300
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 0.1388372866110014,
|
| 2040 |
+
"grad_norm": 0.2638852000236511,
|
| 2041 |
+
"learning_rate": 4.3058380101292557e-05,
|
| 2042 |
+
"loss": 0.0625,
|
| 2043 |
+
"step": 28400
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 0.1393261502962514,
|
| 2047 |
+
"grad_norm": 0.5942810773849487,
|
| 2048 |
+
"learning_rate": 4.303393691703006e-05,
|
| 2049 |
+
"loss": 0.057,
|
| 2050 |
+
"step": 28500
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 0.1398150139815014,
|
| 2054 |
+
"grad_norm": 2.4301233291625977,
|
| 2055 |
+
"learning_rate": 4.3009493732767555e-05,
|
| 2056 |
+
"loss": 0.0514,
|
| 2057 |
+
"step": 28600
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 0.1403038776667514,
|
| 2061 |
+
"grad_norm": 0.2111784815788269,
|
| 2062 |
+
"learning_rate": 4.2985050548505054e-05,
|
| 2063 |
+
"loss": 0.0657,
|
| 2064 |
+
"step": 28700
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 0.1407927413520014,
|
| 2068 |
+
"grad_norm": 0.5004536509513855,
|
| 2069 |
+
"learning_rate": 4.2960607364242554e-05,
|
| 2070 |
+
"loss": 0.0507,
|
| 2071 |
+
"step": 28800
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 0.1412816050372514,
|
| 2075 |
+
"grad_norm": 2.7559454441070557,
|
| 2076 |
+
"learning_rate": 4.293616417998005e-05,
|
| 2077 |
+
"loss": 0.0592,
|
| 2078 |
+
"step": 28900
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.14177046872250143,
|
| 2082 |
+
"grad_norm": 0.16613233089447021,
|
| 2083 |
+
"learning_rate": 4.291172099571756e-05,
|
| 2084 |
+
"loss": 0.0481,
|
| 2085 |
+
"step": 29000
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 0.14225933240775143,
|
| 2089 |
+
"grad_norm": 1.8648772239685059,
|
| 2090 |
+
"learning_rate": 4.288727781145506e-05,
|
| 2091 |
+
"loss": 0.0605,
|
| 2092 |
+
"step": 29100
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 0.14274819609300143,
|
| 2096 |
+
"grad_norm": 0.2779479920864105,
|
| 2097 |
+
"learning_rate": 4.286283462719256e-05,
|
| 2098 |
+
"loss": 0.0536,
|
| 2099 |
+
"step": 29200
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 0.14323705977825144,
|
| 2103 |
+
"grad_norm": 2.463592052459717,
|
| 2104 |
+
"learning_rate": 4.283839144293005e-05,
|
| 2105 |
+
"loss": 0.0571,
|
| 2106 |
+
"step": 29300
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 0.14372592346350144,
|
| 2110 |
+
"grad_norm": 0.9731730818748474,
|
| 2111 |
+
"learning_rate": 4.2813948258667557e-05,
|
| 2112 |
+
"loss": 0.0571,
|
| 2113 |
+
"step": 29400
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 0.14421478714875144,
|
| 2117 |
+
"grad_norm": 0.9727413654327393,
|
| 2118 |
+
"learning_rate": 4.2789505074405056e-05,
|
| 2119 |
+
"loss": 0.0536,
|
| 2120 |
+
"step": 29500
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 0.14470365083400144,
|
| 2124 |
+
"grad_norm": 7.790318489074707,
|
| 2125 |
+
"learning_rate": 4.2765061890142555e-05,
|
| 2126 |
+
"loss": 0.0592,
|
| 2127 |
+
"step": 29600
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 0.14519251451925144,
|
| 2131 |
+
"grad_norm": 0.4684147536754608,
|
| 2132 |
+
"learning_rate": 4.2740618705880054e-05,
|
| 2133 |
+
"loss": 0.0569,
|
| 2134 |
+
"step": 29700
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 0.14568137820450144,
|
| 2138 |
+
"grad_norm": 0.1493144929409027,
|
| 2139 |
+
"learning_rate": 4.2716175521617554e-05,
|
| 2140 |
+
"loss": 0.0502,
|
| 2141 |
+
"step": 29800
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 0.14617024188975147,
|
| 2145 |
+
"grad_norm": 0.1756664216518402,
|
| 2146 |
+
"learning_rate": 4.269173233735505e-05,
|
| 2147 |
+
"loss": 0.062,
|
| 2148 |
+
"step": 29900
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 0.14665910557500147,
|
| 2152 |
+
"grad_norm": 0.11740031093358994,
|
| 2153 |
+
"learning_rate": 4.266728915309255e-05,
|
| 2154 |
+
"loss": 0.0623,
|
| 2155 |
+
"step": 30000
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 0.14665910557500147,
|
| 2159 |
+
"eval_accuracy": 0.9861819771734512,
|
| 2160 |
+
"eval_loss": 0.05502888932824135,
|
| 2161 |
+
"eval_runtime": 86.9277,
|
| 2162 |
+
"eval_samples_per_second": 8366.847,
|
| 2163 |
+
"eval_steps_per_second": 261.47,
|
| 2164 |
+
"step": 30000
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 0.14714796926025148,
|
| 2168 |
+
"grad_norm": 0.2339940071105957,
|
| 2169 |
+
"learning_rate": 4.264284596883005e-05,
|
| 2170 |
+
"loss": 0.0557,
|
| 2171 |
+
"step": 30100
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 0.14763683294550148,
|
| 2175 |
+
"grad_norm": 4.08159875869751,
|
| 2176 |
+
"learning_rate": 4.261840278456755e-05,
|
| 2177 |
+
"loss": 0.0598,
|
| 2178 |
+
"step": 30200
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 0.14812569663075148,
|
| 2182 |
+
"grad_norm": 0.7028560042381287,
|
| 2183 |
+
"learning_rate": 4.259395960030506e-05,
|
| 2184 |
+
"loss": 0.0383,
|
| 2185 |
+
"step": 30300
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 0.14861456031600148,
|
| 2189 |
+
"grad_norm": 6.404703140258789,
|
| 2190 |
