Training checkpoint - Epoch 8, Step 123144
Browse files- checkpoint-123144/1_Pooling/config.json +10 -0
- checkpoint-123144/added_tokens.json +0 -0
- checkpoint-123144/config.json +25 -0
- checkpoint-123144/config_sentence_transformers.json +14 -0
- checkpoint-123144/model.safetensors +3 -0
- checkpoint-123144/modules.json +20 -0
- checkpoint-123144/optimizer.pt +3 -0
- checkpoint-123144/rng_state.pth +3 -0
- checkpoint-123144/scaler.pt +3 -0
- checkpoint-123144/scheduler.pt +3 -0
- checkpoint-123144/sentence_bert_config.json +4 -0
- checkpoint-123144/special_tokens_map.json +37 -0
- checkpoint-123144/tokenizer.json +0 -0
- checkpoint-123144/tokenizer_config.json +0 -0
- checkpoint-123144/trainer_state.json +1017 -0
- checkpoint-123144/training_args.bin +3 -0
- checkpoint-123144/training_metrics.json +372 -0
- checkpoint-123144/vocab.txt +0 -0
checkpoint-123144/1_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-123144/added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-123144/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": 55582
|
| 25 |
+
}
|
checkpoint-123144/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-123144/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b14b93311b416b025a111f72ec093825ff2b54690f7d302ed3f9a556ae8cace0
|
| 3 |
+
size 129356488
|
checkpoint-123144/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-123144/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3e0531435ec82c198ae262c98ce9bfe0045884c47418ef1f276185f1b2ad2e4
|
| 3 |
+
size 257592058
|
checkpoint-123144/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc753f7b3495b15b3bff3a8920741f1d3b26aca827f85909d6e27aea43843891
|
| 3 |
+
size 14244
|
checkpoint-123144/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a4479cd8efb4b048202870006f6767c1b03bc0081d3f1f0db6044f3daed37f
|
| 3 |
+
size 988
|
checkpoint-123144/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63aa0aa96832cec58b366af64c8a84dc116e90a87c19d913c5549c78b1b1ab7b
|
| 3 |
+
size 1064
|
checkpoint-123144/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 256,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-123144/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-123144/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-123144/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-123144/trainer_state.json
ADDED
|
@@ -0,0 +1,1017 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 2000,
|
| 7 |
+
"global_step": 123144,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 6.496459429610862e-05,
|
| 14 |
+
"grad_norm": 8.543986320495605,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.8055,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12992918859221725,
|
| 21 |
+
"grad_norm": 4.228509902954102,
|
| 22 |
+
"learning_rate": 9.740449584199584e-07,
|
| 23 |
+
"loss": 2.5053,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12992918859221725,
|
| 28 |
+
"eval_cosine_accuracy": 0.9490216970443726,
|
| 29 |
+
"eval_loss": 0.9158492088317871,
|
| 30 |
+
"eval_runtime": 24.8196,
|
| 31 |
+
"eval_samples_per_second": 380.948,
|
| 32 |
+
"eval_steps_per_second": 1.491,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.2598583771844345,
|
| 37 |
+
"grad_norm": 4.29846715927124,
|
| 38 |
+
"learning_rate": 1.948577182952183e-06,
|
| 39 |
+
"loss": 2.0544,
|
| 40 |
+
"step": 4000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.2598583771844345,
|
| 44 |
+
"eval_cosine_accuracy": 0.9499735832214355,
|
| 45 |
+
"eval_loss": 0.9200904369354248,
|
| 46 |
+
"eval_runtime": 24.5453,
|
| 47 |
+
"eval_samples_per_second": 385.206,
|
| 48 |
+
"eval_steps_per_second": 1.507,
|
| 49 |
+
"step": 4000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.38978756577665175,
|
| 53 |
+
"grad_norm": 4.714716911315918,
|
| 54 |
+
"learning_rate": 2.9226221413721413e-06,
|
| 55 |
+
"loss": 1.7583,
|
| 56 |
+
"step": 6000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.38978756577665175,
|
| 60 |
+
"eval_cosine_accuracy": 0.9456372261047363,
|
| 61 |
+
"eval_loss": 0.8998962640762329,
|
| 62 |
+
"eval_runtime": 24.5547,
|
| 63 |
+
"eval_samples_per_second": 385.059,
|
| 64 |
+
"eval_steps_per_second": 1.507,
|
| 65 |
+
"step": 6000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.519716754368869,
|
| 69 |
+
"grad_norm": 4.514920234680176,
|
| 70 |
+
"learning_rate": 3.8966670997921e-06,
|
| 71 |
+
"loss": 1.5402,
|
| 72 |
+
"step": 8000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.519716754368869,
|
| 76 |
+
"eval_cosine_accuracy": 0.9466948509216309,
|
| 77 |
+
"eval_loss": 0.8402906060218811,
|
| 78 |
+
"eval_runtime": 24.5672,
|
| 79 |
+
"eval_samples_per_second": 384.862,
|
| 80 |
+
"eval_steps_per_second": 1.506,
|
| 81 |
+
"step": 8000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.6496459429610862,
|
| 85 |
+
"grad_norm": 4.10648250579834,
|
| 86 |
+
"learning_rate": 4.871199324324324e-06,
|
| 87 |
+
"loss": 1.3738,
|
| 88 |
+
"step": 10000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.6496459429610862,
|
| 92 |
+
"eval_cosine_accuracy": 0.947012186050415,
|
| 93 |
+
"eval_loss": 0.8332843780517578,
|
| 94 |
+
"eval_runtime": 24.6002,
|
| 95 |
+
"eval_samples_per_second": 384.346,
|
| 96 |
+
"eval_steps_per_second": 1.504,
|
| 97 |
+
"step": 10000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.7795751315533035,
|
| 101 |
+
"grad_norm": 4.327205657958984,
|
| 102 |
+
"learning_rate": 5.844757016632017e-06,
|
| 103 |
+
"loss": 1.241,
|
| 104 |
+
"step": 12000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.7795751315533035,
|
| 108 |
+
"eval_cosine_accuracy": 0.9478582739830017,
|
| 109 |
+
"eval_loss": 0.8381510972976685,
|
| 110 |
+
"eval_runtime": 24.3575,
|
| 111 |
+
"eval_samples_per_second": 388.176,
|
| 112 |
+
"eval_steps_per_second": 1.519,
|
| 113 |
+
"step": 12000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.9095043201455207,
|
| 117 |
+
"grad_norm": 4.739709854125977,
|
| 118 |
+
"learning_rate": 6.818801975051975e-06,
|
| 119 |
+
"loss": 1.1337,
|
| 120 |
+
"step": 14000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.9095043201455207,
|
| 124 |
+
"eval_cosine_accuracy": 0.9480698108673096,
|
| 125 |
+
"eval_loss": 0.8515253663063049,
|
| 126 |
+
