Training checkpoint - Epoch 1, Step 16609
Browse files- checkpoint-16609/1_Pooling/config.json +10 -0
- checkpoint-16609/config.json +25 -0
- checkpoint-16609/config_sentence_transformers.json +14 -0
- checkpoint-16609/model.safetensors +3 -0
- checkpoint-16609/modules.json +20 -0
- checkpoint-16609/optimizer.pt +3 -0
- checkpoint-16609/rng_state.pth +3 -0
- checkpoint-16609/scaler.pt +3 -0
- checkpoint-16609/scheduler.pt +3 -0
- checkpoint-16609/sentence_bert_config.json +4 -0
- checkpoint-16609/special_tokens_map.json +37 -0
- checkpoint-16609/tokenizer.json +0 -0
- checkpoint-16609/tokenizer_config.json +65 -0
- checkpoint-16609/trainer_state.json +569 -0
- checkpoint-16609/training_args.bin +3 -0
- checkpoint-16609/training_metrics.json +204 -0
- checkpoint-16609/vocab.txt +0 -0
checkpoint-16609/1_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-16609/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-16609/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-16609/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e288403d199e9f6b79aa020f989b194500ab43c4b4c401976d352c2b2038b471
|
| 3 |
+
size 90864192
|
checkpoint-16609/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-16609/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fde4c6e4046cb331de0c731acf5fc1800b0c7fee27507a832793978c71d130ff
|
| 3 |
+
size 180607738
|
checkpoint-16609/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da3dff65e46c310b208013f49891cbf8944a7704bbc7caf15b4e1fa1c5e50ebe
|
| 3 |
+
size 14244
|
checkpoint-16609/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:126761bb1281071868213f097b51a2eb5808e64ae879199f0302ba858ed41bbb
|
| 3 |
+
size 988
|
checkpoint-16609/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18c36647aea3449fc984077f794b0d6285e67f44f4abccbdebcbf884d0aa28c7
|
| 3 |
+
size 1064
|
checkpoint-16609/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 256,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-16609/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-16609/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16609/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-16609/trainer_state.json
ADDED
|
@@ -0,0 +1,569 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 16609,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 6.020832078993317e-05,
|
| 14 |
+
"grad_norm": 0.38543766736984253,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.0947,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.030104160394966585,
|
| 21 |
+
"grad_norm": 0.10387147963047028,
|
| 22 |
+
"learning_rate": 9.013728323699423e-07,
|
| 23 |
+
"loss": 0.0776,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.030104160394966585,
|
| 28 |
+
"eval_cosine_accuracy": 0.9121845364570618,
|
| 29 |
+
"eval_loss": 0.03408537805080414,
|
| 30 |
+
"eval_runtime": 49.9493,
|
| 31 |
+
"eval_samples_per_second": 378.704,
|
| 32 |
+
"eval_steps_per_second": 1.482,
|
| 33 |
+
"step": 500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06020832078993317,
|
| 37 |
+
"grad_norm": 0.0778941884636879,
|
| 38 |
+
"learning_rate": 1.8045520231213872e-06,
|
| 39 |
+
"loss": 0.0395,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.06020832078993317,
|
| 44 |
+
"eval_cosine_accuracy": 0.9305813312530518,
|
| 45 |
+
"eval_loss": 0.03211512416601181,
|
| 46 |
+
"eval_runtime": 50.2255,
|
| 47 |
+
"eval_samples_per_second": 376.622,
|
| 48 |
+
"eval_steps_per_second": 1.473,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.09031248118489975,
|
| 53 |