+
"learning_rate": 4.2569516416042556e-05,
|
| 2191 |
+
"loss": 0.0594,
|
| 2192 |
+
"step": 30400
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 0.14910342400125148,
|
| 2196 |
+
"grad_norm": 0.1876775026321411,
|
| 2197 |
+
"learning_rate": 4.2545073231780056e-05,
|
| 2198 |
+
"loss": 0.0451,
|
| 2199 |
+
"step": 30500
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.14959228768650149,
|
| 2203 |
+
"grad_norm": 2.3061537742614746,
|
| 2204 |
+
"learning_rate": 4.252063004751755e-05,
|
| 2205 |
+
"loss": 0.0601,
|
| 2206 |
+
"step": 30600
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.15008115137175151,
|
| 2210 |
+
"grad_norm": 3.7694387435913086,
|
| 2211 |
+
"learning_rate": 4.249618686325505e-05,
|
| 2212 |
+
"loss": 0.0517,
|
| 2213 |
+
"step": 30700
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 0.15057001505700152,
|
| 2217 |
+
"grad_norm": 0.10565809905529022,
|
| 2218 |
+
"learning_rate": 4.2471743678992554e-05,
|
| 2219 |
+
"loss": 0.0582,
|
| 2220 |
+
"step": 30800
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 0.15105887874225152,
|
| 2224 |
+
"grad_norm": 0.1568797081708908,
|
| 2225 |
+
"learning_rate": 4.244730049473005e-05,
|
| 2226 |
+
"loss": 0.0693,
|
| 2227 |
+
"step": 30900
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 0.15154774242750152,
|
| 2231 |
+
"grad_norm": 0.12189572304487228,
|
| 2232 |
+
"learning_rate": 4.242285731046755e-05,
|
| 2233 |
+
"loss": 0.0564,
|
| 2234 |
+
"step": 31000
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.15203660611275152,
|
| 2238 |
+
"grad_norm": 2.7350354194641113,
|
| 2239 |
+
"learning_rate": 4.239841412620505e-05,
|
| 2240 |
+
"loss": 0.0584,
|
| 2241 |
+
"step": 31100
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.15252546979800152,
|
| 2245 |
+
"grad_norm": 1.2639015913009644,
|
| 2246 |
+
"learning_rate": 4.237397094194255e-05,
|
| 2247 |
+
"loss": 0.0422,
|
| 2248 |
+
"step": 31200
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 0.15301433348325152,
|
| 2252 |
+
"grad_norm": 0.2128947377204895,
|
| 2253 |
+
"learning_rate": 4.234952775768005e-05,
|
| 2254 |
+
"loss": 0.0454,
|
| 2255 |
+
"step": 31300
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 0.15350319716850153,
|
| 2259 |
+
"grad_norm": 3.01932430267334,
|
| 2260 |
+
"learning_rate": 4.232508457341755e-05,
|
| 2261 |
+
"loss": 0.0556,
|
| 2262 |
+
"step": 31400
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 0.15399206085375153,
|
| 2266 |
+
"grad_norm": 0.15684618055820465,
|
| 2267 |
+
"learning_rate": 4.230064138915505e-05,
|
| 2268 |
+
"loss": 0.0406,
|
| 2269 |
+
"step": 31500
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 0.15448092453900156,
|
| 2273 |
+
"grad_norm": 0.860048234462738,
|
| 2274 |
+
"learning_rate": 4.227619820489255e-05,
|
| 2275 |
+
"loss": 0.0391,
|
| 2276 |
+
"step": 31600
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.15496978822425156,
|
| 2280 |
+
"grad_norm": 0.2231738120317459,
|
| 2281 |
+
"learning_rate": 4.2251755020630054e-05,
|
| 2282 |
+
"loss": 0.0484,
|
| 2283 |
+
"step": 31700
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 0.15545865190950156,
|
| 2287 |
+
"grad_norm": 0.6725517511367798,
|
| 2288 |
+
"learning_rate": 4.222731183636755e-05,
|
| 2289 |
+
"loss": 0.0511,
|
| 2290 |
+
"step": 31800
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 0.15594751559475156,
|
| 2294 |
+
"grad_norm": 1.0878608226776123,
|
| 2295 |
+
"learning_rate": 4.2202868652105046e-05,
|
| 2296 |
+
"loss": 0.0545,
|
| 2297 |
+
"step": 31900
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.15643637928000156,
|
| 2301 |
+
"grad_norm": 0.3082568347454071,
|
| 2302 |
+
"learning_rate": 4.2178425467842546e-05,
|
| 2303 |
+
"loss": 0.0535,
|
| 2304 |
+
"step": 32000
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.15692524296525157,
|
| 2308 |
+
"grad_norm": 2.2356953620910645,
|
| 2309 |
+
"learning_rate": 4.215398228358005e-05,
|
| 2310 |
+
"loss": 0.0501,
|
| 2311 |
+
"step": 32100
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.15741410665050157,
|
| 2315 |
+
"grad_norm": 0.3936662971973419,
|
| 2316 |
+
"learning_rate": 4.212953909931755e-05,
|
| 2317 |
+
"loss": 0.0694,
|
| 2318 |
+
"step": 32200
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.15790297033575157,
|
| 2322 |
+
"grad_norm": 1.8886637687683105,
|
| 2323 |
+
"learning_rate": 4.210509591505505e-05,
|
| 2324 |
+
"loss": 0.0535,
|
| 2325 |
+
"step": 32300
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 0.15839183402100157,
|
| 2329 |
+
"grad_norm": 0.2901158928871155,
|
| 2330 |
+
"learning_rate": 4.208065273079255e-05,
|
| 2331 |
+
"loss": 0.0504,
|
| 2332 |
+
"step": 32400
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 0.1588806977062516,
|
| 2336 |
+
"grad_norm": 0.1555911749601364,
|
| 2337 |
+
"learning_rate": 4.205620954653004e-05,
|
| 2338 |
+
"loss": 0.054,
|
| 2339 |
+
"step": 32500
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 0.1593695613915016,
|
| 2343 |
+
"grad_norm": 0.5104485154151917,
|
| 2344 |
+
