Training checkpoint - Epoch 2, Step 17184
Browse files- checkpoint-17184/1_Pooling/config.json +10 -0
- checkpoint-17184/config.json +25 -0
- checkpoint-17184/config_sentence_transformers.json +14 -0
- checkpoint-17184/model.safetensors +3 -0
- checkpoint-17184/modules.json +20 -0
- checkpoint-17184/optimizer.pt +3 -0
- checkpoint-17184/rng_state.pth +3 -0
- checkpoint-17184/scaler.pt +3 -0
- checkpoint-17184/scheduler.pt +3 -0
- checkpoint-17184/sentence_bert_config.json +4 -0
- checkpoint-17184/special_tokens_map.json +37 -0
- checkpoint-17184/tokenizer.json +0 -0
- checkpoint-17184/tokenizer_config.json +65 -0
- checkpoint-17184/trainer_state.json +585 -0
- checkpoint-17184/training_args.bin +3 -0
- checkpoint-17184/training_metrics.json +210 -0
- checkpoint-17184/vocab.txt +0 -0
checkpoint-17184/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 384,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
checkpoint-17184/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 384,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 1536,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 6,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.53.3",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
checkpoint-17184/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "5.2.0",
|
| 4 |
+
"transformers": "4.53.3",
|
| 5 |
+
"pytorch": "2.6.0+cu124"
|
| 6 |
+
},
|
| 7 |
+
"model_type": "SentenceTransformer",
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
checkpoint-17184/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdfba72e7d5000568aab7b878e46a335936d8f854edb6f9b270d853b189fb4f9
|
| 3 |
+
size 90864192
|
checkpoint-17184/modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
checkpoint-17184/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c6b4b288364bb47ebe137d6a7107fab69008b25a2e9837c02b39eaaee6dc140
|
| 3 |
+
size 180607738
|
checkpoint-17184/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:279319e2116492ab86301a1c5048ea3031551ab7f9374abc050eaa8f83cd30e8
|
| 3 |
+
size 14244
|
checkpoint-17184/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aafced1390dd3d6677f7b3f58e0ed7db0bea7ff623e447e9a1f6f192118820d
|
| 3 |
+
size 988
|
checkpoint-17184/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5725d0998c9c256beddf9773464c0517b248a2ea3ab3f24d02bd0a22e80a0970
|
| 3 |
+
size 1064
|
checkpoint-17184/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 256,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-17184/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-17184/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-17184/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 |
+
"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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_length": 128,
|
| 51 |
+
"model_max_length": 256,
|
| 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 |
+
}
|
checkpoint-17184/trainer_state.json
ADDED
|
@@ -0,0 +1,585 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 17184,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00011638733705772812,
|
| 14 |
+
"grad_norm": 8.116299629211426,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.7266,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05819366852886406,
|
| 21 |
+
"grad_norm": 57.76313781738281,
|
| 22 |
+
"learning_rate": 1.732045163543243e-06,
|
| 23 |
+
"loss": 3.7373,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05819366852886406,
|
| 28 |
+
"eval_cosine_accuracy": 0.9404736757278442,
|
| 29 |
+
"eval_loss": 2.536726713180542,
|
| 30 |
+
"eval_runtime": 23.2615,
|
| 31 |
+
"eval_samples_per_second": 406.594,
|
| 32 |
+
"eval_steps_per_second": 1.591,
|
| 33 |
