Upload folder using huggingface_hub
Browse files- config.json +27 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- trainer_state.json +702 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"emb_size": 312,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 312,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 600,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 3,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.52.4",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 29564
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0409faa969a4ef69e4c0c5fbc8ec63fed58a3622ce7d15cbf8f83606b4e62f24
|
| 3 |
+
size 47145624
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bad4e118ed2dfb98d798815f496ad6ca665e6bcece57db051c1023808a8a1ebe
|
| 3 |
+
size 94324747
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863bf585a972b766ec763472b5b7728fac5702eefb9af6cb3b097c2d7db3a052
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386abb53807c5e72754f44db4a1774f06b3ac3f79e21b5218be31117f455858c
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_length": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_to_multiple_of": null,
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"pad_token_type_id": 0,
|
| 56 |
+
"padding_side": "right",
|
| 57 |
+
"sep_token": "[SEP]",
|
| 58 |
+
"stride": 0,
|
| 59 |
+
"strip_accents": null,
|
| 60 |
+
"tokenize_chinese_chars": true,
|
| 61 |
+
"tokenizer_class": "BertTokenizer",
|
| 62 |
+
"truncation_side": "right",
|
| 63 |
+
"truncation_strategy": "longest_first",
|
| 64 |
+
"unk_token": "[UNK]"
|
| 65 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 36872,
|
| 3 |
+
"best_metric": 0.995850622406639,
|
| 4 |
+
"best_model_checkpoint": "./rubert-good-bad/checkpoint-36872",
|
| 5 |
+
"epoch": 12.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 40224,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.14916467780429593,
|
| 14 |
+
"grad_norm": 7.852961540222168,
|
| 15 |
+
"learning_rate": 1.975188941925219e-05,
|
| 16 |
+
"loss": 0.4052,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.29832935560859186,
|
| 21 |
+
"grad_norm": 3.1220028400421143,
|
| 22 |
+
"learning_rate": 1.9503281622911697e-05,
|
| 23 |
+
"loss": 0.2525,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.44749403341288785,
|
| 28 |
+
"grad_norm": 4.411465644836426,
|
| 29 |
+
"learning_rate": 1.9254673826571203e-05,
|
| 30 |
+
"loss": 0.2181,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.5966587112171837,
|
| 35 |
+
"grad_norm": 4.210575580596924,
|
| 36 |
+
"learning_rate": 1.900606603023071e-05,
|
| 37 |
+
"loss": 0.1906,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.7458233890214797,
|
| 42 |
+
"grad_norm": 7.871537685394287,
|
| 43 |
+
"learning_rate": 1.8757458233890215e-05,
|
| 44 |
+
"loss": 0.1713,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.8949880668257757,
|
| 49 |
+
"grad_norm": 4.302709102630615,
|
| 50 |
+
"learning_rate": 1.8508850437549724e-05,
|
| 51 |
+
"loss": 0.1618,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.0,
|
| 56 |
+
"eval_accuracy": 0.9545433353536296,
|
| 57 |
+
"eval_loss": 0.11475327610969543,
|
| 58 |
+
"eval_runtime": 5.422,
|
| 59 |
+
"eval_samples_per_second": 3955.922,
|
| 60 |
+
"eval_steps_per_second": 123.755,
|
| 61 |
+
"step": 3352
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.0441527446300716,
|
| 65 |
+
"grad_norm": 6.954808235168457,
|