"eval_runtime": 24.5042,
|
| 127 |
+
"eval_samples_per_second": 385.853,
|
| 128 |
+
"eval_steps_per_second": 1.51,
|
| 129 |
+
"step": 14000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.039433508737738,
|
| 133 |
+
"grad_norm": 3.9595558643341064,
|
| 134 |
+
"learning_rate": 7.7933341995842e-06,
|
| 135 |
+
"loss": 1.3481,
|
| 136 |
+
"step": 16000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.039433508737738,
|
| 140 |
+
"eval_cosine_accuracy": 0.9481755495071411,
|
| 141 |
+
"eval_loss": 0.861483097076416,
|
| 142 |
+
"eval_runtime": 24.9212,
|
| 143 |
+
"eval_samples_per_second": 379.395,
|
| 144 |
+
"eval_steps_per_second": 1.485,
|
| 145 |
+
"step": 16000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.1693626973299551,
|
| 149 |
+
"grad_norm": 3.8362483978271484,
|
| 150 |
+
"learning_rate": 8.767379158004158e-06,
|
| 151 |
+
"loss": 0.9775,
|
| 152 |
+
"step": 18000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.1693626973299551,
|
| 156 |
+
"eval_cosine_accuracy": 0.9490216970443726,
|
| 157 |
+
"eval_loss": 0.866976261138916,
|
| 158 |
+
"eval_runtime": 24.7567,
|
| 159 |
+
"eval_samples_per_second": 381.917,
|
| 160 |
+
"eval_steps_per_second": 1.495,
|
| 161 |
+
"step": 18000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.2992918859221725,
|
| 165 |
+
"grad_norm": 3.660410165786743,
|
| 166 |
+
"learning_rate": 9.740936850311851e-06,
|
| 167 |
+
"loss": 0.9106,
|
| 168 |
+
"step": 20000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.2992918859221725,
|
| 172 |
+
"eval_cosine_accuracy": 0.9511369466781616,
|
| 173 |
+
"eval_loss": 0.8142719268798828,
|
| 174 |
+
"eval_runtime": 24.6537,
|
| 175 |
+
"eval_samples_per_second": 383.513,
|
| 176 |
+
"eval_steps_per_second": 1.501,
|
| 177 |
+
"step": 20000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.4292210745143896,
|
| 181 |
+
"grad_norm": 3.5640735626220703,
|
| 182 |
+
"learning_rate": 1.0715469074844075e-05,
|
| 183 |
+
"loss": 0.8581,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4292210745143896,
|
| 188 |
+
"eval_cosine_accuracy": 0.9521946310997009,
|
| 189 |
+
"eval_loss": 0.7982929944992065,
|
| 190 |
+
"eval_runtime": 24.9083,
|
| 191 |
+
"eval_samples_per_second": 379.592,
|
| 192 |
+
"eval_steps_per_second": 1.485,
|
| 193 |
+
"step": 22000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.559150263106607,
|
| 197 |
+
"grad_norm": 3.663590908050537,
|
| 198 |
+
"learning_rate": 1.1689514033264035e-05,
|
| 199 |
+
"loss": 0.8119,
|
| 200 |
+
"step": 24000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.559150263106607,
|
| 204 |
+
"eval_cosine_accuracy": 0.9538868069648743,
|
| 205 |
+
"eval_loss": 0.7904353141784668,
|
| 206 |
+
"eval_runtime": 24.419,
|
| 207 |
+
"eval_samples_per_second": 387.198,
|
| 208 |
+
"eval_steps_per_second": 1.515,
|
| 209 |
+
"step": 24000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.6890794516988241,
|
| 213 |
+
"grad_norm": 3.101531505584717,
|
| 214 |
+
"learning_rate": 1.2664046257796258e-05,
|
| 215 |
+
"loss": 0.775,
|
| 216 |
+
"step": 26000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.6890794516988241,
|
| 220 |
+
"eval_cosine_accuracy": 0.9561078548431396,
|
| 221 |
+
"eval_loss": 0.7433677315711975,
|
| 222 |
+
"eval_runtime": 24.4716,
|
| 223 |
+
"eval_samples_per_second": 386.366,
|
| 224 |
+
"eval_steps_per_second": 1.512,
|
| 225 |
+
"step": 26000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.8190086402910413,
|
| 229 |
+
"grad_norm": 3.2498459815979004,
|
| 230 |
+
"learning_rate": 1.3638091216216216e-05,
|
| 231 |
+
"loss": 0.7376,
|
| 232 |
+
"step": 28000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.8190086402910413,
|
| 236 |
+
"eval_cosine_accuracy": 0.9565309286117554,
|
| 237 |
+
"eval_loss": 0.779238760471344,
|
| 238 |
+
"eval_runtime": 24.4481,
|
| 239 |
+
"eval_samples_per_second": 386.737,
|
| 240 |
+
"eval_steps_per_second": 1.513,
|
| 241 |
+
"step": 28000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.9489378288832586,
|
| 245 |
+
"grad_norm": 2.890700101852417,
|
| 246 |
+
"learning_rate": 1.4612136174636175e-05,
|
| 247 |
+
"loss": 0.7072,
|
| 248 |
+
"step": 30000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.9489378288832586,
|
| 252 |
+
"eval_cosine_accuracy": 0.9578000903129578,
|
| 253 |
+
"eval_loss": 0.7882058024406433,
|
| 254 |
+
"eval_runtime": 24.4341,
|
| 255 |
+
"eval_samples_per_second": 386.959,
|
| 256 |
+
"eval_steps_per_second": 1.514,
|
| 257 |
+
"step": 30000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.078867017475476,
|
| 261 |
+
"grad_norm": 3.015334367752075,
|
| 262 |
+
"learning_rate": 1.5586181133056135e-05,
|
| 263 |
+
"loss": 0.9877,
|
| 264 |
+
"step": 32000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.078867017475476,
|
| 268 |
+
"eval_cosine_accuracy": 0.9568482041358948,
|
| 269 |
+
"eval_loss": 0.8047419786453247,
|
| 270 |
+
"eval_runtime": 25.0473,
|
| 271 |
+
"eval_samples_per_second": 377.486,
|
| 272 |
+
"eval_steps_per_second": 1.477,
|
| 273 |
+
"step": 32000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.208796206067693,
|
| 277 |
+
"grad_norm": 2.955296039581299,
|
| 278 |
+
"learning_rate": 1.6559738825363826e-05,
|
| 279 |
+
"loss": 0.6526,
|
| 280 |
+
"step": 34000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.208796206067693,
|
| 284 |
+
"eval_cosine_accuracy": 0.959280788898468,
|
| 285 |
+
"eval_loss": 0.7193956971168518,
|
| 286 |
+
"eval_runtime": 24.5845,
|
| 287 |
+
"eval_samples_per_second": 384.592,
|
| 288 |
+
"eval_steps_per_second": 1.505,
|
| 289 |
+
"step": 34000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.3387253946599103,
|
| 293 |
+
"grad_norm": 2.620438575744629,
|
| 294 |
+
"learning_rate": 1.7534271049896048e-05,
|
| 295 |
+
"loss": 0.6275,
|
| 296 |
+
"step": 36000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.3387253946599103,
|
| 300 |
+
"eval_cosine_accuracy": 0.9604442119598389,
|
| 301 |
+
"eval_loss": 0.725292444229126,
|
| 302 |
+
"eval_runtime": 24.6763,
|
| 303 |
+
"eval_samples_per_second": 383.162,
|
| 304 |
+
"eval_steps_per_second": 1.499,
|
| 305 |
+
"step": 36000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.4686545832521274,
|