+
"grad_norm": 0.07489586621522903,
|
| 54 |
+
"learning_rate": 2.7077312138728323e-06,
|
| 55 |
+
"loss": 0.035,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.09031248118489975,
|
| 60 |
+
"eval_cosine_accuracy": 0.9341157078742981,
|
| 61 |
+
"eval_loss": 0.03070036694407463,
|
| 62 |
+
"eval_runtime": 49.7769,
|
| 63 |
+
"eval_samples_per_second": 380.016,
|
| 64 |
+
"eval_steps_per_second": 1.487,
|
| 65 |
+
"step": 1500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.12041664157986634,
|
| 69 |
+
"grad_norm": 0.11629298329353333,
|
| 70 |
+
"learning_rate": 3.6109104046242777e-06,
|
| 71 |
+
"loss": 0.0314,
|
| 72 |
+
"step": 2000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12041664157986634,
|
| 76 |
+
"eval_cosine_accuracy": 0.9239204525947571,
|
| 77 |
+
"eval_loss": 0.032454561442136765,
|
| 78 |
+
"eval_runtime": 50.1109,
|
| 79 |
+
"eval_samples_per_second": 377.483,
|
| 80 |
+
"eval_steps_per_second": 1.477,
|
| 81 |
+
"step": 2000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15052080197483292,
|
| 85 |
+
"grad_norm": 0.08288636803627014,
|
| 86 |
+
"learning_rate": 4.514089595375723e-06,
|
| 87 |
+
"loss": 0.0283,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.15052080197483292,
|
| 92 |
+
"eval_cosine_accuracy": 0.9068829417228699,
|
| 93 |
+
"eval_loss": 0.0350261889398098,
|
| 94 |
+
"eval_runtime": 49.5334,
|
| 95 |
+
"eval_samples_per_second": 381.884,
|
| 96 |
+
"eval_steps_per_second": 1.494,
|
| 97 |
+
"step": 2500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1806249623697995,
|
| 101 |
+
"grad_norm": 0.09410930424928665,
|
| 102 |
+
"learning_rate": 5.4172687861271674e-06,
|
| 103 |
+
"loss": 0.0258,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.1806249623697995,
|
| 108 |
+
"eval_cosine_accuracy": 0.8916126489639282,
|
| 109 |
+
"eval_loss": 0.037413690239191055,
|
| 110 |
+
"eval_runtime": 50.1483,
|
| 111 |
+
"eval_samples_per_second": 377.201,
|
| 112 |
+
"eval_steps_per_second": 1.476,
|
| 113 |
+
"step": 3000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.2107291227647661,
|
| 117 |
+
"grad_norm": 0.0764598697423935,
|
| 118 |
+
"learning_rate": 6.320447976878613e-06,
|
| 119 |
+
"loss": 0.0236,
|
| 120 |
+
"step": 3500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.2107291227647661,
|
| 124 |
+
"eval_cosine_accuracy": 0.867868959903717,
|
| 125 |
+
"eval_loss": 0.04107580706477165,
|
| 126 |
+
"eval_runtime": 49.5476,
|
| 127 |
+
"eval_samples_per_second": 381.774,
|
| 128 |
+
"eval_steps_per_second": 1.494,
|
| 129 |
+
"step": 3500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24083328315973268,
|
| 133 |
+
"grad_norm": 0.09663169085979462,
|
| 134 |
+
"learning_rate": 7.2236271676300576e-06,
|
| 135 |
+
"loss": 0.0219,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.24083328315973268,
|
| 140 |
+
"eval_cosine_accuracy": 0.8625220656394958,
|
| 141 |
+
"eval_loss": 0.042248476296663284,
|
| 142 |
+
"eval_runtime": 50.2346,
|
| 143 |
+
"eval_samples_per_second": 376.553,
|
| 144 |
+
"eval_steps_per_second": 1.473,
|
| 145 |
+
"step": 4000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.2709374435546993,
|
| 149 |
+
"grad_norm": 0.10593143850564957,
|
| 150 |
+
"learning_rate": 8.126806358381503e-06,
|
| 151 |
+
"loss": 0.0205,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.2709374435546993,
|
| 156 |
+
"eval_cosine_accuracy": 0.8380987048149109,
|
| 157 |
+
"eval_loss": 0.04543215036392212,
|
| 158 |
+
"eval_runtime": 49.5535,
|
| 159 |
+