"learning_rate": 4.203176636226755e-05,
|
| 2345 |
+
"loss": 0.057,
|
| 2346 |
+
"step": 32600
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 0.1598584250767516,
|
| 2350 |
+
"grad_norm": 0.139060378074646,
|
| 2351 |
+
"learning_rate": 4.200732317800505e-05,
|
| 2352 |
+
"loss": 0.0454,
|
| 2353 |
+
"step": 32700
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 0.1603472887620016,
|
| 2357 |
+
"grad_norm": 0.1524643450975418,
|
| 2358 |
+
"learning_rate": 4.198287999374255e-05,
|
| 2359 |
+
"loss": 0.061,
|
| 2360 |
+
"step": 32800
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 0.1608361524472516,
|
| 2364 |
+
"grad_norm": 1.3951168060302734,
|
| 2365 |
+
"learning_rate": 4.1958436809480046e-05,
|
| 2366 |
+
"loss": 0.0586,
|
| 2367 |
+
"step": 32900
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 0.1613250161325016,
|
| 2371 |
+
"grad_norm": 3.101890802383423,
|
| 2372 |
+
"learning_rate": 4.1933993625217546e-05,
|
| 2373 |
+
"loss": 0.0571,
|
| 2374 |
+
"step": 33000
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.1618138798177516,
|
| 2378 |
+
"grad_norm": 0.1697547286748886,
|
| 2379 |
+
"learning_rate": 4.1909550440955045e-05,
|
| 2380 |
+
"loss": 0.0544,
|
| 2381 |
+
"step": 33100
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.1623027435030016,
|
| 2385 |
+
"grad_norm": 0.18328899145126343,
|
| 2386 |
+
"learning_rate": 4.1885107256692544e-05,
|
| 2387 |
+
"loss": 0.056,
|
| 2388 |
+
"step": 33200
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 0.16279160718825164,
|
| 2392 |
+
"grad_norm": 2.1368889808654785,
|
| 2393 |
+
"learning_rate": 4.1860664072430044e-05,
|
| 2394 |
+
"loss": 0.0604,
|
| 2395 |
+
"step": 33300
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 0.16328047087350164,
|
| 2399 |
+
"grad_norm": 0.7929971814155579,
|
| 2400 |
+
"learning_rate": 4.183622088816754e-05,
|
| 2401 |
+
"loss": 0.0513,
|
| 2402 |
+
"step": 33400
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.16376933455875164,
|
| 2406 |
+
"grad_norm": 0.4383431673049927,
|
| 2407 |
+
"learning_rate": 4.181177770390505e-05,
|
| 2408 |
+
"loss": 0.05,
|
| 2409 |
+
"step": 33500
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.16425819824400165,
|
| 2413 |
+
"grad_norm": 1.4057821035385132,
|
| 2414 |
+
"learning_rate": 4.178733451964255e-05,
|
| 2415 |
+
"loss": 0.0609,
|
| 2416 |
+
"step": 33600
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 0.16474706192925165,
|
| 2420 |
+
"grad_norm": 0.20194709300994873,
|
| 2421 |
+
"learning_rate": 4.176289133538005e-05,
|
| 2422 |
+
"loss": 0.058,
|
| 2423 |
+
"step": 33700
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 0.16523592561450165,
|
| 2427 |
+
"grad_norm": 0.19269847869873047,
|
| 2428 |
+
"learning_rate": 4.173844815111754e-05,
|
| 2429 |
+
"loss": 0.0496,
|
| 2430 |
+
"step": 33800
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 0.16572478929975165,
|
| 2434 |
+
"grad_norm": 0.0975380688905716,
|
| 2435 |
+
"learning_rate": 4.171400496685504e-05,
|
| 2436 |
+
"loss": 0.0657,
|
| 2437 |
+
"step": 33900
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 0.16621365298500165,
|
| 2441 |
+
"grad_norm": 29.133684158325195,
|
| 2442 |
+
"learning_rate": 4.1689561782592546e-05,
|
| 2443 |
+
"loss": 0.0553,
|
| 2444 |
+
"step": 34000
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 0.16670251667025165,
|
| 2448 |
+
"grad_norm": 0.3087126314640045,
|
| 2449 |
+
"learning_rate": 4.1665118598330045e-05,
|
| 2450 |
+
"loss": 0.0561,
|
| 2451 |
+
"step": 34100
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 0.16719138035550168,
|
| 2455 |
+
"grad_norm": 0.4835517108440399,
|
| 2456 |
+
"learning_rate": 4.1640675414067544e-05,
|
| 2457 |
+
"loss": 0.059,
|
| 2458 |
+
"step": 34200
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 0.16768024404075169,
|
| 2462 |
+
"grad_norm": 0.5035544633865356,
|
| 2463 |
+
"learning_rate": 4.1616232229805044e-05,
|
| 2464 |
+
"loss": 0.0455,
|
| 2465 |
+
"step": 34300
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.1681691077260017,
|
| 2469 |
+
"grad_norm": 0.10944361984729767,
|
| 2470 |
+
"learning_rate": 4.159178904554254e-05,
|
| 2471 |
+
"loss": 0.0584,
|
| 2472 |
+
"step": 34400
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 0.1686579714112517,
|
| 2476 |
+
"grad_norm": 0.16112853586673737,
|
| 2477 |
+
"learning_rate": 4.156734586128004e-05,
|
| 2478 |
+
"loss": 0.0431,
|
| 2479 |
+
"step": 34500
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 0.1691468350965017,
|
| 2483 |
+
"grad_norm": 0.18445882201194763,
|
| 2484 |
+
"learning_rate": 4.154290267701754e-05,
|
| 2485 |
+
"loss": 0.0576,
|
| 2486 |
+
"step": 34600
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.1696356987817517,
|
| 2490 |
+
"grad_norm": 0.0726209506392479,
|
| 2491 |
+
"learning_rate": 4.151845949275504e-05,
|
| 2492 |
+
"loss": 0.0597,
|
| 2493 |
+
"step": 34700
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 0.1701245624670017,
|
| 2497 |
+
"grad_norm": 1.027795672416687,
|
| 2498 |
+
"learning_rate": 4.149401630849254e-05,