| 66 |
+
"learning_rate": 1.826024264120923e-05,
|
| 67 |
+
"loss": 0.1452,
|
| 68 |
+
"step": 3500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.1933174224343674,
|
| 72 |
+
"grad_norm": 6.441762924194336,
|
| 73 |
+
"learning_rate": 1.8011634844868736e-05,
|
| 74 |
+
"loss": 0.1349,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.3424821002386635,
|
| 79 |
+
"grad_norm": 2.3034775257110596,
|
| 80 |
+
"learning_rate": 1.7763027048528242e-05,
|
| 81 |
+
"loss": 0.1261,
|
| 82 |
+
"step": 4500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.4916467780429594,
|
| 86 |
+
"grad_norm": 1.0179331302642822,
|
| 87 |
+
"learning_rate": 1.751441925218775e-05,
|
| 88 |
+
"loss": 0.116,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.6408114558472553,
|
| 93 |
+
"grad_norm": 8.965306282043457,
|
| 94 |
+
"learning_rate": 1.7265811455847257e-05,
|
| 95 |
+
"loss": 0.1095,
|
| 96 |
+
"step": 5500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.7899761336515514,
|
| 100 |
+
"grad_norm": 2.703307867050171,
|
| 101 |
+
"learning_rate": 1.7017203659506763e-05,
|
| 102 |
+
"loss": 0.114,
|
| 103 |
+
"step": 6000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.9391408114558473,
|
| 107 |
+
"grad_norm": 8.306221961975098,
|
| 108 |
+
"learning_rate": 1.676859586316627e-05,
|
| 109 |
+
"loss": 0.1088,
|
| 110 |
+
"step": 6500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.0,
|
| 114 |
+
"eval_accuracy": 0.9744510233577323,
|
| 115 |
+
"eval_loss": 0.06880993396043777,
|
| 116 |
+
"eval_runtime": 5.2887,
|
| 117 |
+
"eval_samples_per_second": 4055.651,
|
| 118 |
+
"eval_steps_per_second": 126.875,
|
| 119 |
+
"step": 6704
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.088305489260143,
|
| 123 |
+
"grad_norm": 5.413713455200195,
|
| 124 |
+
"learning_rate": 1.6519988066825775e-05,
|
| 125 |
+
"loss": 0.096,
|
| 126 |
+
"step": 7000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.2374701670644392,
|
| 130 |
+
"grad_norm": 9.367850303649902,
|
| 131 |
+
"learning_rate": 1.6271380270485284e-05,
|
| 132 |
+
"loss": 0.0894,
|
| 133 |
+
"step": 7500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.386634844868735,
|
| 137 |
+
"grad_norm": 0.4695867896080017,
|
| 138 |
+
"learning_rate": 1.602277247414479e-05,
|
| 139 |
+
"loss": 0.0882,
|
| 140 |
+
"step": 8000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.535799522673031,
|
| 144 |
+
"grad_norm": 8.3032808303833,
|
| 145 |
+
"learning_rate": 1.57741646778043e-05,
|
| 146 |
+
"loss": 0.0885,
|
| 147 |
+
"step": 8500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.684964200477327,
|
| 151 |
+
"grad_norm": 3.0729820728302,
|
| 152 |
+
"learning_rate": 1.5525556881463802e-05,
|
| 153 |
+
"loss": 0.0844,
|
| 154 |
+
"step": 9000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.834128878281623,
|
| 158 |
+
"grad_norm": 6.244034767150879,
|
| 159 |
+
"learning_rate": 1.527694908512331e-05,
|
| 160 |
+
"loss": 0.0854,
|
| 161 |
+
"step": 9500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.983293556085919,
|
| 165 |
+
"grad_norm": 14.806967735290527,
|
| 166 |
+
"learning_rate": 1.5028341288782817e-05,
|
| 167 |
+
"loss": 0.0871,
|
| 168 |
+
"step": 10000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.0,
|
| 172 |
+
"eval_accuracy": 0.9813044897198004,
|
| 173 |
+
"eval_loss": 0.04988732188940048,
|
| 174 |
+
"eval_runtime": 5.3443,
|
| 175 |
+
"eval_samples_per_second": 4013.427,