| 309 |
+
"grad_norm": 3.143752098083496,
|
| 310 |
+
"learning_rate": 1.8508803274428273e-05,
|
| 311 |
+
"loss": 0.6109,
|
| 312 |
+
"step": 38000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.4686545832521274,
|
| 316 |
+
"eval_cosine_accuracy": 0.9617133736610413,
|
| 317 |
+
"eval_loss": 0.7545588612556458,
|
| 318 |
+
"eval_runtime": 27.6088,
|
| 319 |
+
"eval_samples_per_second": 342.463,
|
| 320 |
+
"eval_steps_per_second": 1.34,
|
| 321 |
+
"step": 38000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.598583771844345,
|
| 325 |
+
"grad_norm": 2.62251353263855,
|
| 326 |
+
"learning_rate": 1.9482848232848233e-05,
|
| 327 |
+
"loss": 0.5918,
|
| 328 |
+
"step": 40000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.598583771844345,
|
| 332 |
+
"eval_cosine_accuracy": 0.9620306491851807,
|
| 333 |
+
"eval_loss": 0.7361720204353333,
|
| 334 |
+
"eval_runtime": 24.6649,
|
| 335 |
+
"eval_samples_per_second": 383.339,
|
| 336 |
+
"eval_steps_per_second": 1.5,
|
| 337 |
+
"step": 40000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.728512960436562,
|
| 341 |
+
"grad_norm": 2.776906967163086,
|
| 342 |
+
"learning_rate": 2.0456405925155924e-05,
|
| 343 |
+
"loss": 0.5768,
|
| 344 |
+
"step": 42000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.728512960436562,
|
| 348 |
+
"eval_cosine_accuracy": 0.9628767967224121,
|
| 349 |
+
"eval_loss": 0.7261704206466675,
|
| 350 |
+
"eval_runtime": 24.5203,
|
| 351 |
+
"eval_samples_per_second": 385.598,
|
| 352 |
+
"eval_steps_per_second": 1.509,
|
| 353 |
+
"step": 42000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.8584421490287792,
|
| 357 |
+
"grad_norm": 3.0380618572235107,
|
| 358 |
+
"learning_rate": 2.143093814968815e-05,
|
| 359 |
+
"loss": 0.5618,
|
| 360 |
+
"step": 44000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.8584421490287792,
|
| 364 |
+
"eval_cosine_accuracy": 0.96308833360672,
|
| 365 |
+
"eval_loss": 0.7182765603065491,
|
| 366 |
+
"eval_runtime": 24.7751,
|
| 367 |
+
"eval_samples_per_second": 381.633,
|
| 368 |
+
"eval_steps_per_second": 1.493,
|
| 369 |
+
"step": 44000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.988371337620997,
|
| 373 |
+
"grad_norm": 6.228867053985596,
|
| 374 |
+
"learning_rate": 2.2404495841995844e-05,
|
| 375 |
+
"loss": 0.7458,
|
| 376 |
+
"step": 46000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.988371337620997,
|
| 380 |
+
"eval_cosine_accuracy": 0.9553675055503845,
|
| 381 |
+
"eval_loss": 0.819146454334259,
|
| 382 |
+
"eval_runtime": 24.7404,
|
| 383 |
+
"eval_samples_per_second": 382.168,
|
| 384 |
+
"eval_steps_per_second": 1.496,
|
| 385 |
+
"step": 46000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 3.118300526213214,
|
| 389 |
+
"grad_norm": 2.492626428604126,
|
| 390 |
+
"learning_rate": 2.337902806652807e-05,
|
| 391 |
+
"loss": 0.643,
|
| 392 |
+
"step": 48000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.118300526213214,
|
| 396 |
+
"eval_cosine_accuracy": 0.9622421860694885,
|
| 397 |
+
"eval_loss": 0.7653650641441345,
|
| 398 |
+
"eval_runtime": 25.1236,
|
| 399 |
+
"eval_samples_per_second": 376.339,
|
| 400 |
+
"eval_steps_per_second": 1.473,
|
| 401 |
+
"step": 48000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.248229714805431,
|
| 405 |
+
"grad_norm": 2.750302314758301,
|
| 406 |
+
"learning_rate": 2.4353073024948026e-05,
|
| 407 |
+
"loss": 0.5174,
|
| 408 |
+
"step": 50000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.248229714805431,
|
| 412 |
+
"eval_cosine_accuracy": 0.9646747708320618,
|
| 413 |
+
"eval_loss": 0.7210116386413574,
|
| 414 |
+
"eval_runtime": 24.8407,
|
| 415 |
+
"eval_samples_per_second": 380.626,
|
| 416 |
+
"eval_steps_per_second": 1.489,
|
| 417 |
+
"step": 50000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.3781589033976482,
|
| 421 |
+
"grad_norm": 2.3254339694976807,
|
| 422 |
+
"learning_rate": 2.5327117983367986e-05,
|
| 423 |
+
"loss": 0.5049,
|
| 424 |
+
"step": 52000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 3.3781589033976482,
|
| 428 |
+
"eval_cosine_accuracy": 0.9627709984779358,
|
| 429 |
+
"eval_loss": 0.7164391875267029,
|
| 430 |
+
"eval_runtime": 24.8177,
|
| 431 |
+
"eval_samples_per_second": 380.979,
|
| 432 |
+
"eval_steps_per_second": 1.491,
|
| 433 |
+
"step": 52000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.5080880919898654,
|
| 437 |
+
"grad_norm": 2.2204036712646484,
|
| 438 |
+
"learning_rate": 2.630165020790021e-05,
|
| 439 |
+
"loss": 0.5003,
|
| 440 |
+
"step": 54000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.5080880919898654,
|
| 444 |
+
"eval_cosine_accuracy": 0.9658381938934326,
|
| 445 |
+
"eval_loss": 0.6905584931373596,
|
| 446 |
+
"eval_runtime": 24.8122,
|
| 447 |
+
"eval_samples_per_second": 381.063,
|
| 448 |
+
"eval_steps_per_second": 1.491,
|
| 449 |
+
"step": 54000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.6380172805820825,
|
| 453 |
+
"grad_norm": 2.4252846240997314,
|
| 454 |
+
"learning_rate": 2.7275695166320167e-05,
|
| 455 |
+
"loss": 0.4873,
|
| 456 |
+
"step": 56000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.6380172805820825,
|
| 460 |
+
"eval_cosine_accuracy": 0.9643574953079224,
|
| 461 |
+
"eval_loss": 0.6991865634918213,
|
| 462 |
+
"eval_runtime": 24.8084,
|
| 463 |
+
"eval_samples_per_second": 381.121,
|
| 464 |
+
"eval_steps_per_second": 1.491,
|
| 465 |
+
"step": 56000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.7679464691743,
|
| 469 |
+
"grad_norm": 2.161461591720581,
|
| 470 |
+
"learning_rate": 2.824925285862786e-05,
|
| 471 |
+
"loss": 0.4786,
|
| 472 |
+
"step": 58000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.7679464691743,
|
| 476 |
+
"eval_cosine_accuracy": 0.9658381938934326,
|
| 477 |
+
"eval_loss": 0.6876057386398315,
|
| 478 |
+
"eval_runtime": 25.0108,
|
| 479 |
+
"eval_samples_per_second": 378.037,
|
| 480 |
+
"eval_steps_per_second": 1.479,
|
| 481 |
+
"step": 58000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 3.8978756577665172,
|
| 485 |
+
"grad_norm": 2.3848555088043213,
|
| 486 |
+
"learning_rate": 2.9223785083160084e-05,
|
| 487 |
+
"loss": 0.4738,
|
| 488 |
+
"step": 60000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.8978756577665172,