+
"step": 500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11638733705772812,
|
| 37 |
+
"grad_norm": 5.569820880889893,
|
| 38 |
+
"learning_rate": 3.4780584332440925e-06,
|
| 39 |
+
"loss": 2.8655,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.11638733705772812,
|
| 44 |
+
"eval_cosine_accuracy": 0.9364559054374695,
|
| 45 |
+
"eval_loss": 2.6046745777130127,
|
| 46 |
+
"eval_runtime": 23.4136,
|
| 47 |
+
"eval_samples_per_second": 403.953,
|
| 48 |
+
"eval_steps_per_second": 1.58,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.17458100558659218,
|
| 53 |
+
"grad_norm": 5.892590045928955,
|
| 54 |
+
"learning_rate": 5.224071702944943e-06,
|
| 55 |
+
"loss": 2.3859,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.17458100558659218,
|
| 60 |
+
"eval_cosine_accuracy": 0.9412137866020203,
|
| 61 |
+
"eval_loss": 2.540637969970703,
|
| 62 |
+
"eval_runtime": 23.458,
|
| 63 |
+
"eval_samples_per_second": 403.189,
|
| 64 |
+
"eval_steps_per_second": 1.577,
|
| 65 |
+
"step": 1500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.23277467411545624,
|
| 69 |
+
"grad_norm": 41.33493423461914,
|
| 70 |
+
"learning_rate": 6.970084972645793e-06,
|
| 71 |
+
"loss": 2.1884,
|
| 72 |
+
"step": 2000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.23277467411545624,
|
| 76 |
+
"eval_cosine_accuracy": 0.9451258182525635,
|
| 77 |
+
"eval_loss": 2.5318424701690674,
|
| 78 |
+
"eval_runtime": 23.2789,
|
| 79 |
+
"eval_samples_per_second": 406.29,
|
| 80 |
+
"eval_steps_per_second": 1.589,
|
| 81 |
+
"step": 2000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2909683426443203,
|
| 85 |
+
"grad_norm": 15.76939582824707,
|
| 86 |
+
"learning_rate": 8.71260621580724e-06,
|
| 87 |
+
"loss": 1.9576,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2909683426443203,
|
| 92 |
+
"eval_cosine_accuracy": 0.9467117786407471,
|
| 93 |
+
"eval_loss": 2.474266767501831,
|
| 94 |
+
"eval_runtime": 23.3675,
|
| 95 |
+
"eval_samples_per_second": 404.75,
|
| 96 |
+
"eval_steps_per_second": 1.583,
|
| 97 |
+
"step": 2500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.34916201117318435,
|
| 101 |
+
"grad_norm": 7.4116950035095215,
|
| 102 |
+
"learning_rate": 1.045861948550809e-05,
|
| 103 |
+
"loss": 1.8211,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.34916201117318435,
|
| 108 |
+
"eval_cosine_accuracy": 0.9435398578643799,
|
| 109 |
+
"eval_loss": 2.547072649002075,
|
| 110 |
+
"eval_runtime": 23.3771,
|
| 111 |
+
"eval_samples_per_second": 404.583,
|
| 112 |
+
"eval_steps_per_second": 1.583,
|
| 113 |
+
"step": 3000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.4073556797020484,
|
| 117 |
+
"grad_norm": 25.99747657775879,
|
| 118 |
+
"learning_rate": 1.2204632755208939e-05,
|
| 119 |
+
"loss": 1.6603,
|
| 120 |
+
"step": 3500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.4073556797020484,
|
| 124 |
+
"eval_cosine_accuracy": 0.9489321112632751,
|
| 125 |
+
"eval_loss": 2.472174644470215,
|
| 126 |
+
"eval_runtime": 23.4652,
|
| 127 |
+
"eval_samples_per_second": 403.065,
|
| 128 |
+
"eval_steps_per_second": 1.577,
|
| 129 |
+
"step": 3500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4655493482309125,
|
| 133 |
+
"grad_norm": 5.763104438781738,
|
| 134 |
+
"learning_rate": 1.395064602490979e-05,
|
| 135 |
+
"loss": 1.596,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4655493482309125,
|
| 140 |
+
"eval_cosine_accuracy": 0.9438570737838745,
|
| 141 |
+
"eval_loss": 2.5426251888275146,
|
| 142 |
+
"eval_runtime": 23.3963,
|
| 143 |
+
"eval_samples_per_second": 404.252,
|
| 144 |
+
"eval_steps_per_second": 1.581,
|
| 145 |
+
"step": 4000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.5237430167597765,