|
| 176 |
+
"eval_steps_per_second": 125.554,
|
| 177 |
+
"step": 10056
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.132458233890215,
|
| 181 |
+
"grad_norm": 3.9732472896575928,
|
| 182 |
+
"learning_rate": 1.4779733492442325e-05,
|
| 183 |
+
"loss": 0.0745,
|
| 184 |
+
"step": 10500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.2816229116945106,
|
| 188 |
+
"grad_norm": 3.8117780685424805,
|
| 189 |
+
"learning_rate": 1.4531125696101831e-05,
|
| 190 |
+
"loss": 0.0697,
|
| 191 |
+
"step": 11000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.4307875894988067,
|
| 195 |
+
"grad_norm": 1.4716224670410156,
|
| 196 |
+
"learning_rate": 1.4282517899761337e-05,
|
| 197 |
+
"loss": 0.0707,
|
| 198 |
+
"step": 11500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.579952267303103,
|
| 202 |
+
"grad_norm": 1.516440749168396,
|
| 203 |
+
"learning_rate": 1.4033910103420844e-05,
|
| 204 |
+
"loss": 0.0687,
|
| 205 |
+
"step": 12000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 3.7291169451073984,
|
| 209 |
+
"grad_norm": 9.91383171081543,
|
| 210 |
+
"learning_rate": 1.378530230708035e-05,
|
| 211 |
+
"loss": 0.074,
|
| 212 |
+
"step": 12500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.8782816229116945,
|
| 216 |
+
"grad_norm": 0.14348161220550537,
|
| 217 |
+
"learning_rate": 1.3536694510739858e-05,
|
| 218 |
+
"loss": 0.0743,
|
| 219 |
+
"step": 13000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.0,
|
| 223 |
+
"eval_accuracy": 0.986386311716164,
|
| 224 |
+
"eval_loss": 0.037734854966402054,
|
| 225 |
+
"eval_runtime": 5.3579,
|
| 226 |
+
"eval_samples_per_second": 4003.226,
|
| 227 |
+
"eval_steps_per_second": 125.235,
|
| 228 |
+
"step": 13408
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.02744630071599,
|
| 232 |
+
"grad_norm": 3.358393430709839,
|
| 233 |
+
"learning_rate": 1.3288086714399364e-05,
|
| 234 |
+
"loss": 0.0687,
|
| 235 |
+
"step": 13500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 4.176610978520286,
|
| 239 |
+
"grad_norm": 11.118879318237305,
|
| 240 |
+
"learning_rate": 1.3039478918058872e-05,
|
| 241 |
+
"loss": 0.0572,
|
| 242 |
+
"step": 14000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.325775656324582,
|
| 246 |
+
"grad_norm": 3.1460227966308594,
|
| 247 |
+
"learning_rate": 1.2790871121718378e-05,
|
| 248 |
+
"loss": 0.0604,
|
| 249 |
+
"step": 14500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.4749403341288785,
|
| 253 |
+
"grad_norm": 5.454690933227539,
|
| 254 |
+
"learning_rate": 1.2542263325377885e-05,
|
| 255 |
+
"loss": 0.0576,
|
| 256 |
+
"step": 15000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.624105011933175,
|
| 260 |
+
"grad_norm": 5.29376220703125,
|
| 261 |
+
"learning_rate": 1.2293655529037391e-05,
|
| 262 |
+
"loss": 0.0619,
|
| 263 |
+
"step": 15500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.77326968973747,
|
| 267 |
+
"grad_norm": 0.4051016867160797,
|
| 268 |
+
"learning_rate": 1.2045047732696897e-05,
|
| 269 |
+
"loss": 0.0591,
|
| 270 |
+
"step": 16000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.922434367541766,
|
| 274 |
+
"grad_norm": 3.9757938385009766,
|
| 275 |
+
"learning_rate": 1.1796439936356405e-05,
|
| 276 |
+
"loss": 0.0566,
|
| 277 |
+
"step": 16500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 5.0,
|
| 281 |
+
"eval_accuracy": 0.9901627115483239,
|
| 282 |
+
"eval_loss": 0.02832028456032276,