|
| 2499 |
+
"loss": 0.0719,
|
| 2500 |
+
"step": 34800
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 0.1706134261522517,
|
| 2504 |
+
"grad_norm": 0.7160241603851318,
|
| 2505 |
+
"learning_rate": 4.1469573124230046e-05,
|
| 2506 |
+
"loss": 0.0632,
|
| 2507 |
+
"step": 34900
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 0.1711022898375017,
|
| 2511 |
+
"grad_norm": 0.09210514277219772,
|
| 2512 |
+
"learning_rate": 4.144512993996754e-05,
|
| 2513 |
+
"loss": 0.0522,
|
| 2514 |
+
"step": 35000
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 0.1711022898375017,
|
| 2518 |
+
"eval_accuracy": 0.9861984763051844,
|
| 2519 |
+
"eval_loss": 0.05476883053779602,
|
| 2520 |
+
"eval_runtime": 83.72,
|
| 2521 |
+
"eval_samples_per_second": 8687.422,
|
| 2522 |
+
"eval_steps_per_second": 271.488,
|
| 2523 |
+
"step": 35000
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.17159115352275173,
|
| 2527 |
+
"grad_norm": 0.4589071571826935,
|
| 2528 |
+
"learning_rate": 4.142068675570504e-05,
|
| 2529 |
+
"loss": 0.0545,
|
| 2530 |
+
"step": 35100
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.17208001720800173,
|
| 2534 |
+
"grad_norm": 9.137639999389648,
|
| 2535 |
+
"learning_rate": 4.139624357144254e-05,
|
| 2536 |
+
"loss": 0.0509,
|
| 2537 |
+
"step": 35200
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.17256888089325173,
|
| 2541 |
+
"grad_norm": 10.065511703491211,
|
| 2542 |
+
"learning_rate": 4.1371800387180043e-05,
|
| 2543 |
+
"loss": 0.0468,
|
| 2544 |
+
"step": 35300
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.17305774457850173,
|
| 2548 |
+
"grad_norm": 0.24406224489212036,
|
| 2549 |
+
"learning_rate": 4.134735720291754e-05,
|
| 2550 |
+
"loss": 0.0597,
|
| 2551 |
+
"step": 35400
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.17354660826375173,
|
| 2555 |
+
"grad_norm": 3.0440268516540527,
|
| 2556 |
+
"learning_rate": 4.132291401865504e-05,
|
| 2557 |
+
"loss": 0.0554,
|
| 2558 |
+
"step": 35500
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.17403547194900174,
|
| 2562 |
+
"grad_norm": 0.07257217913866043,
|
| 2563 |
+
"learning_rate": 4.129847083439254e-05,
|
| 2564 |
+
"loss": 0.0556,
|
| 2565 |
+
"step": 35600
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.17452433563425174,
|
| 2569 |
+
"grad_norm": 0.4422941505908966,
|
| 2570 |
+
"learning_rate": 4.1274027650130034e-05,
|
| 2571 |
+
"loss": 0.038,
|
| 2572 |
+
"step": 35700
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.17501319931950174,
|
| 2576 |
+
"grad_norm": 0.31847652792930603,
|
| 2577 |
+
"learning_rate": 4.124958446586754e-05,
|
| 2578 |
+
"loss": 0.0534,
|
| 2579 |
+
"step": 35800
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.17550206300475177,
|
| 2583 |
+
"grad_norm": 0.13630542159080505,
|
| 2584 |
+
"learning_rate": 4.122514128160504e-05,
|
| 2585 |
+
"loss": 0.0702,
|
| 2586 |
+
"step": 35900
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.17599092669000177,
|
| 2590 |
+
"grad_norm": 0.29072999954223633,
|
| 2591 |
+
"learning_rate": 4.120069809734254e-05,
|
| 2592 |
+
"loss": 0.0515,
|
| 2593 |
+
"step": 36000
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.17647979037525177,
|
| 2597 |
+
"grad_norm": 7.930593490600586,
|
| 2598 |
+
"learning_rate": 4.117625491308004e-05,
|
| 2599 |
+
"loss": 0.0494,
|
| 2600 |
+
"step": 36100
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.17696865406050177,
|
| 2604 |
+
"grad_norm": 0.2192128747701645,
|
| 2605 |
+
"learning_rate": 4.1151811728817544e-05,
|
| 2606 |
+
"loss": 0.0561,
|
| 2607 |
+
"step": 36200
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.17745751774575177,
|
| 2611 |
+
"grad_norm": 0.2658151090145111,
|
| 2612 |
+
"learning_rate": 4.112736854455504e-05,
|
| 2613 |
+
"loss": 0.0533,
|
| 2614 |
+
"step": 36300
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.17794638143100178,
|
| 2618 |
+
"grad_norm": 22.97039794921875,
|
| 2619 |
+
"learning_rate": 4.1102925360292536e-05,
|
| 2620 |
+
"loss": 0.0536,
|
| 2621 |
+
"step": 36400
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.17843524511625178,
|
| 2625 |
+
"grad_norm": 1.5622408390045166,
|
| 2626 |
+
"learning_rate": 4.1078482176030035e-05,
|
| 2627 |
+
"loss": 0.056,
|
| 2628 |
+
"step": 36500
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.17892410880150178,
|
| 2632 |
+
"grad_norm": 7.789410591125488,
|
| 2633 |
+
"learning_rate": 4.1054038991767535e-05,
|
| 2634 |
+
"loss": 0.0489,
|
| 2635 |
+
"step": 36600
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.17941297248675178,
|
| 2639 |
+
"grad_norm": 0.22617486119270325,
|
| 2640 |
+
"learning_rate": 4.102959580750504e-05,
|
| 2641 |
+
"loss": 0.0538,
|
| 2642 |
+
"step": 36700
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.1799018361720018,
|
| 2646 |
+
"grad_norm": 0.14124618470668793,
|
| 2647 |
+
"learning_rate": 4.100515262324254e-05,
|
| 2648 |
+
"loss": 0.0559,
|
| 2649 |
+
"step": 36800
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.1803906998572518,
|
| 2653 |
+
"grad_norm": 2.7587430477142334,