"eval_samples_per_second": 381.729,
|
| 160 |
+
"eval_steps_per_second": 1.493,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.30104160394966584,
|
| 165 |
+
"grad_norm": 0.07745221257209778,
|
| 166 |
+
"learning_rate": 9.02998554913295e-06,
|
| 167 |
+
"loss": 0.019,
|
| 168 |
+
"step": 5000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.30104160394966584,
|
| 172 |
+
"eval_cosine_accuracy": 0.8265440464019775,
|
| 173 |
+
"eval_loss": 0.04734260216355324,
|
| 174 |
+
"eval_runtime": 49.6392,
|
| 175 |
+
"eval_samples_per_second": 381.07,
|
| 176 |
+
"eval_steps_per_second": 1.491,
|
| 177 |
+
"step": 5000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.33114576434463244,
|
| 181 |
+
"grad_norm": 0.09874160587787628,
|
| 182 |
+
"learning_rate": 9.933164739884392e-06,
|
| 183 |
+
"loss": 0.0179,
|
| 184 |
+
"step": 5500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.33114576434463244,
|
| 188 |
+
"eval_cosine_accuracy": 0.812904953956604,
|
| 189 |
+
"eval_loss": 0.048521969467401505,
|
| 190 |
+
"eval_runtime": 50.9191,
|
| 191 |
+
"eval_samples_per_second": 371.491,
|
| 192 |
+
"eval_steps_per_second": 1.453,
|
| 193 |
+
"step": 5500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.361249924739599,
|
| 197 |
+
"grad_norm": 0.08646717667579651,
|
| 198 |
+
"learning_rate": 1.0836343930635839e-05,
|
| 199 |
+
"loss": 0.017,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.361249924739599,
|
| 204 |
+
"eval_cosine_accuracy": 0.8010784387588501,
|
| 205 |
+
"eval_loss": 0.051017291843891144,
|
| 206 |
+
"eval_runtime": 49.7081,
|
| 207 |
+
"eval_samples_per_second": 380.541,
|
| 208 |
+
"eval_steps_per_second": 1.489,
|
| 209 |
+
"step": 6000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.3913540851345656,
|
| 213 |
+
"grad_norm": 0.10478880256414413,
|
| 214 |
+
"learning_rate": 1.1739523121387283e-05,
|
| 215 |
+
"loss": 0.0161,
|
| 216 |
+
"step": 6500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.3913540851345656,
|
| 220 |
+
"eval_cosine_accuracy": 0.7926956415176392,
|
| 221 |
+
"eval_loss": 0.05125237628817558,
|
| 222 |
+
"eval_runtime": 50.4664,
|
| 223 |
+
"eval_samples_per_second": 374.824,
|
| 224 |
+
"eval_steps_per_second": 1.466,
|
| 225 |
+
"step": 6500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.4214582455295322,
|
| 229 |
+
"grad_norm": 0.09687662869691849,
|
| 230 |
+
"learning_rate": 1.2642702312138728e-05,
|
| 231 |
+
"loss": 0.0153,
|
| 232 |
+
"step": 7000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.4214582455295322,
|
| 236 |
+
"eval_cosine_accuracy": 0.7693597078323364,
|
| 237 |
+
"eval_loss": 0.053376998752355576,
|
| 238 |
+
"eval_runtime": 50.2601,
|
| 239 |
+
"eval_samples_per_second": 376.362,
|
| 240 |
+
"eval_steps_per_second": 1.472,
|
| 241 |
+
"step": 7000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.45156240592449876,
|
| 245 |
+
"grad_norm": 0.12575113773345947,
|
| 246 |
+
"learning_rate": 1.3545881502890174e-05,
|
| 247 |
+
"loss": 0.0145,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.45156240592449876,
|
| 252 |
+
"eval_cosine_accuracy": 0.7683628797531128,
|
| 253 |
+
"eval_loss": 0.05461883544921875,
|
| 254 |
+
"eval_runtime": 49.9602,
|
| 255 |
+
"eval_samples_per_second": 378.621,
|
| 256 |
+
"eval_steps_per_second": 1.481,
|
| 257 |
+
"step": 7500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.48166656631946536,
|
| 261 |
+
"grad_norm": 0.09359786659479141,
|
| 262 |
+
"learning_rate": 1.4449060693641619e-05,
|
| 263 |
+