|
| 492 |
+
"eval_cosine_accuracy": 0.9663670063018799,
|
| 493 |
+
"eval_loss": 0.6974127888679504,
|
| 494 |
+
"eval_runtime": 24.9874,
|
| 495 |
+
"eval_samples_per_second": 378.39,
|
| 496 |
+
"eval_steps_per_second": 1.481,
|
| 497 |
+
"step": 60000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.027804846358735,
|
| 501 |
+
"grad_norm": 2.194507360458374,
|
| 502 |
+
"learning_rate": 2.9998576762001792e-05,
|
| 503 |
+
"loss": 0.7724,
|
| 504 |
+
"step": 62000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.027804846358735,
|
| 508 |
+
"eval_cosine_accuracy": 0.9637228846549988,
|
| 509 |
+
"eval_loss": 0.7903416752815247,
|
| 510 |
+
"eval_runtime": 25.2398,
|
| 511 |
+
"eval_samples_per_second": 374.607,
|
| 512 |
+
"eval_steps_per_second": 1.466,
|
| 513 |
+
"step": 62000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.157734034950952,
|
| 517 |
+
"grad_norm": 2.304309844970703,
|
| 518 |
+
"learning_rate": 2.994983944707142e-05,
|
| 519 |
+
"loss": 0.446,
|
| 520 |
+
"step": 64000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 4.157734034950952,
|
| 524 |
+
"eval_cosine_accuracy": 0.9673188924789429,
|
| 525 |
+
"eval_loss": 0.702480673789978,
|
| 526 |
+
"eval_runtime": 24.8537,
|
| 527 |
+
"eval_samples_per_second": 380.427,
|
| 528 |
+
"eval_steps_per_second": 1.489,
|
| 529 |
+
"step": 64000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 4.287663223543169,
|
| 533 |
+
"grad_norm": 2.074822187423706,
|
| 534 |
+
"learning_rate": 2.9832020332202645e-05,
|
| 535 |
+
"loss": 0.4415,
|
| 536 |
+
"step": 66000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.287663223543169,
|
| 540 |
+
"eval_cosine_accuracy": 0.966155469417572,
|
| 541 |
+
"eval_loss": 0.6973665952682495,
|
| 542 |
+
"eval_runtime": 25.0867,
|
| 543 |
+
"eval_samples_per_second": 376.893,
|
| 544 |
+
"eval_steps_per_second": 1.475,
|
| 545 |
+
"step": 66000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 4.417592412135386,
|
| 549 |
+
"grad_norm": 2.2352564334869385,
|
| 550 |
+
"learning_rate": 2.96455466160021e-05,
|
| 551 |
+
"loss": 0.4351,
|
| 552 |
+
"step": 68000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 4.417592412135386,
|
| 556 |
+
"eval_cosine_accuracy": 0.9681649804115295,
|
| 557 |
+
"eval_loss": 0.7310513854026794,
|
| 558 |
+
"eval_runtime": 25.0704,
|
| 559 |
+
"eval_samples_per_second": 377.138,
|
| 560 |
+
"eval_steps_per_second": 1.476,
|
| 561 |
+
"step": 68000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.547521600727603,
|
| 565 |
+
"grad_norm": 2.129157304763794,
|
| 566 |
+
"learning_rate": 2.9391610307156934e-05,
|
| 567 |
+
"loss": 0.4316,
|
| 568 |
+
"step": 70000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 4.547521600727603,
|
| 572 |
+
"eval_cosine_accuracy": 0.9675304293632507,
|
| 573 |
+
"eval_loss": 0.7204111218452454,
|
| 574 |
+
"eval_runtime": 24.9634,
|
| 575 |
+
"eval_samples_per_second": 378.755,
|
| 576 |
+
"eval_steps_per_second": 1.482,
|
| 577 |
+
"step": 70000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 4.6774507893198205,
|
| 581 |
+
"grad_norm": 2.012279510498047,
|
| 582 |
+
"learning_rate": 2.907087793019168e-05,
|
| 583 |
+
"loss": 0.4271,
|
| 584 |
+
"step": 72000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.6774507893198205,
|
| 588 |
+
"eval_cosine_accuracy": 0.967107355594635,
|
| 589 |
+
"eval_loss": 0.7272541522979736,
|
| 590 |
+
"eval_runtime": 25.2676,
|
| 591 |
+
"eval_samples_per_second": 374.194,
|
| 592 |
+
"eval_steps_per_second": 1.464,
|
| 593 |
+
"step": 72000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.807379977912038,
|
| 597 |
+
"grad_norm": 1.9547345638275146,
|
| 598 |
+
"learning_rate": 2.8685680306643546e-05,
|
| 599 |
+
"loss": 0.4198,
|
| 600 |
+
"step": 74000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.807379977912038,
|
| 604 |
+
"eval_cosine_accuracy": 0.969011127948761,
|
| 605 |
+
"eval_loss": 0.6957398056983948,
|
| 606 |
+
"eval_runtime": 25.4095,
|
| 607 |
+
"eval_samples_per_second": 372.105,
|
| 608 |
+
"eval_steps_per_second": 1.456,
|
| 609 |
+
"step": 74000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.937309166504255,
|
| 613 |
+
"grad_norm": 2.0091848373413086,
|
| 614 |
+
"learning_rate": 2.823664247871571e-05,
|
| 615 |
+
"loss": 0.4167,
|
| 616 |
+
"step": 76000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.937309166504255,
|
| 620 |
+
"eval_cosine_accuracy": 0.9691168665885925,
|
| 621 |
+
"eval_loss": 0.6990842819213867,
|
| 622 |
+
"eval_runtime": 25.0447,
|
| 623 |
+
"eval_samples_per_second": 377.524,
|
| 624 |
+
"eval_steps_per_second": 1.477,
|
| 625 |
+
"step": 76000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 5.067238355096473,
|
| 629 |
+
"grad_norm": 1.8354514837265015,
|
| 630 |
+
"learning_rate": 2.7726371948366402e-05,
|
| 631 |
+
"loss": 0.7129,
|
| 632 |
+
"step": 78000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 5.067238355096473,
|
| 636 |
+
"eval_cosine_accuracy": 0.9697514772415161,
|
| 637 |
+
"eval_loss": 0.7074629664421082,
|
| 638 |
+
"eval_runtime": 25.1305,
|
| 639 |
+
"eval_samples_per_second": 376.236,
|
| 640 |
+
"eval_steps_per_second": 1.472,
|
| 641 |
+
"step": 78000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 5.19716754368869,
|
| 645 |
+
"grad_norm": 1.7867507934570312,
|
| 646 |
+
"learning_rate": 2.7157528081470084e-05,
|
| 647 |
+
"loss": 0.3983,
|
| 648 |
+
"step": 80000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 5.19716754368869,
|
| 652 |
+
"eval_cosine_accuracy": 0.9703860282897949,
|
| 653 |
+
"eval_loss": 0.7379214763641357,
|
| 654 |
+
"eval_runtime": 24.9769,
|
| 655 |
+
"eval_samples_per_second": 378.549,
|
| 656 |
+
"eval_steps_per_second": 1.481,
|
| 657 |
+
"step": 80000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 5.327096732280907,
|
| 661 |
+
"grad_norm": 1.9852467775344849,
|
| 662 |
+
"learning_rate": 2.6532173440689846e-05,
|
| 663 |
+
"loss": 0.3942,
|
| 664 |
+
"step": 82000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 5.327096732280907,
|
| 668 |
+
"eval_cosine_accuracy": 0.9683765172958374,
|
| 669 |
+
"eval_loss": 0.7474883794784546,
|
| 670 |
+
"eval_runtime": 24.8649,
|
| 671 |
+