|
| 2654 |
+
"learning_rate": 4.098070943898004e-05,
|
| 2655 |
+
"loss": 0.0533,
|
| 2656 |
+
"step": 36900
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.18087956354250181,
|
| 2660 |
+
"grad_norm": 3.543409824371338,
|
| 2661 |
+
"learning_rate": 4.095626625471753e-05,
|
| 2662 |
+
"loss": 0.0586,
|
| 2663 |
+
"step": 37000
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.18136842722775182,
|
| 2667 |
+
"grad_norm": 0.7680773138999939,
|
| 2668 |
+
"learning_rate": 4.093182307045504e-05,
|
| 2669 |
+
"loss": 0.0506,
|
| 2670 |
+
"step": 37100
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.18185729091300182,
|
| 2674 |
+
"grad_norm": 0.12951484322547913,
|
| 2675 |
+
"learning_rate": 4.090737988619254e-05,
|
| 2676 |
+
"loss": 0.0499,
|
| 2677 |
+
"step": 37200
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.18234615459825182,
|
| 2681 |
+
"grad_norm": 0.8773353099822998,
|
| 2682 |
+
"learning_rate": 4.088293670193004e-05,
|
| 2683 |
+
"loss": 0.065,
|
| 2684 |
+
"step": 37300
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.18283501828350182,
|
| 2688 |
+
"grad_norm": 0.5426205396652222,
|
| 2689 |
+
"learning_rate": 4.0858493517667536e-05,
|
| 2690 |
+
"loss": 0.0579,
|
| 2691 |
+
"step": 37400
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.18332388196875182,
|
| 2695 |
+
"grad_norm": 0.2478882372379303,
|
| 2696 |
+
"learning_rate": 4.0834050333405035e-05,
|
| 2697 |
+
"loss": 0.0542,
|
| 2698 |
+
"step": 37500
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.18381274565400182,
|
| 2702 |
+
"grad_norm": 0.33753451704978943,
|
| 2703 |
+
"learning_rate": 4.0809607149142535e-05,
|
| 2704 |
+
"loss": 0.0388,
|
| 2705 |
+
"step": 37600
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.18430160933925185,
|
| 2709 |
+
"grad_norm": 0.5146340131759644,
|
| 2710 |
+
"learning_rate": 4.0785163964880034e-05,
|
| 2711 |
+
"loss": 0.0601,
|
| 2712 |
+
"step": 37700
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.18479047302450186,
|
| 2716 |
+
"grad_norm": 1.7206333875656128,
|
| 2717 |
+
"learning_rate": 4.076072078061753e-05,
|
| 2718 |
+
"loss": 0.0563,
|
| 2719 |
+
"step": 37800
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.18527933670975186,
|
| 2723 |
+
"grad_norm": 1.2320764064788818,
|
| 2724 |
+
"learning_rate": 4.073627759635503e-05,
|
| 2725 |
+
"loss": 0.0507,
|
| 2726 |
+
"step": 37900
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.18576820039500186,
|
| 2730 |
+
"grad_norm": 0.2969370186328888,
|
| 2731 |
+
"learning_rate": 4.071183441209254e-05,
|
| 2732 |
+
"loss": 0.0606,
|
| 2733 |
+
"step": 38000
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.18625706408025186,
|
| 2737 |
+
"grad_norm": 2.1548097133636475,
|
| 2738 |
+
"learning_rate": 4.068739122783004e-05,
|
| 2739 |
+
"loss": 0.0677,
|
| 2740 |
+
"step": 38100
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.18674592776550186,
|
| 2744 |
+
"grad_norm": 1.6644550561904907,
|
| 2745 |
+
"learning_rate": 4.066294804356753e-05,
|
| 2746 |
+
"loss": 0.0592,
|
| 2747 |
+
"step": 38200
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.18723479145075186,
|
| 2751 |
+
"grad_norm": 0.5412784814834595,
|
| 2752 |
+
"learning_rate": 4.063850485930503e-05,
|
| 2753 |
+
"loss": 0.0562,
|
| 2754 |
+
"step": 38300
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.18772365513600187,
|
| 2758 |
+
"grad_norm": 0.09251736104488373,
|
| 2759 |
+
"learning_rate": 4.061406167504253e-05,
|
| 2760 |
+
"loss": 0.0505,
|
| 2761 |
+
"step": 38400
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.1882125188212519,
|
| 2765 |
+
"grad_norm": 0.42549386620521545,
|
| 2766 |
+
"learning_rate": 4.0589618490780035e-05,
|
| 2767 |
+
"loss": 0.0668,
|
| 2768 |
+
"step": 38500
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.1887013825065019,
|
| 2772 |
+
"grad_norm": 2.619304895401001,
|
| 2773 |
+
"learning_rate": 4.0565175306517535e-05,
|
| 2774 |
+
"loss": 0.0661,
|
| 2775 |
+
"step": 38600
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.1891902461917519,
|
| 2779 |
+
"grad_norm": 0.10342859476804733,
|
| 2780 |
+
"learning_rate": 4.0540732122255034e-05,
|
| 2781 |
+
"loss": 0.0611,
|
| 2782 |
+
"step": 38700
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.1896791098770019,
|
| 2786 |
+
"grad_norm": 2.5073416233062744,
|
| 2787 |
+
"learning_rate": 4.051628893799253e-05,
|
| 2788 |
+
"loss": 0.0577,
|
| 2789 |
+
"step": 38800
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.1901679735622519,
|
| 2793 |
+
"grad_norm": 0.4327889382839203,
|
| 2794 |
+
"learning_rate": 4.049184575373003e-05,
|
| 2795 |
+
"loss": 0.057,
|
| 2796 |
+
"step": 38900
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.1906568372475019,
|
| 2800 |
+
"grad_norm": 1.2307000160217285,
|
| 2801 |
+
"learning_rate": 4.046740256946753e-05,
|
| 2802 |
+
"loss": 0.0577,
|
| 2803 |
+
"step": 39000
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.1911457009327519,
|
| 2807 |
+
"grad_norm": 0.4778403043746948,
|
| 2808 |
+