|
| 283 |
+
"eval_runtime": 5.3872,
|
| 284 |
+
"eval_samples_per_second": 3981.457,
|
| 285 |
+
"eval_steps_per_second": 124.554,
|
| 286 |
+
"step": 16760
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 5.071599045346062,
|
| 290 |
+
"grad_norm": 5.767542839050293,
|
| 291 |
+
"learning_rate": 1.154783214001591e-05,
|
| 292 |
+
"loss": 0.0554,
|
| 293 |
+
"step": 17000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.220763723150358,
|
| 297 |
+
"grad_norm": 0.15083061158657074,
|
| 298 |
+
"learning_rate": 1.1299224343675418e-05,
|
| 299 |
+
"loss": 0.0507,
|
| 300 |
+
"step": 17500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.369928400954654,
|
| 304 |
+
"grad_norm": 3.9027342796325684,
|
| 305 |
+
"learning_rate": 1.1050616547334924e-05,
|
| 306 |
+
"loss": 0.0526,
|
| 307 |
+
"step": 18000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.519093078758949,
|
| 311 |
+
"grad_norm": 0.34978094696998596,
|
| 312 |
+
"learning_rate": 1.0802008750994433e-05,
|
| 313 |
+
"loss": 0.0489,
|
| 314 |
+
"step": 18500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.6682577565632455,
|
| 318 |
+
"grad_norm": 24.885211944580078,
|
| 319 |
+
"learning_rate": 1.0553400954653938e-05,
|
| 320 |
+
"loss": 0.0496,
|
| 321 |
+
"step": 19000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.817422434367542,
|
| 325 |
+
"grad_norm": 3.8451194763183594,
|
| 326 |
+
"learning_rate": 1.0304793158313447e-05,
|
| 327 |
+
"loss": 0.0462,
|
| 328 |
+
"step": 19500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 5.966587112171838,
|
| 332 |
+
"grad_norm": 2.7605342864990234,
|
| 333 |
+
"learning_rate": 1.0056185361972953e-05,
|
| 334 |
+
"loss": 0.0524,
|
| 335 |
+
"step": 20000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 6.0,
|
| 339 |
+
"eval_accuracy": 0.9920276003543289,
|
| 340 |
+
"eval_loss": 0.023812290281057358,
|
| 341 |
+
"eval_runtime": 5.7441,
|
| 342 |
+
"eval_samples_per_second": 3734.067,
|
| 343 |
+
"eval_steps_per_second": 116.815,
|
| 344 |
+
"step": 20112
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.115751789976134,
|
| 348 |
+
"grad_norm": 12.299605369567871,
|
| 349 |
+
"learning_rate": 9.807577565632459e-06,
|
| 350 |
+
"loss": 0.0451,
|
| 351 |
+
"step": 20500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.26491646778043,
|
| 355 |
+
"grad_norm": 0.014037308283150196,
|
| 356 |
+
"learning_rate": 9.558969769291967e-06,
|
| 357 |
+
"loss": 0.0439,
|
| 358 |
+
"step": 21000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.414081145584726,
|
| 362 |
+
"grad_norm": 4.366552829742432,
|
| 363 |
+
"learning_rate": 9.310361972951472e-06,
|
| 364 |
+
"loss": 0.0447,
|
| 365 |
+
"step": 21500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 6.563245823389021,
|
| 369 |
+
"grad_norm": 0.3234240412712097,
|
| 370 |
+
"learning_rate": 9.06175417661098e-06,
|
| 371 |
+
"loss": 0.0474,
|
| 372 |
+
"step": 22000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 6.712410501193317,
|
| 376 |
+
"grad_norm": 5.625737190246582,
|
| 377 |
+
"learning_rate": 8.813146380270486e-06,
|
| 378 |
+
"loss": 0.0401,
|
| 379 |
+
"step": 22500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 6.861575178997613,
|
| 383 |
+
"grad_norm": 1.9961190223693848,
|
| 384 |
+
"learning_rate": 8.564538583929994e-06,
|
| 385 |
+
"loss": 0.0442,
|
| 386 |
+
"step": 23000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 7.0,
|
| 390 |
+