"loss": 0.0139,
|
| 264 |
+
"step": 8000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.48166656631946536,
|
| 268 |
+
"eval_cosine_accuracy": 0.7625628709793091,
|
| 269 |
+
"eval_loss": 0.05498296022415161,
|
| 270 |
+
"eval_runtime": 49.4526,
|
| 271 |
+
"eval_samples_per_second": 382.508,
|
| 272 |
+
"eval_steps_per_second": 1.496,
|
| 273 |
+
"step": 8000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.5117707267144319,
|
| 277 |
+
"grad_norm": 0.08199989050626755,
|
| 278 |
+
"learning_rate": 1.5352239884393065e-05,
|
| 279 |
+
"loss": 0.0132,
|
| 280 |
+
"step": 8500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.5117707267144319,
|
| 284 |
+
"eval_cosine_accuracy": 0.7560831904411316,
|
| 285 |
+
"eval_loss": 0.055622003972530365,
|
| 286 |
+
"eval_runtime": 51.0115,
|
| 287 |
+
"eval_samples_per_second": 370.818,
|
| 288 |
+
"eval_steps_per_second": 1.451,
|
| 289 |
+
"step": 8500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5418748871093986,
|
| 293 |
+
"grad_norm": 0.08838484436273575,
|
| 294 |
+
"learning_rate": 1.625541907514451e-05,
|
| 295 |
+
"loss": 0.0128,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5418748871093986,
|
| 300 |
+
"eval_cosine_accuracy": 0.7378675937652588,
|
| 301 |
+
"eval_loss": 0.056548163294792175,
|
| 302 |
+
"eval_runtime": 50.9508,
|
| 303 |
+
"eval_samples_per_second": 371.26,
|
| 304 |
+
"eval_steps_per_second": 1.452,
|
| 305 |
+
"step": 9000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.5719790475043651,
|
| 309 |
+
"grad_norm": 0.09884914755821228,
|
| 310 |
+
"learning_rate": 1.7158598265895954e-05,
|
| 311 |
+
"loss": 0.0123,
|
| 312 |
+
"step": 9500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.5719790475043651,
|
| 316 |
+
"eval_cosine_accuracy": 0.7324753999710083,
|
| 317 |
+
"eval_loss": 0.05744454637169838,
|
| 318 |
+
"eval_runtime": 49.4469,
|
| 319 |
+
"eval_samples_per_second": 382.552,
|
| 320 |
+
"eval_steps_per_second": 1.497,
|
| 321 |
+
"step": 9500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6020832078993317,
|
| 325 |
+
"grad_norm": 0.0804782584309578,
|
| 326 |
+
"learning_rate": 1.80617774566474e-05,
|
| 327 |
+
"loss": 0.0119,
|
| 328 |
+
"step": 10000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.6020832078993317,
|
| 332 |
+
"eval_cosine_accuracy": 0.7181566953659058,
|
| 333 |
+
"eval_loss": 0.058585748076438904,
|
| 334 |
+
"eval_runtime": 50.1288,
|
| 335 |
+
"eval_samples_per_second": 377.348,
|
| 336 |
+
"eval_steps_per_second": 1.476,
|
| 337 |
+
"step": 10000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.6321873682942982,
|
| 341 |
+
"grad_norm": 0.09254036843776703,
|
| 342 |
+
"learning_rate": 1.8964956647398844e-05,
|
| 343 |
+
"loss": 0.0114,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.6321873682942982,
|
| 348 |
+
"eval_cosine_accuracy": 0.725497305393219,
|
| 349 |
+
"eval_loss": 0.05707884952425957,
|
| 350 |
+
"eval_runtime": 49.3636,
|
| 351 |
+
"eval_samples_per_second": 383.197,
|
| 352 |
+
"eval_steps_per_second": 1.499,
|
| 353 |
+
"step": 10500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6622915286892649,
|
| 357 |
+
"grad_norm": 0.13671717047691345,
|
| 358 |
+
"learning_rate": 1.986813583815029e-05,
|
| 359 |
+
"loss": 0.0111,
|
| 360 |
+
"step": 11000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6622915286892649,
|
| 364 |
+
"eval_cosine_accuracy": 0.7044723629951477,
|
| 365 |
+
"eval_loss": 0.0592338964343071,
|
| 366 |
+
"eval_runtime": 51.6332,
|
| 367 |
+