|
| 149 |
+
"grad_norm": 4.893315315246582,
|
| 150 |
+
"learning_rate": 1.5693167268071237e-05,
|
| 151 |
+
"loss": 1.5379,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.5237430167597765,
|
| 156 |
+
"eval_cosine_accuracy": 0.9473461508750916,
|
| 157 |
+
"eval_loss": 2.4768149852752686,
|
| 158 |
+
"eval_runtime": 23.5926,
|
| 159 |
+
"eval_samples_per_second": 400.888,
|
| 160 |
+
"eval_steps_per_second": 1.568,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.5819366852886406,
|
| 165 |
+
"grad_norm": 43.368614196777344,
|
| 166 |
+
"learning_rate": 1.7439180537772086e-05,
|
| 167 |
+
"loss": 1.5397,
|
| 168 |
+
"step": 5000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.5819366852886406,
|
| 172 |
+
"eval_cosine_accuracy": 0.9487206339836121,
|
| 173 |
+
"eval_loss": 2.4771170616149902,
|
| 174 |
+
"eval_runtime": 23.566,
|
| 175 |
+
"eval_samples_per_second": 401.341,
|
| 176 |
+
"eval_steps_per_second": 1.57,
|
| 177 |
+
"step": 5000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6401303538175046,
|
| 181 |
+
"grad_norm": 0.21546457707881927,
|
| 182 |
+
"learning_rate": 1.9185193807472936e-05,
|
| 183 |
+
"loss": 1.381,
|
| 184 |
+
"step": 5500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6401303538175046,
|
| 188 |
+
"eval_cosine_accuracy": 0.9412137866020203,
|
| 189 |
+
"eval_loss": 2.6126925945281982,
|
| 190 |
+
"eval_runtime": 23.871,
|
| 191 |
+
"eval_samples_per_second": 396.213,
|
| 192 |
+
"eval_steps_per_second": 1.55,
|
| 193 |
+
"step": 5500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.6983240223463687,
|
| 197 |
+
"grad_norm": 27.70214080810547,
|
| 198 |
+
"learning_rate": 2.0931207077173788e-05,
|
| 199 |
+
"loss": 1.4407,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.6983240223463687,
|
| 204 |
+
"eval_cosine_accuracy": 0.9492493271827698,
|
| 205 |
+
"eval_loss": 2.457711935043335,
|
| 206 |
+
"eval_runtime": 23.5818,
|
| 207 |
+
"eval_samples_per_second": 401.072,
|
| 208 |
+
"eval_steps_per_second": 1.569,
|
| 209 |
+
"step": 6000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.7565176908752328,
|
| 213 |
+
"grad_norm": 0.6600456237792969,
|
| 214 |
+
"learning_rate": 2.2677220346874637e-05,
|
| 215 |
+
"loss": 1.3692,
|
| 216 |
+
"step": 6500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.7565176908752328,
|
| 220 |
+
"eval_cosine_accuracy": 0.9438570737838745,
|
| 221 |
+
"eval_loss": 2.48168683052063,
|
| 222 |
+
"eval_runtime": 23.5688,
|
| 223 |
+
"eval_samples_per_second": 401.294,
|
| 224 |
+
"eval_steps_per_second": 1.57,
|
| 225 |
+
"step": 6500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8147113594040968,
|
| 229 |
+
"grad_norm": 15.486236572265625,
|
| 230 |
+
"learning_rate": 2.4419741590036085e-05,
|
| 231 |
+
"loss": 1.2731,
|
| 232 |
+
"step": 7000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.8147113594040968,
|
| 236 |
+
"eval_cosine_accuracy": 0.943751335144043,
|
| 237 |
+
"eval_loss": 2.5139832496643066,
|
| 238 |
+
"eval_runtime": 23.6217,
|
| 239 |
+
"eval_samples_per_second": 400.394,
|
| 240 |
+
"eval_steps_per_second": 1.566,
|
| 241 |
+
"step": 7000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.8729050279329609,
|
| 245 |
+
"grad_norm": 13.570350646972656,
|
| 246 |
+
"learning_rate": 2.6165754859736934e-05,
|
| 247 |
+
"loss": 1.223,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.8729050279329609,
|
| 252 |
+
"eval_cosine_accuracy": 0.9494607448577881,
|
| 253 |
+
"eval_loss": 2.4431588649749756,
|
| 254 |
+
"eval_runtime": 23.5387,
|
| 255 |
+
"eval_samples_per_second": 401.807,
|
| 256 |
+
"eval_steps_per_second": 1.572,
|
| 257 |
+