"eval_samples_per_second": 380.255,
|
| 672 |
+
"eval_steps_per_second": 1.488,
|
| 673 |
+
"step": 82000
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 5.457025920873124,
|
| 677 |
+
"grad_norm": 1.8092862367630005,
|
| 678 |
+
"learning_rate": 2.585382313908924e-05,
|
| 679 |
+
"loss": 0.3892,
|
| 680 |
+
"step": 84000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 5.457025920873124,
|
| 684 |
+
"eval_cosine_accuracy": 0.9691168665885925,
|
| 685 |
+
"eval_loss": 0.7109271883964539,
|
| 686 |
+
"eval_runtime": 24.8482,
|
| 687 |
+
"eval_samples_per_second": 380.511,
|
| 688 |
+
"eval_steps_per_second": 1.489,
|
| 689 |
+
"step": 84000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 5.586955109465341,
|
| 693 |
+
"grad_norm": 2.0343291759490967,
|
| 694 |
+
"learning_rate": 2.5125689659567008e-05,
|
| 695 |
+
"loss": 0.3888,
|
| 696 |
+
"step": 86000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 5.586955109465341,
|
| 700 |
+
"eval_cosine_accuracy": 0.9697514772415161,
|
| 701 |
+
"eval_loss": 0.6926469206809998,
|
| 702 |
+
"eval_runtime": 25.0044,
|
| 703 |
+
"eval_samples_per_second": 378.134,
|
| 704 |
+
"eval_steps_per_second": 1.48,
|
| 705 |
+
"step": 86000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 5.7168842980575585,
|
| 709 |
+
"grad_norm": 1.6932772397994995,
|
| 710 |
+
"learning_rate": 2.4350010444574302e-05,
|
| 711 |
+
"loss": 0.3833,
|
| 712 |
+
"step": 88000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 5.7168842980575585,
|
| 716 |
+
"eval_cosine_accuracy": 0.9700687527656555,
|
| 717 |
+
"eval_loss": 0.7088406682014465,
|
| 718 |
+
"eval_runtime": 24.8656,
|
| 719 |
+
"eval_samples_per_second": 380.244,
|
| 720 |
+
"eval_steps_per_second": 1.488,
|
| 721 |
+
"step": 88000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 5.846813486649776,
|
| 725 |
+
"grad_norm": 1.9986995458602905,
|
| 726 |
+
"learning_rate": 2.3531078085280767e-05,
|
| 727 |
+
"loss": 0.382,
|
| 728 |
+
"step": 90000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 5.846813486649776,
|
| 732 |
+
"eval_cosine_accuracy": 0.9683765172958374,
|
| 733 |
+
"eval_loss": 0.7337806820869446,
|
| 734 |
+
"eval_runtime": 24.887,
|
| 735 |
+
"eval_samples_per_second": 379.917,
|
| 736 |
+
"eval_steps_per_second": 1.487,
|
| 737 |
+
"step": 90000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 5.976742675241993,
|
| 741 |
+
"grad_norm": 3.3190348148345947,
|
| 742 |
+
"learning_rate": 2.2673119368072682e-05,
|
| 743 |
+
"loss": 0.4537,
|
| 744 |
+
"step": 92000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.976742675241993,
|
| 748 |
+
"eval_cosine_accuracy": 0.9683765172958374,
|
| 749 |
+
"eval_loss": 0.8023020625114441,
|
| 750 |
+
"eval_runtime": 27.7815,
|
| 751 |
+
"eval_samples_per_second": 340.335,
|
| 752 |
+
"eval_steps_per_second": 1.332,
|
| 753 |
+
"step": 92000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 6.106671863834211,
|
| 757 |
+
"grad_norm": 2.010073184967041,
|
| 758 |
+
"learning_rate": 2.177970027726351e-05,
|
| 759 |
+
"loss": 0.604,
|
| 760 |
+
"step": 94000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 6.106671863834211,
|
| 764 |
+
"eval_cosine_accuracy": 0.9703860282897949,
|
| 765 |
+
"eval_loss": 0.7333589196205139,
|
| 766 |
+
"eval_runtime": 25.1648,
|
| 767 |
+
"eval_samples_per_second": 375.723,
|
| 768 |
+
"eval_steps_per_second": 1.47,
|
| 769 |
+
"step": 94000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 6.236601052426428,
|
| 773 |
+
"grad_norm": 2.00160813331604,
|
| 774 |
+
"learning_rate": 2.085494963885253e-05,
|
| 775 |
+
"loss": 0.3655,
|
| 776 |
+
"step": 96000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 6.236601052426428,
|
| 780 |
+
"eval_cosine_accuracy": 0.9714436531066895,
|
| 781 |
+
"eval_loss": 0.7170628309249878,
|
| 782 |
+
"eval_runtime": 24.6841,
|
| 783 |
+
"eval_samples_per_second": 383.04,
|
| 784 |
+
"eval_steps_per_second": 1.499,
|
| 785 |
+
"step": 96000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 6.366530241018645,
|
| 789 |
+
"grad_norm": 2.0749340057373047,
|
| 790 |
+
"learning_rate": 1.9902658889430463e-05,
|
| 791 |
+
"loss": 0.3639,
|
| 792 |
+
"step": 98000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 6.366530241018645,
|
| 796 |
+
"eval_cosine_accuracy": 0.9705975651741028,
|
| 797 |
+
"eval_loss": 0.7307552099227905,
|
| 798 |
+
"eval_runtime": 24.7379,
|
| 799 |
+
"eval_samples_per_second": 382.208,
|
| 800 |
+
"eval_steps_per_second": 1.496,
|
| 801 |
+
"step": 98000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 6.496459429610862,
|
| 805 |
+
"grad_norm": 1.738723635673523,
|
| 806 |
+
"learning_rate": 1.892768844209156e-05,
|
| 807 |
+
"loss": 0.3601,
|
| 808 |
+
"step": 100000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 6.496459429610862,
|
| 812 |
+
"eval_cosine_accuracy": 0.9716551899909973,
|
| 813 |
+
"eval_loss": 0.7068495750427246,
|
| 814 |
+
"eval_runtime": 24.9455,
|
| 815 |
+
"eval_samples_per_second": 379.026,
|
| 816 |
+
"eval_steps_per_second": 1.483,
|
| 817 |
+
"step": 100000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 6.626388618203079,
|
| 821 |
+
"grad_norm": 2.0313949584960938,
|
| 822 |
+
"learning_rate": 1.793554920211596e-05,
|
| 823 |
+
"loss": 0.361,
|
| 824 |
+
"step": 102000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 6.626388618203079,
|
| 828 |
+
"eval_cosine_accuracy": 0.9704918265342712,
|
| 829 |
+
"eval_loss": 0.731741189956665,
|
| 830 |
+
"eval_runtime": 24.7785,
|
| 831 |
+
"eval_samples_per_second": 381.58,
|
| 832 |
+
"eval_steps_per_second": 1.493,
|
| 833 |
+
"step": 102000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 6.7563178067952965,
|
| 837 |
+
"grad_norm": 1.9645425081253052,
|
| 838 |
+
"learning_rate": 1.692884530728219e-05,
|
| 839 |
+
"loss": 0.3591,
|
| 840 |
+
"step": 104000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 6.7563178067952965,
|
| 844 |
+
"eval_cosine_accuracy": 0.9717609882354736,
|
| 845 |
+
"eval_loss": 0.7156817317008972,
|
| 846 |
+
"eval_runtime": 24.9034,
|
| 847 |
+
"eval_samples_per_second": 379.667,
|
| 848 |
+
"eval_steps_per_second": 1.486,
|
| 849 |
+
"step": 104000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 6.886246995387514,