"eval_samples_per_second": 366.353,
|
| 368 |
+
"eval_steps_per_second": 1.433,
|
| 369 |
+
"step": 11000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.6923956890842314,
|
| 373 |
+
"grad_norm": 0.09350993484258652,
|
| 374 |
+
"learning_rate": 2.0771315028901736e-05,
|
| 375 |
+
"loss": 0.0108,
|
| 376 |
+
"step": 11500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.6923956890842314,
|
| 380 |
+
"eval_cosine_accuracy": 0.712537944316864,
|
| 381 |
+
"eval_loss": 0.05877280980348587,
|
| 382 |
+
"eval_runtime": 49.2617,
|
| 383 |
+
"eval_samples_per_second": 383.99,
|
| 384 |
+
"eval_steps_per_second": 1.502,
|
| 385 |
+
"step": 11500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.722499849479198,
|
| 389 |
+
"grad_norm": 0.08495638519525528,
|
| 390 |
+
"learning_rate": 2.167449421965318e-05,
|
| 391 |
+
"loss": 0.0104,
|
| 392 |
+
"step": 12000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.722499849479198,
|
| 396 |
+
"eval_cosine_accuracy": 0.690652072429657,
|
| 397 |
+
"eval_loss": 0.06046264246106148,
|
| 398 |
+
"eval_runtime": 50.2235,
|
| 399 |
+
"eval_samples_per_second": 376.636,
|
| 400 |
+
"eval_steps_per_second": 1.473,
|
| 401 |
+
"step": 12000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7526040098741646,
|
| 405 |
+
"grad_norm": 0.08468858897686005,
|
| 406 |
+
"learning_rate": 2.2577673410404626e-05,
|
| 407 |
+
"loss": 0.01,
|
| 408 |
+
"step": 12500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7526040098741646,
|
| 412 |
+
"eval_cosine_accuracy": 0.6941410899162292,
|
| 413 |
+
"eval_loss": 0.0607633963227272,
|
| 414 |
+
"eval_runtime": 49.538,
|
| 415 |
+
"eval_samples_per_second": 381.848,
|
| 416 |
+
"eval_steps_per_second": 1.494,
|
| 417 |
+
"step": 12500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.7827081702691312,
|
| 421 |
+
"grad_norm": 0.08423547446727753,
|
| 422 |
+
"learning_rate": 2.348085260115607e-05,
|
| 423 |
+
"loss": 0.0098,
|
| 424 |
+
"step": 13000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.7827081702691312,
|
| 428 |
+
"eval_cosine_accuracy": 0.6935520172119141,
|
| 429 |
+
"eval_loss": 0.060512788593769073,
|
| 430 |
+
"eval_runtime": 50.0245,
|
| 431 |
+
"eval_samples_per_second": 378.135,
|
| 432 |
+
"eval_steps_per_second": 1.479,
|
| 433 |
+
"step": 13000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.8128123306640977,
|
| 437 |
+
"grad_norm": 0.09347085654735565,
|
| 438 |
+
"learning_rate": 2.4384031791907515e-05,
|
| 439 |
+
"loss": 0.0095,
|
| 440 |
+
"step": 13500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.8128123306640977,
|
| 444 |
+
"eval_cosine_accuracy": 0.6864833235740662,
|
| 445 |
+
"eval_loss": 0.06169861555099487,
|
| 446 |
+
"eval_runtime": 49.1632,
|
| 447 |
+
"eval_samples_per_second": 384.759,
|
| 448 |
+
"eval_steps_per_second": 1.505,
|
| 449 |
+
"step": 13500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.8429164910590644,
|
| 453 |
+
"grad_norm": 0.08714573830366135,
|
| 454 |
+
"learning_rate": 2.528721098265896e-05,
|
| 455 |
+
"loss": 0.0093,
|
| 456 |
+
"step": 14000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.8429164910590644,
|
| 460 |
+
"eval_cosine_accuracy": 0.6852598786354065,
|
| 461 |
+
"eval_loss": 0.06119261682033539,
|
| 462 |
+
"eval_runtime": 49.9368,
|
| 463 |
+
"eval_samples_per_second": 378.799,
|
| 464 |
+
"eval_steps_per_second": 1.482,
|
| 465 |
+
"step": 14000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.873020651454031,
|
| 469 |
+
"grad_norm": 0.07207969576120377,
|
| 470 |