"step": 7500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.931098696461825,
|
| 261 |
+
"grad_norm": 4.8542633056640625,
|
| 262 |
+
"learning_rate": 2.7911768129437783e-05,
|
| 263 |
+
"loss": 1.1982,
|
| 264 |
+
"step": 8000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.931098696461825,
|
| 268 |
+
"eval_cosine_accuracy": 0.9420596361160278,
|
| 269 |
+
"eval_loss": 2.5187907218933105,
|
| 270 |
+
"eval_runtime": 23.6462,
|
| 271 |
+
"eval_samples_per_second": 399.98,
|
| 272 |
+
"eval_steps_per_second": 1.565,
|
| 273 |
+
"step": 8000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.9892923649906891,
|
| 277 |
+
"grad_norm": 36.649906158447266,
|
| 278 |
+
"learning_rate": 2.9657781399138632e-05,
|
| 279 |
+
"loss": 1.1693,
|
| 280 |
+
"step": 8500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.9892923649906891,
|
| 284 |
+
"eval_cosine_accuracy": 0.9469232559204102,
|
| 285 |
+
"eval_loss": 2.4668424129486084,
|
| 286 |
+
"eval_runtime": 23.9878,
|
| 287 |
+
"eval_samples_per_second": 394.284,
|
| 288 |
+
"eval_steps_per_second": 1.542,
|
| 289 |
+
"step": 8500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.047486033519553,
|
| 293 |
+
"grad_norm": 14.853631019592285,
|
| 294 |
+
"learning_rate": 2.9982089877066498e-05,
|
| 295 |
+
"loss": 1.1045,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.047486033519553,
|
| 300 |
+
"eval_cosine_accuracy": 0.9422711133956909,
|
| 301 |
+
"eval_loss": 2.6691627502441406,
|
| 302 |
+
"eval_runtime": 23.6926,
|
| 303 |
+
"eval_samples_per_second": 399.197,
|
| 304 |
+
"eval_steps_per_second": 1.562,
|
| 305 |
+
"step": 9000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.105679702048417,
|
| 309 |
+
"grad_norm": 15.238059997558594,
|
| 310 |
+
"learning_rate": 2.9909854135876818e-05,
|
| 311 |
+
"loss": 0.9695,
|
| 312 |
+
"step": 9500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.105679702048417,
|
| 316 |
+
"eval_cosine_accuracy": 0.9454430341720581,
|
| 317 |
+
"eval_loss": 2.5817720890045166,
|
| 318 |
+
"eval_runtime": 23.7575,
|
| 319 |
+
"eval_samples_per_second": 398.106,
|
| 320 |
+
"eval_steps_per_second": 1.557,
|
| 321 |
+
"step": 9500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.1638733705772812,
|
| 325 |
+
"grad_norm": 0.052569806575775146,
|
| 326 |
+
"learning_rate": 2.9782179657431337e-05,
|
| 327 |
+
"loss": 0.9498,
|
| 328 |
+
"step": 10000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.1638733705772812,
|
| 332 |
+
"eval_cosine_accuracy": 0.9443857073783875,
|
| 333 |
+
"eval_loss": 2.5811285972595215,
|
| 334 |
+
"eval_runtime": 24.7703,
|
| 335 |
+
"eval_samples_per_second": 381.828,
|
| 336 |
+
"eval_steps_per_second": 1.494,
|
| 337 |
+
"step": 10000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.2220670391061452,
|
| 341 |
+
"grad_norm": 5.478404998779297,
|
| 342 |
+
"learning_rate": 2.9599629603266307e-05,
|
| 343 |
+
"loss": 1.0137,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.2220670391061452,
|
| 348 |
+
"eval_cosine_accuracy": 0.9443857073783875,
|
| 349 |
+
"eval_loss": 2.588257312774658,
|
| 350 |
+
"eval_runtime": 23.6811,
|
| 351 |
+
"eval_samples_per_second": 399.391,
|
| 352 |
+
"eval_steps_per_second": 1.562,
|
| 353 |
+
"step": 10500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.2802607076350094,
|
| 357 |
+
"grad_norm": 22.226593017578125,
|
| 358 |
+
"learning_rate": 2.93628816501217e-05,
|
| 359 |
+
"loss": 1.0031,
|
| 360 |
+
"step": 11000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.2802607076350094,
|
| 364 |
+
"eval_cosine_accuracy": 0.943751335144043,
|
| 365 |
+
"eval_loss": 2.626814842224121,
|
| 366 |
+
"eval_runtime": 24.0203,
|
| 367 |
+