|
| 853 |
+
"grad_norm": 1.853805422782898,
|
| 854 |
+
"learning_rate": 1.5913727836562072e-05,
|
| 855 |
+
"loss": 0.3572,
|
| 856 |
+
"step": 106000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 6.886246995387514,
|
| 860 |
+
"eval_cosine_accuracy": 0.9712321758270264,
|
| 861 |
+
"eval_loss": 0.7309637665748596,
|
| 862 |
+
"eval_runtime": 24.8644,
|
| 863 |
+
"eval_samples_per_second": 380.262,
|
| 864 |
+
"eval_steps_per_second": 1.488,
|
| 865 |
+
"step": 106000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 7.016176183979731,
|
| 869 |
+
"grad_norm": 1.6603094339370728,
|
| 870 |
+
"learning_rate": 1.4894387685482128e-05,
|
| 871 |
+
"loss": 0.6611,
|
| 872 |
+
"step": 108000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 7.016176183979731,
|
| 876 |
+
"eval_cosine_accuracy": 0.9700687527656555,
|
| 877 |
+
"eval_loss": 0.7406259179115295,
|
| 878 |
+
"eval_runtime": 25.1504,
|
| 879 |
+
"eval_samples_per_second": 375.938,
|
| 880 |
+
"eval_steps_per_second": 1.471,
|
| 881 |
+
"step": 108000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 7.146105372571948,
|
| 885 |
+
"grad_norm": 1.585109829902649,
|
| 886 |
+
"learning_rate": 1.3875026836304197e-05,
|
| 887 |
+
"loss": 0.3471,
|
| 888 |
+
"step": 110000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 7.146105372571948,
|
| 892 |
+
"eval_cosine_accuracy": 0.9719725251197815,
|
| 893 |
+
"eval_loss": 0.7105578184127808,
|
| 894 |
+
"eval_runtime": 24.8057,
|
| 895 |
+
"eval_samples_per_second": 381.163,
|
| 896 |
+
"eval_steps_per_second": 1.492,
|
| 897 |
+
"step": 110000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 7.276034561164166,
|
| 901 |
+
"grad_norm": 1.8678215742111206,
|
| 902 |
+
"learning_rate": 1.2861880105184743e-05,
|
| 903 |
+
"loss": 0.3472,
|
| 904 |
+
"step": 112000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 7.276034561164166,
|
| 908 |
+
"eval_cosine_accuracy": 0.9704918265342712,
|
| 909 |
+
"eval_loss": 0.7393450140953064,
|
| 910 |
+
"eval_runtime": 24.7726,
|
| 911 |
+
"eval_samples_per_second": 381.671,
|
| 912 |
+
"eval_steps_per_second": 1.494,
|
| 913 |
+
"step": 112000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 7.405963749756383,
|
| 917 |
+
"grad_norm": 1.526391863822937,
|
| 918 |
+
"learning_rate": 1.1857606769744665e-05,
|
| 919 |
+
"loss": 0.3419,
|
| 920 |
+
"step": 114000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 7.405963749756383,
|
| 924 |
+
"eval_cosine_accuracy": 0.9707033038139343,
|
| 925 |
+
"eval_loss": 0.7284339666366577,
|
| 926 |
+
"eval_runtime": 24.9718,
|
| 927 |
+
"eval_samples_per_second": 378.627,
|
| 928 |
+
"eval_steps_per_second": 1.482,
|
| 929 |
+
"step": 114000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 7.5358929383486,
|
| 933 |
+
"grad_norm": 1.7915260791778564,
|
| 934 |
+
"learning_rate": 1.0867870144038113e-05,
|
| 935 |
+
"loss": 0.3434,
|
| 936 |
+
"step": 116000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 7.5358929383486,
|
| 940 |
+
"eval_cosine_accuracy": 0.9710206389427185,
|
| 941 |
+
"eval_loss": 0.7197515368461609,
|
| 942 |
+
"eval_runtime": 24.688,
|
| 943 |
+
"eval_samples_per_second": 382.98,
|
| 944 |
+
"eval_steps_per_second": 1.499,
|
| 945 |
+
"step": 116000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 7.665822126940817,
|
| 949 |
+
"grad_norm": 1.7209705114364624,
|
| 950 |
+
"learning_rate": 9.898208319743011e-06,
|
| 951 |
+
"loss": 0.3407,
|
| 952 |
+
"step": 118000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 7.665822126940817,
|
| 956 |
+
"eval_cosine_accuracy": 0.97112637758255,
|
| 957 |
+
"eval_loss": 0.7177817225456238,
|
| 958 |
+
"eval_runtime": 24.5575,
|
| 959 |
+
"eval_samples_per_second": 385.014,
|
| 960 |
+
"eval_steps_per_second": 1.507,
|
| 961 |
+
"step": 118000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 7.7957513155330345,
|
| 965 |
+
"grad_norm": 2.1164979934692383,
|
| 966 |
+
"learning_rate": 8.951166436580978e-06,
|
| 967 |
+
"loss": 0.3386,
|
| 968 |
+
"step": 120000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 7.7957513155330345,
|
| 972 |
+
"eval_cosine_accuracy": 0.9714436531066895,
|
| 973 |
+
"eval_loss": 0.7391806840896606,
|
| 974 |
+
"eval_runtime": 24.4886,
|
| 975 |
+
"eval_samples_per_second": 386.098,
|
| 976 |
+
"eval_steps_per_second": 1.511,
|
| 977 |
+
"step": 120000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 7.925680504125252,
|
| 981 |
+
"grad_norm": 2.0003724098205566,
|
| 982 |
+
"learning_rate": 8.032106454885379e-06,
|
| 983 |
+
"loss": 0.3425,
|
| 984 |
+
"step": 122000
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 7.925680504125252,
|
| 988 |
+
"eval_cosine_accuracy": 0.9718667268753052,
|
| 989 |
+
"eval_loss": 0.7296627759933472,
|
| 990 |
+
"eval_runtime": 24.66,
|
| 991 |
+
"eval_samples_per_second": 383.415,
|
| 992 |
+
"eval_steps_per_second": 1.5,
|
| 993 |
+
"step": 122000
|
| 994 |
+
}
|
| 995 |
+
],
|
| 996 |
+
"logging_steps": 2000,
|
| 997 |
+
"max_steps": 153930,
|
| 998 |
+
"num_input_tokens_seen": 0,
|
| 999 |
+
"num_train_epochs": 10,
|
| 1000 |
+
"save_steps": 500,
|
| 1001 |
+
"stateful_callbacks": {
|
| 1002 |
+
"TrainerControl": {
|
| 1003 |
+
"args": {
|
| 1004 |
+
"should_epoch_stop": false,
|
| 1005 |
+
"should_evaluate": false,
|
| 1006 |
+
"should_log": false,
|
| 1007 |
+
"should_save": true,
|
| 1008 |
+
"should_training_stop": false
|
| 1009 |
+
},
|
| 1010 |
+
"attributes": {}
|
| 1011 |
+
}
|
| 1012 |
+
},
|
| 1013 |
+
"total_flos": 0.0,
|
| 1014 |
+
"train_batch_size": 256,
|
| 1015 |
+
"trial_name": null,
|
| 1016 |
+
"trial_params": null
|
| 1017 |
+
}
|
checkpoint-123144/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8add1478bcad8e00d4a109bb811a7177f7917c9b899c8df593575b4a025bf534
|
| 3 |
+
size 5624
|
checkpoint-123144/training_metrics.json
ADDED
|
@@ -0,0 +1,372 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metrics_history": [
|
| 3 |
+
{
|
| 4 |
+
"epoch": 0.12992918859221725,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
+
"eval_loss": 0.9158492088317871,
|
| 7 |
+
"eval_cosine_accuracy": 0.9490216970443726
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"epoch": 0.2598583771844345,