"learning_rate": 4.044295938520503e-05,
|
| 2809 |
+
"loss": 0.0568,
|
| 2810 |
+
"step": 39100
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.1916345646180019,
|
| 2814 |
+
"grad_norm": 7.530700206756592,
|
| 2815 |
+
"learning_rate": 4.041851620094253e-05,
|
| 2816 |
+
"loss": 0.0611,
|
| 2817 |
+
"step": 39200
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.1921234283032519,
|
| 2821 |
+
"grad_norm": 2.092331647872925,
|
| 2822 |
+
"learning_rate": 4.039407301668003e-05,
|
| 2823 |
+
"loss": 0.05,
|
| 2824 |
+
"step": 39300
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.19261229198850194,
|
| 2828 |
+
"grad_norm": 0.31135672330856323,
|
| 2829 |
+
"learning_rate": 4.0369629832417536e-05,
|
| 2830 |
+
"loss": 0.0527,
|
| 2831 |
+
"step": 39400
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.19310115567375194,
|
| 2835 |
+
"grad_norm": 0.9611905217170715,
|
| 2836 |
+
"learning_rate": 4.034518664815503e-05,
|
| 2837 |
+
"loss": 0.0521,
|
| 2838 |
+
"step": 39500
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.19359001935900194,
|
| 2842 |
+
"grad_norm": 0.16668935120105743,
|
| 2843 |
+
"learning_rate": 4.032074346389253e-05,
|
| 2844 |
+
"loss": 0.067,
|
| 2845 |
+
"step": 39600
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.19407888304425194,
|
| 2849 |
+
"grad_norm": 2.3609893321990967,
|
| 2850 |
+
"learning_rate": 4.029630027963003e-05,
|
| 2851 |
+
"loss": 0.0564,
|
| 2852 |
+
"step": 39700
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.19456774672950194,
|
| 2856 |
+
"grad_norm": 0.16242274641990662,
|
| 2857 |
+
"learning_rate": 4.027185709536753e-05,
|
| 2858 |
+
"loss": 0.0496,
|
| 2859 |
+
"step": 39800
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.19505661041475195,
|
| 2863 |
+
"grad_norm": 3.0595743656158447,
|
| 2864 |
+
"learning_rate": 4.024741391110503e-05,
|
| 2865 |
+
"loss": 0.057,
|
| 2866 |
+
"step": 39900
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.19554547410000195,
|
| 2870 |
+
"grad_norm": 0.2363801896572113,
|
| 2871 |
+
"learning_rate": 4.022297072684253e-05,
|
| 2872 |
+
"loss": 0.0581,
|
| 2873 |
+
"step": 40000
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.19554547410000195,
|
| 2877 |
+
"eval_accuracy": 0.9868694409956676,
|
| 2878 |
+
"eval_loss": 0.05335470661520958,
|
| 2879 |
+
"eval_runtime": 82.4289,
|
| 2880 |
+
"eval_samples_per_second": 8823.495,
|
| 2881 |
+
"eval_steps_per_second": 275.741,
|
| 2882 |
+
"step": 40000
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.19603433778525195,
|
| 2886 |
+
"grad_norm": 0.797435462474823,
|
| 2887 |
+
"learning_rate": 4.019852754258003e-05,
|
| 2888 |
+
"loss": 0.0604,
|
| 2889 |
+
"step": 40100
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 0.19652320147050195,
|
| 2893 |
+
"grad_norm": 1.976039171218872,
|
| 2894 |
+
"learning_rate": 4.0174084358317524e-05,
|
| 2895 |
+
"loss": 0.0573,
|
| 2896 |
+
"step": 40200
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.19701206515575198,
|
| 2900 |
+
"grad_norm": 0.15019837021827698,
|
| 2901 |
+
"learning_rate": 4.014964117405503e-05,
|
| 2902 |
+
"loss": 0.0526,
|
| 2903 |
+
"step": 40300
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.19750092884100198,
|
| 2907 |
+
"grad_norm": 3.6244313716888428,
|
| 2908 |
+
"learning_rate": 4.012519798979253e-05,
|
| 2909 |
+
"loss": 0.049,
|
| 2910 |
+
"step": 40400
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 0.19798979252625198,
|
| 2914 |
+
"grad_norm": 0.09811869263648987,
|
| 2915 |
+
"learning_rate": 4.010075480553003e-05,
|
| 2916 |
+
"loss": 0.0591,
|
| 2917 |
+
"step": 40500
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.19847865621150199,
|
| 2921 |
+
"grad_norm": 0.21949000656604767,
|
| 2922 |
+
"learning_rate": 4.007631162126753e-05,
|
| 2923 |
+
"loss": 0.0562,
|
| 2924 |
+
"step": 40600
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.198967519896752,
|
| 2928 |
+
"grad_norm": 0.11894066631793976,
|
| 2929 |
+
"learning_rate": 4.005186843700503e-05,
|
| 2930 |
+
"loss": 0.059,
|
| 2931 |
+
"step": 40700
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.199456383582002,
|
| 2935 |
+
"grad_norm": 0.16808772087097168,
|
| 2936 |
+
"learning_rate": 4.0027425252742526e-05,
|
| 2937 |
+
"loss": 0.0498,
|
| 2938 |
+
"step": 40800
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.199945247267252,
|
| 2942 |
+
"grad_norm": 0.22556403279304504,
|
| 2943 |
+
"learning_rate": 4.0002982068480026e-05,
|
| 2944 |
+
"loss": 0.0554,
|
| 2945 |
+
"step": 40900
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.200434110952502,
|
| 2949 |
+
"grad_norm": 0.32521432638168335,
|
| 2950 |
+
"learning_rate": 3.9978538884217525e-05,
|
| 2951 |
+
"loss": 0.0452,
|
| 2952 |
+
"step": 41000
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.20092297463775202,
|
| 2956 |
+
"grad_norm": 0.9060903191566467,
|
| 2957 |
+
"learning_rate": 3.9954095699955024e-05,
|
| 2958 |
+
"loss": 0.0509,
|
| 2959 |
+
"step": 41100
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.20141183832300202,
|
| 2963 |
+