"eval_accuracy": 0.9929134225371812,
|
| 391 |
+
"eval_loss": 0.02055698074400425,
|
| 392 |
+
"eval_runtime": 5.2686,
|
| 393 |
+
"eval_samples_per_second": 4071.116,
|
| 394 |
+
"eval_steps_per_second": 127.359,
|
| 395 |
+
"step": 23464
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.0107398568019095,
|
| 399 |
+
"grad_norm": 0.7006446123123169,
|
| 400 |
+
"learning_rate": 8.3159307875895e-06,
|
| 401 |
+
"loss": 0.0446,
|
| 402 |
+
"step": 23500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 7.159904534606206,
|
| 406 |
+
"grad_norm": 0.009974448010325432,
|
| 407 |
+
"learning_rate": 8.067322991249006e-06,
|
| 408 |
+
"loss": 0.0353,
|
| 409 |
+
"step": 24000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 7.309069212410501,
|
| 413 |
+
"grad_norm": 13.073637962341309,
|
| 414 |
+
"learning_rate": 7.818715194908513e-06,
|
| 415 |
+
"loss": 0.0327,
|
| 416 |
+
"step": 24500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 7.458233890214797,
|
| 420 |
+
"grad_norm": 0.47934669256210327,
|
| 421 |
+
"learning_rate": 7.57010739856802e-06,
|
| 422 |
+
"loss": 0.0415,
|
| 423 |
+
"step": 25000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 7.607398568019093,
|
| 427 |
+
"grad_norm": 9.82204532623291,
|
| 428 |
+
"learning_rate": 7.321499602227527e-06,
|
| 429 |
+
"loss": 0.0396,
|
| 430 |
+
"step": 25500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 7.756563245823389,
|
| 434 |
+
"grad_norm": 3.7507293224334717,
|
| 435 |
+
"learning_rate": 7.0728918058870335e-06,
|
| 436 |
+
"loss": 0.0419,
|
| 437 |
+
"step": 26000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 7.905727923627685,
|
| 441 |
+
"grad_norm": 12.792013168334961,
|
| 442 |
+
"learning_rate": 6.82428400954654e-06,
|
| 443 |
+
"loss": 0.0437,
|
| 444 |
+
"step": 26500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 8.0,
|
| 448 |
+
"eval_accuracy": 0.9944053335819851,
|
| 449 |
+
"eval_loss": 0.017598649486899376,
|
| 450 |
+
"eval_runtime": 5.3397,
|
| 451 |
+
"eval_samples_per_second": 4016.869,
|
| 452 |
+
"eval_steps_per_second": 125.662,
|
| 453 |
+
"step": 26816
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 8.05489260143198,
|
| 457 |
+
"grad_norm": 2.062351703643799,
|
| 458 |
+
"learning_rate": 6.575676213206047e-06,
|
| 459 |
+
"loss": 0.037,
|
| 460 |
+
"step": 27000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 8.204057279236277,
|
| 464 |
+
"grad_norm": 7.230820178985596,
|
| 465 |
+
"learning_rate": 6.327068416865554e-06,
|
| 466 |
+
"loss": 0.0363,
|
| 467 |
+
"step": 27500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 8.353221957040573,
|
| 471 |
+
"grad_norm": 9.108207702636719,
|
| 472 |
+
"learning_rate": 6.078460620525061e-06,
|
| 473 |
+
"loss": 0.0343,
|
| 474 |
+
"step": 28000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 8.50238663484487,
|
| 478 |
+
"grad_norm": 3.1893274784088135,
|
| 479 |
+
"learning_rate": 5.829852824184567e-06,
|
| 480 |
+
"loss": 0.0374,
|
| 481 |
+
"step": 28500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 8.651551312649165,
|
| 485 |
+
"grad_norm": 7.297391414642334,
|
| 486 |
+
"learning_rate": 5.581245027844073e-06,
|
| 487 |
+
"loss": 0.0371,
|
| 488 |
+
"step": 29000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 8.80071599045346,
|
| 492 |
+
"grad_norm": 0.8091713190078735,
|
| 493 |
+
"learning_rate": 5.33263723150358e-06,
|
| 494 |
+
"loss": 0.0322,
|
| 495 |
+