|
| 11 |
+
"global_step": 4000,
|
| 12 |
+
"eval_loss": 0.9200904369354248,
|
| 13 |
+
"eval_cosine_accuracy": 0.9499735832214355
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 0.38978756577665175,
|
| 17 |
+
"global_step": 6000,
|
| 18 |
+
"eval_loss": 0.8998962640762329,
|
| 19 |
+
"eval_cosine_accuracy": 0.9456372261047363
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.519716754368869,
|
| 23 |
+
"global_step": 8000,
|
| 24 |
+
"eval_loss": 0.8402906060218811,
|
| 25 |
+
"eval_cosine_accuracy": 0.9466948509216309
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.6496459429610862,
|
| 29 |
+
"global_step": 10000,
|
| 30 |
+
"eval_loss": 0.8332843780517578,
|
| 31 |
+
"eval_cosine_accuracy": 0.947012186050415
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.7795751315533035,
|
| 35 |
+
"global_step": 12000,
|
| 36 |
+
"eval_loss": 0.8381510972976685,
|
| 37 |
+
"eval_cosine_accuracy": 0.9478582739830017
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9095043201455207,
|
| 41 |
+
"global_step": 14000,
|
| 42 |
+
"eval_loss": 0.8515253663063049,
|
| 43 |
+
"eval_cosine_accuracy": 0.9480698108673096
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.039433508737738,
|
| 47 |
+
"global_step": 16000,
|
| 48 |
+
"eval_loss": 0.861483097076416,
|
| 49 |
+
"eval_cosine_accuracy": 0.9481755495071411
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.1693626973299551,
|
| 53 |
+
"global_step": 18000,
|
| 54 |
+
"eval_loss": 0.866976261138916,
|
| 55 |
+
"eval_cosine_accuracy": 0.9490216970443726
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.2992918859221725,
|
| 59 |
+
"global_step": 20000,
|
| 60 |
+
"eval_loss": 0.8142719268798828,
|
| 61 |
+
"eval_cosine_accuracy": 0.9511369466781616
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.4292210745143896,
|
| 65 |
+
"global_step": 22000,
|
| 66 |
+
"eval_loss": 0.7982929944992065,
|
| 67 |
+
"eval_cosine_accuracy": 0.9521946310997009
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.559150263106607,
|
| 71 |
+
"global_step": 24000,
|
| 72 |
+
"eval_loss": 0.7904353141784668,
|
| 73 |
+
"eval_cosine_accuracy": 0.9538868069648743
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.6890794516988241,
|
| 77 |
+
"global_step": 26000,
|
| 78 |
+
"eval_loss": 0.7433677315711975,
|
| 79 |
+
"eval_cosine_accuracy": 0.9561078548431396
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.8190086402910413,
|
| 83 |
+
"global_step": 28000,
|
| 84 |
+
"eval_loss": 0.779238760471344,
|
| 85 |
+
"eval_cosine_accuracy": 0.9565309286117554
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.9489378288832586,
|
| 89 |
+
"global_step": 30000,
|
| 90 |
+
"eval_loss": 0.7882058024406433,
|
| 91 |
+
"eval_cosine_accuracy": 0.9578000903129578
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 2.078867017475476,
|
| 95 |
+
"global_step": 32000,
|
| 96 |
+
"eval_loss": 0.8047419786453247,
|
| 97 |
+
"eval_cosine_accuracy": 0.9568482041358948
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.208796206067693,
|
| 101 |
+
"global_step": 34000,
|
| 102 |
+
"eval_loss": 0.7193956971168518,
|
| 103 |
+
"eval_cosine_accuracy": 0.959280788898468
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.3387253946599103,
|
| 107 |
+
"global_step": 36000,
|
| 108 |
+
"eval_loss": 0.725292444229126,
|
| 109 |
+
"eval_cosine_accuracy": 0.9604442119598389
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.4686545832521274,
|
| 113 |
+
"global_step": 38000,
|
| 114 |
+
"eval_loss": 0.7545588612556458,
|
| 115 |
+
"eval_cosine_accuracy": 0.9617133736610413
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.598583771844345,
|
| 119 |
+
"global_step": 40000,
|
| 120 |
+
"eval_loss": 0.7361720204353333,
|
| 121 |
+
"eval_cosine_accuracy": 0.9620306491851807
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.728512960436562,
|
| 125 |
+
"global_step": 42000,
|
| 126 |
+
"eval_loss": 0.7261704206466675,
|
| 127 |
+
"eval_cosine_accuracy": 0.9628767967224121
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.8584421490287792,
|
| 131 |
+
"global_step": 44000,
|
| 132 |
+
"eval_loss": 0.7182765603065491,
|
| 133 |
+
"eval_cosine_accuracy": 0.96308833360672
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.988371337620997,
|
| 137 |
+
"global_step": 46000,
|
| 138 |
+
"eval_loss": 0.819146454334259,
|
| 139 |
+
"eval_cosine_accuracy": 0.9553675055503845
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 3.118300526213214,
|
| 143 |
+
"global_step": 48000,
|
| 144 |
+
"eval_loss": 0.7653650641441345,
|
| 145 |
+
"eval_cosine_accuracy": 0.9622421860694885
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.248229714805431,
|
| 149 |
+
"global_step": 50000,
|
| 150 |
+
"eval_loss": 0.7210116386413574,
|
| 151 |
+
"eval_cosine_accuracy": 0.9646747708320618
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.3781589033976482,
|
| 155 |
+
"global_step": 52000,
|
| 156 |
+
"eval_loss": 0.7164391875267029,
|
| 157 |
+
"eval_cosine_accuracy": 0.9627709984779358
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 3.5080880919898654,
|
| 161 |
+
"global_step": 54000,
|
| 162 |
+
"eval_loss": 0.6905584931373596,
|
| 163 |
+
"eval_cosine_accuracy": 0.9658381938934326
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.6380172805820825,
|
| 167 |
+
"global_step": 56000,
|
| 168 |
+
"eval_loss": 0.6991865634918213,
|
| 169 |
+
"eval_cosine_accuracy": 0.9643574953079224
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.7679464691743,
|
| 173 |
+
"global_step": 58000,
|
| 174 |
+
"eval_loss": 0.6876057386398315,
|
| 175 |
+
"eval_cosine_accuracy": 0.9658381938934326
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 3.8978756577665172,
|
| 179 |
+
"global_step": 60000,
|
| 180 |
+
"eval_loss": 0.6974127888679504,
|
| 181 |
+
"eval_cosine_accuracy": 0.9663670063018799
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 4.027804846358735,
|
| 185 |
+
"global_step": 62000,
|
| 186 |
+
"eval_loss": 0.7903416752815247,
|
| 187 |
+
"eval_cosine_accuracy": 0.9637228846549988
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.157734034950952,
|
| 191 |
+
"global_step": 64000,
|
| 192 |
+
"eval_loss": 0.702480673789978,
|
| 193 |
+