+
"learning_rate": 2.6190390173410404e-05,
|
| 471 |
+
"loss": 0.009,
|
| 472 |
+
"step": 14500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.873020651454031,
|
| 476 |
+
"eval_cosine_accuracy": 0.6856223940849304,
|
| 477 |
+
"eval_loss": 0.062048524618148804,
|
| 478 |
+
"eval_runtime": 51.5454,
|
| 479 |
+
"eval_samples_per_second": 366.977,
|
| 480 |
+
"eval_steps_per_second": 1.436,
|
| 481 |
+
"step": 14500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.9031248118489975,
|
| 485 |
+
"grad_norm": 0.06467518210411072,
|
| 486 |
+
"learning_rate": 2.709176300578035e-05,
|
| 487 |
+
"loss": 0.0088,
|
| 488 |
+
"step": 15000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.9031248118489975,
|
| 492 |
+
"eval_cosine_accuracy": 0.6777833104133606,
|
| 493 |
+
"eval_loss": 0.06211797520518303,
|
| 494 |
+
"eval_runtime": 50.4574,
|
| 495 |
+
"eval_samples_per_second": 374.891,
|
| 496 |
+
"eval_steps_per_second": 1.467,
|
| 497 |
+
"step": 15000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.9332289722439641,
|
| 501 |
+
"grad_norm": 0.06801892071962357,
|
| 502 |
+
"learning_rate": 2.7994942196531793e-05,
|
| 503 |
+
"loss": 0.0087,
|
| 504 |
+
"step": 15500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.9332289722439641,
|
| 508 |
+
"eval_cosine_accuracy": 0.6719833016395569,
|
| 509 |
+
"eval_loss": 0.062346458435058594,
|
| 510 |
+
"eval_runtime": 49.8448,
|
| 511 |
+
"eval_samples_per_second": 379.498,
|
| 512 |
+
"eval_steps_per_second": 1.485,
|
| 513 |
+
"step": 15500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9633331326389307,
|
| 517 |
+
"grad_norm": 0.09557406604290009,
|
| 518 |
+
"learning_rate": 2.8898121387283238e-05,
|
| 519 |
+
"loss": 0.0084,
|
| 520 |
+
"step": 16000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9633331326389307,
|
| 524 |
+
"eval_cosine_accuracy": 0.6719833016395569,
|
| 525 |
+
"eval_loss": 0.06308408081531525,
|
| 526 |
+
"eval_runtime": 50.6807,
|
| 527 |
+
"eval_samples_per_second": 373.239,
|
| 528 |
+
"eval_steps_per_second": 1.46,
|
| 529 |
+
"step": 16000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.9934372930338973,
|
| 533 |
+
"grad_norm": 0.09788572043180466,
|
| 534 |
+
"learning_rate": 2.9801300578034682e-05,
|
| 535 |
+
"loss": 0.0081,
|
| 536 |
+
"step": 16500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.9934372930338973,
|
| 540 |
+
"eval_cosine_accuracy": 0.6685395836830139,
|
| 541 |
+
"eval_loss": 0.06304680556058884,
|
| 542 |
+
"eval_runtime": 49.8791,
|
| 543 |
+
"eval_samples_per_second": 379.237,
|
| 544 |
+
"eval_steps_per_second": 1.484,
|
| 545 |
+
"step": 16500
|
| 546 |
+
}
|
| 547 |
+
],
|
| 548 |
+
"logging_steps": 500,
|
| 549 |
+
"max_steps": 66436,
|
| 550 |
+
"num_input_tokens_seen": 0,
|
| 551 |
+
"num_train_epochs": 4,
|
| 552 |
+
"save_steps": 500,
|
| 553 |
+
"stateful_callbacks": {
|
| 554 |
+
"TrainerControl": {
|
| 555 |
+
"args": {
|
| 556 |
+
"should_epoch_stop": false,
|
| 557 |
+
"should_evaluate": false,
|
| 558 |
+
"should_log": false,
|
| 559 |
+
"should_save": true,
|
| 560 |
+
"should_training_stop": false
|
| 561 |
+
},
|
| 562 |
+
"attributes": {}
|
| 563 |
+
}
|
| 564 |
+
},
|
| 565 |
+
"total_flos": 0.0,
|
| 566 |
+
"train_batch_size": 256,
|
| 567 |
+
"trial_name": null,
|
| 568 |
+
"trial_params": null
|
| 569 |
+
}
|
checkpoint-16609/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31a374185de9ba568af7f04e4450fc2799098799600f78ee8a5c6075bc6ca038
|
| 3 |
+
size 5624
|
checkpoint-16609/training_metrics.json