"step": 29500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.949880668257757,
|
| 499 |
+
"grad_norm": 9.286097526550293,
|
| 500 |
+
"learning_rate": 5.084029435163087e-06,
|
| 501 |
+
"loss": 0.0366,
|
| 502 |
+
"step": 30000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 9.0,
|
| 506 |
+
"eval_accuracy": 0.995104666884237,
|
| 507 |
+
"eval_loss": 0.015091103501617908,
|
| 508 |
+
"eval_runtime": 5.5227,
|
| 509 |
+
"eval_samples_per_second": 3883.811,
|
| 510 |
+
"eval_steps_per_second": 121.499,
|
| 511 |
+
"step": 30168
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 9.099045346062052,
|
| 515 |
+
"grad_norm": 2.9286885261535645,
|
| 516 |
+
"learning_rate": 4.835421638822594e-06,
|
| 517 |
+
"loss": 0.0295,
|
| 518 |
+
"step": 30500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 9.24821002386635,
|
| 522 |
+
"grad_norm": 0.06805476546287537,
|
| 523 |
+
"learning_rate": 4.5868138424821005e-06,
|
| 524 |
+
"loss": 0.0337,
|
| 525 |
+
"step": 31000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 9.397374701670644,
|
| 529 |
+
"grad_norm": 1.571494698524475,
|
| 530 |
+
"learning_rate": 4.338206046141607e-06,
|
| 531 |
+
"loss": 0.0331,
|
| 532 |
+
"step": 31500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 9.54653937947494,
|
| 536 |
+
"grad_norm": 0.042112987488508224,
|
| 537 |
+
"learning_rate": 4.089598249801114e-06,
|
| 538 |
+
"loss": 0.0298,
|
| 539 |
+
"step": 32000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.695704057279237,
|
| 543 |
+
"grad_norm": 0.060358405113220215,
|
| 544 |
+
"learning_rate": 3.840990453460621e-06,
|
| 545 |
+
"loss": 0.0354,
|
| 546 |
+
"step": 32500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 9.844868735083532,
|
| 550 |
+
"grad_norm": 17.142175674438477,
|
| 551 |
+
"learning_rate": 3.5923826571201277e-06,
|
| 552 |
+
"loss": 0.0315,
|
| 553 |
+
"step": 33000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 9.994033412887829,
|
| 557 |
+
"grad_norm": 0.03519833832979202,
|
| 558 |
+
"learning_rate": 3.3437748607796345e-06,
|
| 559 |
+
"loss": 0.0341,
|
| 560 |
+
"step": 33500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 10.0,
|
| 564 |
+
"eval_accuracy": 0.9953844002051377,
|
| 565 |
+
"eval_loss": 0.014557760208845139,
|
| 566 |
+
"eval_runtime": 5.4843,
|
| 567 |
+
"eval_samples_per_second": 3911.0,
|
| 568 |
+
"eval_steps_per_second": 122.35,
|
| 569 |
+
"step": 33520
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 10.143198090692124,
|
| 573 |
+
"grad_norm": 8.01278018951416,
|
| 574 |
+
"learning_rate": 3.0951670644391413e-06,
|
| 575 |
+
"loss": 0.0291,
|
| 576 |
+
"step": 34000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 10.292362768496421,
|
| 580 |
+
"grad_norm": 1.2233223915100098,
|
| 581 |
+
"learning_rate": 2.8465592680986476e-06,
|
| 582 |
+
"loss": 0.0295,
|
| 583 |
+
"step": 34500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 10.441527446300716,
|
| 587 |
+
"grad_norm": 0.13490265607833862,
|
| 588 |
+
"learning_rate": 2.5979514717581544e-06,
|
| 589 |
+
"loss": 0.0314,
|
| 590 |
+
"step": 35000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 10.590692124105011,
|
| 594 |
+
"grad_norm": 22.723793029785156,
|
| 595 |
+
"learning_rate": 2.349343675417661e-06,
|
| 596 |
+
"loss": 0.0323,
|
| 597 |
+
"step": 35500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 10.739856801909308,
|
| 601 |
+
"grad_norm": 0.0038608636241406202,