"eval_samples_per_second": 393.75,
|
| 368 |
+
"eval_steps_per_second": 1.54,
|
| 369 |
+
"step": 11000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.3384543761638734,
|
| 373 |
+
"grad_norm": 18.21111488342285,
|
| 374 |
+
"learning_rate": 2.907281467246193e-05,
|
| 375 |
+
"loss": 0.9391,
|
| 376 |
+
"step": 11500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.3384543761638734,
|
| 380 |
+
"eval_cosine_accuracy": 0.9466060400009155,
|
| 381 |
+
"eval_loss": 2.5278029441833496,
|
| 382 |
+
"eval_runtime": 23.6597,
|
| 383 |
+
"eval_samples_per_second": 399.751,
|
| 384 |
+
"eval_steps_per_second": 1.564,
|
| 385 |
+
"step": 11500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.3966480446927374,
|
| 389 |
+
"grad_norm": 13.534646987915039,
|
| 390 |
+
"learning_rate": 2.873050547984859e-05,
|
| 391 |
+
"loss": 0.9508,
|
| 392 |
+
"step": 12000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.3966480446927374,
|
| 396 |
+
"eval_cosine_accuracy": 0.9545358419418335,
|
| 397 |
+
"eval_loss": 2.387155532836914,
|
| 398 |
+
"eval_runtime": 24.4172,
|
| 399 |
+
"eval_samples_per_second": 387.35,
|
| 400 |
+
"eval_steps_per_second": 1.515,
|
| 401 |
+
"step": 12000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.4548417132216014,
|
| 405 |
+
"grad_norm": 4.7890801429748535,
|
| 406 |
+
"learning_rate": 2.8337224819522882e-05,
|
| 407 |
+
"loss": 0.8975,
|
| 408 |
+
"step": 12500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.4548417132216014,
|
| 412 |
+
"eval_cosine_accuracy": 0.9511524438858032,
|
| 413 |
+
"eval_loss": 2.531130313873291,
|
| 414 |
+
"eval_runtime": 23.694,
|
| 415 |
+
"eval_samples_per_second": 399.173,
|
| 416 |
+
"eval_steps_per_second": 1.562,
|
| 417 |
+
"step": 12500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.5130353817504656,
|
| 421 |
+
"grad_norm": 39.141204833984375,
|
| 422 |
+
"learning_rate": 2.7894432659037298e-05,
|
| 423 |
+
"loss": 0.9006,
|
| 424 |
+
"step": 13000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.5130353817504656,
|
| 428 |
+
"eval_cosine_accuracy": 0.9498836994171143,
|
| 429 |
+
"eval_loss": 2.4939699172973633,
|
| 430 |
+
"eval_runtime": 23.6563,
|
| 431 |
+
"eval_samples_per_second": 399.809,
|
| 432 |
+
"eval_steps_per_second": 1.564,
|
| 433 |
+
"step": 13000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.5712290502793296,
|
| 437 |
+
"grad_norm": 5.199061393737793,
|
| 438 |
+
"learning_rate": 2.740480067649311e-05,
|
| 439 |
+
"loss": 0.9293,
|
| 440 |
+
"step": 13500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.5712290502793296,
|
| 444 |
+
"eval_cosine_accuracy": 0.9558045864105225,
|
| 445 |
+
"eval_loss": 2.3089163303375244,
|
| 446 |
+
"eval_runtime": 23.8068,
|
| 447 |
+
"eval_samples_per_second": 397.282,
|
| 448 |
+
"eval_steps_per_second": 1.554,
|
| 449 |
+
"step": 13500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.6294227188081938,
|
| 453 |
+
"grad_norm": 13.1704683303833,
|
| 454 |
+
"learning_rate": 2.6868184678138455e-05,
|
| 455 |
+
"loss": 0.9289,
|
| 456 |
+
"step": 14000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.6294227188081938,
|
| 460 |
+
"eval_cosine_accuracy": 0.9548530578613281,
|
| 461 |
+
"eval_loss": 2.4148993492126465,
|
| 462 |
+
"eval_runtime": 23.6698,
|
| 463 |
+
"eval_samples_per_second": 399.58,
|
| 464 |
+
"eval_steps_per_second": 1.563,
|
| 465 |
+
"step": 14000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6876163873370578,
|
| 469 |
+
"grad_norm": 4.7075276374816895,
|
| 470 |
+
"learning_rate": 2.628751066655086e-05,
|
| 471 |
+
"loss": 0.9206,
|
| 472 |
+
"step": 14500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.6876163873370578,
|
| 476 |