"eval_cosine_accuracy": 0.9673188924789429
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 4.287663223543169,
|
| 197 |
+
"global_step": 66000,
|
| 198 |
+
"eval_loss": 0.6973665952682495,
|
| 199 |
+
"eval_cosine_accuracy": 0.966155469417572
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.417592412135386,
|
| 203 |
+
"global_step": 68000,
|
| 204 |
+
"eval_loss": 0.7310513854026794,
|
| 205 |
+
"eval_cosine_accuracy": 0.9681649804115295
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.547521600727603,
|
| 209 |
+
"global_step": 70000,
|
| 210 |
+
"eval_loss": 0.7204111218452454,
|
| 211 |
+
"eval_cosine_accuracy": 0.9675304293632507
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 4.6774507893198205,
|
| 215 |
+
"global_step": 72000,
|
| 216 |
+
"eval_loss": 0.7272541522979736,
|
| 217 |
+
"eval_cosine_accuracy": 0.967107355594635
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 4.807379977912038,
|
| 221 |
+
"global_step": 74000,
|
| 222 |
+
"eval_loss": 0.6957398056983948,
|
| 223 |
+
"eval_cosine_accuracy": 0.969011127948761
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.937309166504255,
|
| 227 |
+
"global_step": 76000,
|
| 228 |
+
"eval_loss": 0.6990842819213867,
|
| 229 |
+
"eval_cosine_accuracy": 0.9691168665885925
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 5.067238355096473,
|
| 233 |
+
"global_step": 78000,
|
| 234 |
+
"eval_loss": 0.7074629664421082,
|
| 235 |
+
"eval_cosine_accuracy": 0.9697514772415161
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 5.19716754368869,
|
| 239 |
+
"global_step": 80000,
|
| 240 |
+
"eval_loss": 0.7379214763641357,
|
| 241 |
+
"eval_cosine_accuracy": 0.9703860282897949
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 5.327096732280907,
|
| 245 |
+
"global_step": 82000,
|
| 246 |
+
"eval_loss": 0.7474883794784546,
|
| 247 |
+
"eval_cosine_accuracy": 0.9683765172958374
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.457025920873124,
|
| 251 |
+
"global_step": 84000,
|
| 252 |
+
"eval_loss": 0.7109271883964539,
|
| 253 |
+
"eval_cosine_accuracy": 0.9691168665885925
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 5.586955109465341,
|
| 257 |
+
"global_step": 86000,
|
| 258 |
+
"eval_loss": 0.6926469206809998,
|
| 259 |
+
"eval_cosine_accuracy": 0.9697514772415161
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.7168842980575585,
|
| 263 |
+
"global_step": 88000,
|
| 264 |
+
"eval_loss": 0.7088406682014465,
|
| 265 |
+
"eval_cosine_accuracy": 0.9700687527656555
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 5.846813486649776,
|
| 269 |
+
"global_step": 90000,
|
| 270 |
+
"eval_loss": 0.7337806820869446,
|
| 271 |
+
"eval_cosine_accuracy": 0.9683765172958374
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.976742675241993,
|
| 275 |
+
"global_step": 92000,
|
| 276 |
+
"eval_loss": 0.8023020625114441,
|
| 277 |
+
"eval_cosine_accuracy": 0.9683765172958374
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 6.106671863834211,
|
| 281 |
+
"global_step": 94000,
|
| 282 |
+
"eval_loss": 0.7333589196205139,
|
| 283 |
+
"eval_cosine_accuracy": 0.9703860282897949
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 6.236601052426428,
|
| 287 |
+
"global_step": 96000,
|
| 288 |
+
"eval_loss": 0.7170628309249878,
|
| 289 |
+
"eval_cosine_accuracy": 0.9714436531066895
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 6.366530241018645,
|
| 293 |
+
"global_step": 98000,
|
| 294 |
+
"eval_loss": 0.7307552099227905,
|
| 295 |
+
"eval_cosine_accuracy": 0.9705975651741028
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.496459429610862,
|
| 299 |
+
"global_step": 100000,
|
| 300 |
+
"eval_loss": 0.7068495750427246,
|
| 301 |
+
"eval_cosine_accuracy": 0.9716551899909973
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.626388618203079,
|
| 305 |
+
"global_step": 102000,
|
| 306 |
+
"eval_loss": 0.731741189956665,
|
| 307 |
+
"eval_cosine_accuracy": 0.9704918265342712
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 6.7563178067952965,
|
| 311 |
+
"global_step": 104000,
|
| 312 |
+
"eval_loss": 0.7156817317008972,
|
| 313 |
+
"eval_cosine_accuracy": 0.9717609882354736
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 6.886246995387514,
|
| 317 |
+
"global_step": 106000,
|
| 318 |
+
"eval_loss": 0.7309637665748596,
|
| 319 |
+
"eval_cosine_accuracy": 0.9712321758270264
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 7.016176183979731,
|
| 323 |
+
"global_step": 108000,
|
| 324 |
+
"eval_loss": 0.7406259179115295,
|
| 325 |
+
"eval_cosine_accuracy": 0.9700687527656555
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 7.146105372571948,
|
| 329 |
+
"global_step": 110000,
|
| 330 |
+
"eval_loss": 0.7105578184127808,
|
| 331 |
+
"eval_cosine_accuracy": 0.9719725251197815
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.276034561164166,
|
| 335 |
+
"global_step": 112000,
|
| 336 |
+
"eval_loss": 0.7393450140953064,
|
| 337 |
+
"eval_cosine_accuracy": 0.9704918265342712
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 7.405963749756383,
|
| 341 |
+
"global_step": 114000,
|
| 342 |
+
"eval_loss": 0.7284339666366577,
|
| 343 |
+
"eval_cosine_accuracy": 0.9707033038139343
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 7.5358929383486,
|
| 347 |
+
"global_step": 116000,
|
| 348 |
+
"eval_loss": 0.7197515368461609,
|
| 349 |
+
"eval_cosine_accuracy": 0.9710206389427185
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 7.665822126940817,
|
| 353 |
+
"global_step": 118000,
|
| 354 |
+
"eval_loss": 0.7177817225456238,
|
| 355 |
+
"eval_cosine_accuracy": 0.97112637758255
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 7.7957513155330345,
|
| 359 |
+
"global_step": 120000,
|
| 360 |
+
"eval_loss": 0.7391806840896606,
|
| 361 |
+
"eval_cosine_accuracy": 0.9714436531066895
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 7.925680504125252,
|
| 365 |
+
"global_step": 122000,
|
| 366 |
+
"eval_loss": 0.7296627759933472,
|
| 367 |
+
"eval_cosine_accuracy": 0.9718667268753052
|
| 368 |
+
}
|
| 369 |
+
],
|
| 370 |
+
"current_epoch": 8,
|
| 371 |
+
"global_step": 123144
|
| 372 |
+
}
|
checkpoint-123144/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|