|
| 602 |
+
"learning_rate": 2.100735879077168e-06,
|
| 603 |
+
"loss": 0.0304,
|
| 604 |
+
"step": 36000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 10.889021479713604,
|
| 608 |
+
"grad_norm": 0.08787856996059418,
|
| 609 |
+
"learning_rate": 1.8521280827366748e-06,
|
| 610 |
+
"loss": 0.031,
|
| 611 |
+
"step": 36500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 11.0,
|
| 615 |
+
"eval_accuracy": 0.995850622406639,
|
| 616 |
+
"eval_loss": 0.013228594325482845,
|
| 617 |
+
"eval_runtime": 5.4141,
|
| 618 |
+
"eval_samples_per_second": 3961.682,
|
| 619 |
+
"eval_steps_per_second": 123.935,
|
| 620 |
+
"step": 36872
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 11.0381861575179,
|
| 624 |
+
"grad_norm": 0.11552688479423523,
|
| 625 |
+
"learning_rate": 1.6035202863961815e-06,
|
| 626 |
+
"loss": 0.0318,
|
| 627 |
+
"step": 37000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 11.187350835322196,
|
| 631 |
+
"grad_norm": 0.19442684948444366,
|
| 632 |
+
"learning_rate": 1.3549124900556881e-06,
|
| 633 |
+
"loss": 0.027,
|
| 634 |
+
"step": 37500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 11.336515513126491,
|
| 638 |
+
"grad_norm": 10.4265718460083,
|
| 639 |
+
"learning_rate": 1.106304693715195e-06,
|
| 640 |
+
"loss": 0.027,
|
| 641 |
+
"step": 38000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 11.485680190930788,
|
| 645 |
+
"grad_norm": 0.03579527512192726,
|
| 646 |
+
"learning_rate": 8.576968973747017e-07,
|
| 647 |
+
"loss": 0.0325,
|
| 648 |
+
"step": 38500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 11.634844868735083,
|
| 652 |
+
"grad_norm": 3.7483468055725098,
|
| 653 |
+
"learning_rate": 6.090891010342085e-07,
|
| 654 |
+
"loss": 0.0267,
|
| 655 |
+
"step": 39000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 11.78400954653938,
|
| 659 |
+
"grad_norm": 0.031889185309410095,
|
| 660 |
+
"learning_rate": 3.604813046937152e-07,
|
| 661 |
+
"loss": 0.0268,
|
| 662 |
+
"step": 39500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 11.933174224343675,
|
| 666 |
+
"grad_norm": 0.04797011986374855,
|
| 667 |
+
"learning_rate": 1.1187350835322197e-07,
|
| 668 |
+
"loss": 0.0273,
|
| 669 |
+
"step": 40000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 12.0,
|
| 673 |
+
"eval_accuracy": 0.9957573779663388,
|
| 674 |
+
"eval_loss": 0.013085125014185905,
|
| 675 |
+
"eval_runtime": 5.2528,
|
| 676 |
+
"eval_samples_per_second": 4083.366,
|
| 677 |
+
"eval_steps_per_second": 127.742,
|
| 678 |
+
"step": 40224
|
| 679 |
+
}
|
| 680 |
+
],
|
| 681 |
+
"logging_steps": 500,
|
| 682 |
+
"max_steps": 40224,
|
| 683 |
+
"num_input_tokens_seen": 0,
|
| 684 |
+
"num_train_epochs": 12,
|
| 685 |
+
"save_steps": 500,
|
| 686 |
+
"stateful_callbacks": {
|
| 687 |
+
"TrainerControl": {
|
| 688 |
+
"args": {
|
| 689 |
+
"should_epoch_stop": false,
|
| 690 |
+
"should_evaluate": false,
|
| 691 |
+
"should_log": false,
|
| 692 |
+
"should_save": true,
|
| 693 |
+
"should_training_stop": true
|
| 694 |
+
},
|
| 695 |
+
"attributes": {}
|
| 696 |
+
}
|
| 697 |
+
},
|
| 698 |
+
"total_flos": 1159020529550640.0,
|
| 699 |
+
"train_batch_size": 32,
|
| 700 |
+
"trial_name": null,
|
| 701 |
+
"trial_params": null
|
| 702 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ce5a2c79f950e777178c6537e8e427ee8065fe88e4d1be81254cbe000e9efe6
|
| 3 |
+
size 5713
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|