"grad_norm": 0.13762670755386353,
|
| 2964 |
+
"learning_rate": 3.992965251569253e-05,
|
| 2965 |
+
"loss": 0.0613,
|
| 2966 |
+
"step": 41200
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.20190070200825203,
|
| 2970 |
+
"grad_norm": 0.10924024134874344,
|
| 2971 |
+
"learning_rate": 3.990520933143003e-05,
|
| 2972 |
+
"loss": 0.0484,
|
| 2973 |
+
"step": 41300
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 0.20238956569350203,
|
| 2977 |
+
"grad_norm": 0.091897152364254,
|
| 2978 |
+
"learning_rate": 3.988076614716752e-05,
|
| 2979 |
+
"loss": 0.044,
|
| 2980 |
+
"step": 41400
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 0.20287842937875203,
|
| 2984 |
+
"grad_norm": 2.079496145248413,
|
| 2985 |
+
"learning_rate": 3.985632296290502e-05,
|
| 2986 |
+
"loss": 0.0587,
|
| 2987 |
+
"step": 41500
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 0.20336729306400203,
|
| 2991 |
+
"grad_norm": 0.22760938107967377,
|
| 2992 |
+
"learning_rate": 3.983187977864253e-05,
|
| 2993 |
+
"loss": 0.0509,
|
| 2994 |
+
"step": 41600
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.20385615674925203,
|
| 2998 |
+
"grad_norm": 0.34075501561164856,
|
| 2999 |
+
"learning_rate": 3.980743659438003e-05,
|
| 3000 |
+
"loss": 0.0452,
|
| 3001 |
+
"step": 41700
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.20434502043450203,
|
| 3005 |
+
"grad_norm": 0.933623194694519,
|
| 3006 |
+
"learning_rate": 3.9782993410117526e-05,
|
| 3007 |
+
"loss": 0.0533,
|
| 3008 |
+
"step": 41800
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.20483388411975204,
|
| 3012 |
+
"grad_norm": 0.21169444918632507,
|
| 3013 |
+
"learning_rate": 3.9758550225855026e-05,
|
| 3014 |
+
"loss": 0.0453,
|
| 3015 |
+
"step": 41900
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 0.20532274780500206,
|
| 3019 |
+
"grad_norm": 0.7756932973861694,
|
| 3020 |
+
"learning_rate": 3.9734107041592525e-05,
|
| 3021 |
+
"loss": 0.0467,
|
| 3022 |
+
"step": 42000
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 0.20581161149025207,
|
| 3026 |
+
"grad_norm": 0.1386423110961914,
|
| 3027 |
+
"learning_rate": 3.9709663857330024e-05,
|
| 3028 |
+
"loss": 0.0512,
|
| 3029 |
+
"step": 42100
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 0.20630047517550207,
|
| 3033 |
+
"grad_norm": 0.09077015519142151,
|
| 3034 |
+
"learning_rate": 3.9685220673067524e-05,
|
| 3035 |
+
"loss": 0.0436,
|
| 3036 |
+
"step": 42200
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 0.20678933886075207,
|
| 3040 |
+
"grad_norm": 5.80927848815918,
|
| 3041 |
+
"learning_rate": 3.966077748880502e-05,
|
| 3042 |
+
"loss": 0.0524,
|
| 3043 |
+
"step": 42300
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 0.20727820254600207,
|
| 3047 |
+
"grad_norm": 0.38893625140190125,
|
| 3048 |
+
"learning_rate": 3.963633430454252e-05,
|
| 3049 |
+
"loss": 0.0716,
|
| 3050 |
+
"step": 42400
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.20776706623125207,
|
| 3054 |
+
"grad_norm": 0.10657148063182831,
|
| 3055 |
+
"learning_rate": 3.961189112028002e-05,
|
| 3056 |
+
"loss": 0.0521,
|
| 3057 |
+
"step": 42500
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 0.20825592991650207,
|
| 3061 |
+
"grad_norm": 2.5555455684661865,
|
| 3062 |
+
"learning_rate": 3.958744793601753e-05,
|
| 3063 |
+
"loss": 0.0603,
|
| 3064 |
+
"step": 42600
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 0.20874479360175208,
|
| 3068 |
+
"grad_norm": 0.23071211576461792,
|
| 3069 |
+
"learning_rate": 3.956300475175502e-05,
|
| 3070 |
+
"loss": 0.0534,
|
| 3071 |
+
"step": 42700
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 0.2092336572870021,
|
| 3075 |
+
"grad_norm": 10.159393310546875,
|
| 3076 |
+
"learning_rate": 3.953856156749252e-05,
|
| 3077 |
+
"loss": 0.0552,
|
| 3078 |
+
"step": 42800
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 0.2097225209722521,
|
| 3082 |
+
"grad_norm": 0.3250768482685089,
|
| 3083 |
+
"learning_rate": 3.951411838323002e-05,
|
| 3084 |
+
"loss": 0.0521,
|
| 3085 |
+
"step": 42900
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 0.2102113846575021,
|
| 3089 |
+
"grad_norm": 0.12644216418266296,
|
| 3090 |
+
"learning_rate": 3.9489675198967525e-05,
|
| 3091 |
+
"loss": 0.0549,
|
| 3092 |
+
"step": 43000
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.2107002483427521,
|
| 3096 |
+
"grad_norm": 1.32017183303833,
|
| 3097 |
+
"learning_rate": 3.9465232014705024e-05,
|
| 3098 |
+
"loss": 0.0581,
|
| 3099 |
+
"step": 43100
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 0.2111891120280021,
|
| 3103 |
+
"grad_norm": 0.1982656568288803,
|
| 3104 |
+
"learning_rate": 3.9440788830442524e-05,
|
| 3105 |
+
"loss": 0.0494,
|
| 3106 |
+
"step": 43200
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 0.21167797571325211,
|
| 3110 |
+
"grad_norm": 0.6591283679008484,
|
| 3111 |
+
"learning_rate": 3.941634564618002e-05,
|
| 3112 |
+
"loss": 0.063,
|
| 3113 |
+
"step": 43300
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 0.21216683939850212,
|
| 3117 |
+
"grad_norm": 0.3437107503414154,