+
"eval_cosine_accuracy": 0.9537957310676575,
|
| 477 |
+
"eval_loss": 2.3580262660980225,
|
| 478 |
+
"eval_runtime": 23.8237,
|
| 479 |
+
"eval_samples_per_second": 396.999,
|
| 480 |
+
"eval_steps_per_second": 1.553,
|
| 481 |
+
"step": 14500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.7458100558659218,
|
| 485 |
+
"grad_norm": 17.35055923461914,
|
| 486 |
+
"learning_rate": 2.5664934265693082e-05,
|
| 487 |
+
"loss": 0.9212,
|
| 488 |
+
"step": 15000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.7458100558659218,
|
| 492 |
+
"eval_cosine_accuracy": 0.9540072083473206,
|
| 493 |
+
"eval_loss": 2.4263856410980225,
|
| 494 |
+
"eval_runtime": 24.2294,
|
| 495 |
+
"eval_samples_per_second": 390.352,
|
| 496 |
+
"eval_steps_per_second": 1.527,
|
| 497 |
+
"step": 15000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.8040037243947857,
|
| 501 |
+
"grad_norm": 4.250364303588867,
|
| 502 |
+
"learning_rate": 2.5002766652889314e-05,
|
| 503 |
+
"loss": 0.8754,
|
| 504 |
+
"step": 15500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.8040037243947857,
|
| 508 |
+
"eval_cosine_accuracy": 0.9536899924278259,
|
| 509 |
+
"eval_loss": 2.4231128692626953,
|
| 510 |
+
"eval_runtime": 23.6253,
|
| 511 |
+
"eval_samples_per_second": 400.334,
|
| 512 |
+
"eval_steps_per_second": 1.566,
|
| 513 |
+
"step": 15500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.86219739292365,
|
| 517 |
+
"grad_norm": 7.852247714996338,
|
| 518 |
+
"learning_rate": 2.4303465979090062e-05,
|
| 519 |
+
"loss": 0.8594,
|
| 520 |
+
"step": 16000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.86219739292365,
|
| 524 |
+
"eval_cosine_accuracy": 0.954430103302002,
|
| 525 |
+
"eval_loss": 2.395444393157959,
|
| 526 |
+
"eval_runtime": 23.5537,
|
| 527 |
+
"eval_samples_per_second": 401.551,
|
| 528 |
+
"eval_steps_per_second": 1.571,
|
| 529 |
+
"step": 16000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.920391061452514,
|
| 533 |
+
"grad_norm": 0.0026893599424511194,
|
| 534 |
+
"learning_rate": 2.3571128596645755e-05,
|
| 535 |
+
"loss": 0.8732,
|
| 536 |
+
"step": 16500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.920391061452514,
|
| 540 |
+
"eval_cosine_accuracy": 0.9555931687355042,
|
| 541 |
+
"eval_loss": 2.3798062801361084,
|
| 542 |
+
"eval_runtime": 23.6528,
|
| 543 |
+
"eval_samples_per_second": 399.868,
|
| 544 |
+
"eval_steps_per_second": 1.564,
|
| 545 |
+
"step": 16500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.9785847299813781,
|
| 549 |
+
"grad_norm": 1.7342342138290405,
|
| 550 |
+
"learning_rate": 2.2805538836485382e-05,
|
| 551 |
+
"loss": 0.8562,
|
| 552 |
+
"step": 17000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.9785847299813781,
|
| 556 |
+
"eval_cosine_accuracy": 0.9586593508720398,
|
| 557 |
+
"eval_loss": 2.3469178676605225,
|
| 558 |
+
"eval_runtime": 23.7353,
|
| 559 |
+
"eval_samples_per_second": 398.479,
|
| 560 |
+
"eval_steps_per_second": 1.559,
|
| 561 |
+
"step": 17000
|
| 562 |
+
}
|
| 563 |
+
],
|
| 564 |
+
"logging_steps": 500,
|
| 565 |
+
"max_steps": 34368,
|
| 566 |
+
"num_input_tokens_seen": 0,
|
| 567 |
+
"num_train_epochs": 4,
|
| 568 |
+
"save_steps": 500,
|
| 569 |
+
"stateful_callbacks": {
|
| 570 |
+
"TrainerControl": {
|
| 571 |
+
"args": {
|
| 572 |
+
"should_epoch_stop": false,
|
| 573 |
+
"should_evaluate": false,
|
| 574 |
+
"should_log": false,
|
| 575 |
+
"should_save": true,
|
| 576 |
+
"should_training_stop": false
|
| 577 |
+
},
|
| 578 |
+
"attributes": {}
|
| 579 |
+
}
|
| 580 |
+
},
|
| 581 |
+
"total_flos": 0.0,
|
| 582 |
+
"train_batch_size": 256,
|
| 583 |
+
"trial_name": null,
|
| 584 |
+
"trial_params": null
|
| 585 |
+