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metrics_history": [
|
| 3 |
+
{
|
| 4 |
+
"epoch": 0.030104160394966585,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"eval_loss": 0.03408537805080414,
|
| 7 |
+
"eval_cosine_accuracy": 0.9121845364570618
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"epoch": 0.06020832078993317,
|
| 11 |
+
"global_step": 1000,
|
| 12 |
+
"eval_loss": 0.03211512416601181,
|
| 13 |
+
"eval_cosine_accuracy": 0.9305813312530518
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 0.09031248118489975,
|
| 17 |
+
"global_step": 1500,
|
| 18 |
+
"eval_loss": 0.03070036694407463,
|
| 19 |
+
"eval_cosine_accuracy": 0.9341157078742981
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.12041664157986634,
|
| 23 |
+
"global_step": 2000,
|
| 24 |
+
"eval_loss": 0.032454561442136765,
|
| 25 |
+
"eval_cosine_accuracy": 0.9239204525947571
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.15052080197483292,
|
| 29 |
+
"global_step": 2500,
|
| 30 |
+
"eval_loss": 0.0350261889398098,
|
| 31 |
+
"eval_cosine_accuracy": 0.9068829417228699
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1806249623697995,
|
| 35 |
+
"global_step": 3000,
|
| 36 |
+
"eval_loss": 0.037413690239191055,
|
| 37 |
+
"eval_cosine_accuracy": 0.8916126489639282
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2107291227647661,
|
| 41 |
+
"global_step": 3500,
|
| 42 |
+
"eval_loss": 0.04107580706477165,
|
| 43 |
+
"eval_cosine_accuracy": 0.867868959903717
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.24083328315973268,
|
| 47 |
+
"global_step": 4000,
|
| 48 |
+
"eval_loss": 0.042248476296663284,
|
| 49 |
+
"eval_cosine_accuracy": 0.8625220656394958
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.2709374435546993,
|
| 53 |
+
"global_step": 4500,
|
| 54 |
+
"eval_loss": 0.04543215036392212,
|
| 55 |
+
"eval_cosine_accuracy": 0.8380987048149109
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.30104160394966584,
|
| 59 |
+
"global_step": 5000,
|
| 60 |
+
"eval_loss": 0.04734260216355324,
|
| 61 |
+
"eval_cosine_accuracy": 0.8265440464019775
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.33114576434463244,
|
| 65 |
+
"global_step": 5500,
|
| 66 |
+
"eval_loss": 0.048521969467401505,
|
| 67 |
+
"eval_cosine_accuracy": 0.812904953956604
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.361249924739599,
|
| 71 |
+
"global_step": 6000,
|
| 72 |
+
"eval_loss": 0.051017291843891144,
|
| 73 |
+
"eval_cosine_accuracy": 0.8010784387588501
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3913540851345656,
|
| 77 |
+
"global_step": 6500,
|
| 78 |
+
"eval_loss": 0.05125237628817558,
|
| 79 |
+
"eval_cosine_accuracy": 0.7926956415176392
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4214582455295322,
|
| 83 |
+
"global_step": 7000,
|
| 84 |
+
"eval_loss": 0.053376998752355576,
|
| 85 |
+
"eval_cosine_accuracy": 0.7693597078323364
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.45156240592449876,
|
| 89 |
+
"global_step": 7500,
|
| 90 |
+
"eval_loss": 0.05461883544921875,
|
| 91 |
+
"eval_cosine_accuracy": 0.7683628797531128
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.48166656631946536,
|
| 95 |
+
"global_step": 8000,
|
| 96 |
+
"eval_loss": 0.05498296022415161,
|
| 97 |
+
"eval_cosine_accuracy": 0.7625628709793091
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.5117707267144319,
|
| 101 |
+
"global_step": 8500,
|
| 102 |
+
"eval_loss": 0.055622003972530365,
|
| 103 |
+