|
| 3118 |
+
"learning_rate": 3.9391902461917515e-05,
|
| 3119 |
+
"loss": 0.0553,
|
| 3120 |
+
"step": 43400
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 0.21265570308375212,
|
| 3124 |
+
"grad_norm": 0.6630529165267944,
|
| 3125 |
+
"learning_rate": 3.936745927765502e-05,
|
| 3126 |
+
"loss": 0.0698,
|
| 3127 |
+
"step": 43500
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 0.21314456676900212,
|
| 3131 |
+
"grad_norm": 0.29054370522499084,
|
| 3132 |
+
"learning_rate": 3.934301609339252e-05,
|
| 3133 |
+
"loss": 0.0528,
|
| 3134 |
+
"step": 43600
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 0.21363343045425215,
|
| 3138 |
+
"grad_norm": 0.16758283972740173,
|
| 3139 |
+
"learning_rate": 3.931857290913002e-05,
|
| 3140 |
+
"loss": 0.0528,
|
| 3141 |
+
"step": 43700
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 0.21412229413950215,
|
| 3145 |
+
"grad_norm": 0.08710280060768127,
|
| 3146 |
+
"learning_rate": 3.929412972486752e-05,
|
| 3147 |
+
"loss": 0.0546,
|
| 3148 |
+
"step": 43800
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 0.21461115782475215,
|
| 3152 |
+
"grad_norm": 0.21002624928951263,
|
| 3153 |
+
"learning_rate": 3.926968654060502e-05,
|
| 3154 |
+
"loss": 0.0367,
|
| 3155 |
+
"step": 43900
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 0.21510002151000215,
|
| 3159 |
+
"grad_norm": 0.07941875606775284,
|
| 3160 |
+
"learning_rate": 3.924524335634252e-05,
|
| 3161 |
+
"loss": 0.0517,
|
| 3162 |
+
"step": 44000
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 0.21558888519525216,
|
| 3166 |
+
"grad_norm": 1.2570215463638306,
|
| 3167 |
+
"learning_rate": 3.922080017208002e-05,
|
| 3168 |
+
"loss": 0.0528,
|
| 3169 |
+
"step": 44100
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 0.21607774888050216,
|
| 3173 |
+
"grad_norm": 0.14295117557048798,
|
| 3174 |
+
"learning_rate": 3.919635698781752e-05,
|
| 3175 |
+
"loss": 0.0526,
|
| 3176 |
+
"step": 44200
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 0.21656661256575216,
|
| 3180 |
+
"grad_norm": 0.19140535593032837,
|
| 3181 |
+
"learning_rate": 3.9171913803555016e-05,
|
| 3182 |
+
"loss": 0.0543,
|
| 3183 |
+
"step": 44300
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 0.21705547625100216,
|
| 3187 |
+
"grad_norm": 0.1624194234609604,
|
| 3188 |
+
"learning_rate": 3.914747061929252e-05,
|
| 3189 |
+
"loss": 0.0552,
|
| 3190 |
+
"step": 44400
|
| 3191 |
+
},
|
| 3192 |
+
{
|
| 3193 |
+
"epoch": 0.21754433993625216,
|
| 3194 |
+
"grad_norm": 1.0798214673995972,
|
| 3195 |
+
"learning_rate": 3.912302743503002e-05,
|
| 3196 |
+
"loss": 0.0645,
|
| 3197 |
+
"step": 44500
|
| 3198 |
+
},
|
| 3199 |
+
{
|
| 3200 |
+
"epoch": 0.2180332036215022,
|
| 3201 |
+
"grad_norm": 0.15491537749767303,
|
| 3202 |
+
"learning_rate": 3.9098584250767514e-05,
|
| 3203 |
+
"loss": 0.0552,
|
| 3204 |
+
"step": 44600
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 0.2185220673067522,
|
| 3208 |
+
"grad_norm": 0.3464176058769226,
|
| 3209 |
+
"learning_rate": 3.9074141066505013e-05,
|
| 3210 |
+
"loss": 0.0559,
|
| 3211 |
+
"step": 44700
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 0.2190109309920022,
|
| 3215 |
+
"grad_norm": 4.439806938171387,
|
| 3216 |
+
"learning_rate": 3.904969788224252e-05,
|
| 3217 |
+
"loss": 0.0552,
|
| 3218 |
+
"step": 44800
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 0.2194997946772522,
|
| 3222 |
+
"grad_norm": 1.2820477485656738,
|
| 3223 |
+
"learning_rate": 3.902525469798002e-05,
|
| 3224 |
+
"loss": 0.0522,
|
| 3225 |
+
"step": 44900
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 0.2199886583625022,
|
| 3229 |
+
"grad_norm": 2.3823161125183105,
|
| 3230 |
+
"learning_rate": 3.900081151371752e-05,
|
| 3231 |
+
"loss": 0.0459,
|
| 3232 |
+
"step": 45000
|
| 3233 |
+
},
|
| 3234 |
+
{
|
| 3235 |
+
"epoch": 0.2199886583625022,
|
| 3236 |
+
"eval_accuracy": 0.9869973092665999,
|
| 3237 |
+
"eval_loss": 0.051773812621831894,
|
| 3238 |
+
"eval_runtime": 82.2788,
|
| 3239 |
+
"eval_samples_per_second": 8839.595,
|
| 3240 |
+
"eval_steps_per_second": 276.244,
|
| 3241 |
+
"step": 45000
|
| 3242 |
+
}
|
| 3243 |
+
],
|
| 3244 |
+
"logging_steps": 100,
|
| 3245 |
+
"max_steps": 204556,
|
| 3246 |
+
"num_input_tokens_seen": 0,
|
| 3247 |
+
"num_train_epochs": 1,
|
| 3248 |
+
"save_steps": 5000,
|
| 3249 |
+
"stateful_callbacks": {
|
| 3250 |
+
"TrainerControl": {
|
| 3251 |
+
"args": {
|
| 3252 |
+
"should_epoch_stop": false,
|
| 3253 |
+
"should_evaluate": false,
|
| 3254 |
+
"should_log": false,
|
| 3255 |
+
"should_save": true,
|
| 3256 |
+
"should_training_stop": false
|
| 3257 |
+
},
|
| 3258 |
+
"attributes": {}
|
| 3259 |
+
}
|
| 3260 |
+
},
|
| 3261 |
+
"total_flos": 6433270936516224.0,
|
| 3262 |
+
"train_batch_size": 32,
|
| 3263 |
+
"trial_name": null,
|
| 3264 |
+
"trial_params": null
|
| 3265 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:079adec8667cc7fc4549c52c39577a8201f99100660f3f8d567b771f0a0f96d8
|
| 3 |
+
size 5841
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|