}
|
checkpoint-17184/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4d75a4b36857a175cdfda60f40427b0ec82ca5e37197466aed6d4cb12e0e9a8
|
| 3 |
+
size 5688
|
checkpoint-17184/training_metrics.json
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metrics_history": [
|
| 3 |
+
{
|
| 4 |
+
"epoch": 0.05819366852886406,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"eval_loss": 2.536726713180542,
|
| 7 |
+
"eval_cosine_accuracy": 0.9404736757278442
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"epoch": 0.11638733705772812,
|
| 11 |
+
"global_step": 1000,
|
| 12 |
+
"eval_loss": 2.6046745777130127,
|
| 13 |
+
"eval_cosine_accuracy": 0.9364559054374695
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 0.17458100558659218,
|
| 17 |
+
"global_step": 1500,
|
| 18 |
+
"eval_loss": 2.540637969970703,
|
| 19 |
+
"eval_cosine_accuracy": 0.9412137866020203
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.23277467411545624,
|
| 23 |
+
"global_step": 2000,
|
| 24 |
+
"eval_loss": 2.5318424701690674,
|
| 25 |
+
"eval_cosine_accuracy": 0.9451258182525635
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2909683426443203,
|
| 29 |
+
"global_step": 2500,
|
| 30 |
+
"eval_loss": 2.474266767501831,
|
| 31 |
+
"eval_cosine_accuracy": 0.9467117786407471
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.34916201117318435,
|
| 35 |
+
"global_step": 3000,
|
| 36 |
+
"eval_loss": 2.547072649002075,
|
| 37 |
+
"eval_cosine_accuracy": 0.9435398578643799
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4073556797020484,
|
| 41 |
+
"global_step": 3500,
|
| 42 |
+
"eval_loss": 2.472174644470215,
|
| 43 |
+
"eval_cosine_accuracy": 0.9489321112632751
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.4655493482309125,
|
| 47 |
+
"global_step": 4000,
|
| 48 |
+
"eval_loss": 2.5426251888275146,
|
| 49 |
+
"eval_cosine_accuracy": 0.9438570737838745
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.5237430167597765,
|
| 53 |
+
"global_step": 4500,
|
| 54 |
+
"eval_loss": 2.4768149852752686,
|
| 55 |
+
"eval_cosine_accuracy": 0.9473461508750916
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.5819366852886406,
|
| 59 |
+
"global_step": 5000,
|
| 60 |
+
"eval_loss": 2.4771170616149902,
|
| 61 |
+
"eval_cosine_accuracy": 0.9487206339836121
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.6401303538175046,
|
| 65 |
+
"global_step": 5500,
|
| 66 |
+
"eval_loss": 2.6126925945281982,
|
| 67 |
+
"eval_cosine_accuracy": 0.9412137866020203
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.6983240223463687,
|
| 71 |
+
"global_step": 6000,
|
| 72 |
+
"eval_loss": 2.457711935043335,
|
| 73 |
+
"eval_cosine_accuracy": 0.9492493271827698
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7565176908752328,
|
| 77 |
+
"global_step": 6500,
|
| 78 |
+
"eval_loss": 2.48168683052063,
|
| 79 |
+
"eval_cosine_accuracy": 0.9438570737838745
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8147113594040968,
|
| 83 |
+
"global_step": 7000,
|
| 84 |
+
"eval_loss": 2.5139832496643066,
|
| 85 |
+
"eval_cosine_accuracy": 0.943751335144043
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.8729050279329609,
|
| 89 |
+
"global_step": 7500,
|
| 90 |
+
"eval_loss": 2.4431588649749756,
|
| 91 |
+
"eval_cosine_accuracy": 0.9494607448577881
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.931098696461825,
|
| 95 |
+
"global_step": 8000,
|
| 96 |
+
"eval_loss": 2.5187907218933105,
|
| 97 |
+
"eval_cosine_accuracy": 0.9420596361160278
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.9892923649906891,
|
| 101 |
+
"global_step": 8500,
|
| 102 |
+
"eval_loss": 2.4668424129486084,
|
| 103 |
+
"eval_cosine_accuracy": 0.9469232559204102