"eval_cosine_accuracy": 0.7560831904411316
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.5418748871093986,
|
| 107 |
+
"global_step": 9000,
|
| 108 |
+
"eval_loss": 0.056548163294792175,
|
| 109 |
+
"eval_cosine_accuracy": 0.7378675937652588
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.5719790475043651,
|
| 113 |
+
"global_step": 9500,
|
| 114 |
+
"eval_loss": 0.05744454637169838,
|
| 115 |
+
"eval_cosine_accuracy": 0.7324753999710083
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6020832078993317,
|
| 119 |
+
"global_step": 10000,
|
| 120 |
+
"eval_loss": 0.058585748076438904,
|
| 121 |
+
"eval_cosine_accuracy": 0.7181566953659058
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6321873682942982,
|
| 125 |
+
"global_step": 10500,
|
| 126 |
+
"eval_loss": 0.05707884952425957,
|
| 127 |
+
"eval_cosine_accuracy": 0.725497305393219
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.6622915286892649,
|
| 131 |
+
"global_step": 11000,
|
| 132 |
+
"eval_loss": 0.0592338964343071,
|
| 133 |
+
"eval_cosine_accuracy": 0.7044723629951477
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.6923956890842314,
|
| 137 |
+
"global_step": 11500,
|
| 138 |
+
"eval_loss": 0.05877280980348587,
|
| 139 |
+
"eval_cosine_accuracy": 0.712537944316864
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.722499849479198,
|
| 143 |
+
"global_step": 12000,
|
| 144 |
+
"eval_loss": 0.06046264246106148,
|
| 145 |
+
"eval_cosine_accuracy": 0.690652072429657
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.7526040098741646,
|
| 149 |
+
"global_step": 12500,
|
| 150 |
+
"eval_loss": 0.0607633963227272,
|
| 151 |
+
"eval_cosine_accuracy": 0.6941410899162292
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.7827081702691312,
|
| 155 |
+
"global_step": 13000,
|
| 156 |
+
"eval_loss": 0.060512788593769073,
|
| 157 |
+
"eval_cosine_accuracy": 0.6935520172119141
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.8128123306640977,
|
| 161 |
+
"global_step": 13500,
|
| 162 |
+
"eval_loss": 0.06169861555099487,
|
| 163 |
+
"eval_cosine_accuracy": 0.6864833235740662
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8429164910590644,
|
| 167 |
+
"global_step": 14000,
|
| 168 |
+
"eval_loss": 0.06119261682033539,
|
| 169 |
+
"eval_cosine_accuracy": 0.6852598786354065
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.873020651454031,
|
| 173 |
+
"global_step": 14500,
|
| 174 |
+
"eval_loss": 0.062048524618148804,
|
| 175 |
+
"eval_cosine_accuracy": 0.6856223940849304
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.9031248118489975,
|
| 179 |
+
"global_step": 15000,
|
| 180 |
+
"eval_loss": 0.06211797520518303,
|
| 181 |
+
"eval_cosine_accuracy": 0.6777833104133606
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.9332289722439641,
|
| 185 |
+
"global_step": 15500,
|
| 186 |
+
"eval_loss": 0.062346458435058594,
|
| 187 |
+
"eval_cosine_accuracy": 0.6719833016395569
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.9633331326389307,
|
| 191 |
+
"global_step": 16000,
|
| 192 |
+
"eval_loss": 0.06308408081531525,
|
| 193 |
+
"eval_cosine_accuracy": 0.6719833016395569
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.9934372930338973,
|
| 197 |
+
"global_step": 16500,
|
| 198 |
+
"eval_loss": 0.06304680556058884,
|
| 199 |
+
"eval_cosine_accuracy": 0.6685395836830139
|
| 200 |
+
}
|
| 201 |
+
],
|
| 202 |
+
"current_epoch": 1,
|
| 203 |
+
"global_step": 16609
|
| 204 |
+
}
|
checkpoint-16609/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|