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.047486033519553,
|
| 107 |
+
"global_step": 9000,
|
| 108 |
+
"eval_loss": 2.6691627502441406,
|
| 109 |
+
"eval_cosine_accuracy": 0.9422711133956909
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.105679702048417,
|
| 113 |
+
"global_step": 9500,
|
| 114 |
+
"eval_loss": 2.5817720890045166,
|
| 115 |
+
"eval_cosine_accuracy": 0.9454430341720581
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.1638733705772812,
|
| 119 |
+
"global_step": 10000,
|
| 120 |
+
"eval_loss": 2.5811285972595215,
|
| 121 |
+
"eval_cosine_accuracy": 0.9443857073783875
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.2220670391061452,
|
| 125 |
+
"global_step": 10500,
|
| 126 |
+
"eval_loss": 2.588257312774658,
|
| 127 |
+
"eval_cosine_accuracy": 0.9443857073783875
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.2802607076350094,
|
| 131 |
+
"global_step": 11000,
|
| 132 |
+
"eval_loss": 2.626814842224121,
|
| 133 |
+
"eval_cosine_accuracy": 0.943751335144043
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.3384543761638734,
|
| 137 |
+
"global_step": 11500,
|
| 138 |
+
"eval_loss": 2.5278029441833496,
|
| 139 |
+
"eval_cosine_accuracy": 0.9466060400009155
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.3966480446927374,
|
| 143 |
+
"global_step": 12000,
|
| 144 |
+
"eval_loss": 2.387155532836914,
|
| 145 |
+
"eval_cosine_accuracy": 0.9545358419418335
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.4548417132216014,
|
| 149 |
+
"global_step": 12500,
|
| 150 |
+
"eval_loss": 2.531130313873291,
|
| 151 |
+
"eval_cosine_accuracy": 0.9511524438858032
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.5130353817504656,
|
| 155 |
+
"global_step": 13000,
|
| 156 |
+
"eval_loss": 2.4939699172973633,
|
| 157 |
+
"eval_cosine_accuracy": 0.9498836994171143
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.5712290502793296,
|
| 161 |
+
"global_step": 13500,
|
| 162 |
+
"eval_loss": 2.3089163303375244,
|
| 163 |
+
"eval_cosine_accuracy": 0.9558045864105225
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.6294227188081938,
|
| 167 |
+
"global_step": 14000,
|
| 168 |
+
"eval_loss": 2.4148993492126465,
|
| 169 |
+
"eval_cosine_accuracy": 0.9548530578613281
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.6876163873370578,
|
| 173 |
+
"global_step": 14500,
|
| 174 |
+
"eval_loss": 2.3580262660980225,
|
| 175 |
+
"eval_cosine_accuracy": 0.9537957310676575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.7458100558659218,
|
| 179 |
+
"global_step": 15000,
|
| 180 |
+
"eval_loss": 2.4263856410980225,
|
| 181 |
+
"eval_cosine_accuracy": 0.9540072083473206
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.8040037243947857,
|
| 185 |
+
"global_step": 15500,
|
| 186 |
+
"eval_loss": 2.4231128692626953,
|
| 187 |
+
"eval_cosine_accuracy": 0.9536899924278259
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.86219739292365,
|
| 191 |
+
"global_step": 16000,
|
| 192 |
+
"eval_loss": 2.395444393157959,
|
| 193 |
+
"eval_cosine_accuracy": 0.954430103302002
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.920391061452514,
|
| 197 |
+
"global_step": 16500,
|
| 198 |
+
"eval_loss": 2.3798062801361084,
|
| 199 |
+
"eval_cosine_accuracy": 0.9555931687355042
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.9785847299813781,
|
| 203 |
+
"global_step": 17000,
|
| 204 |
+
"eval_loss": 2.3469178676605225,
|
| 205 |
+
"eval_cosine_accuracy": 0.9586593508720398
|
| 206 |
+
}
|
| 207 |
+
],
|
| 208 |
+
"current_epoch": 2,
|
| 209 |
+
"global_step": 17184
|
| 210 |
+
}
|
checkpoint-17184/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|