Training checkpoint - Epoch 4, Step 34368
Browse files- checkpoint-34368/1_Pooling/config.json +10 -0
- checkpoint-34368/config.json +25 -0
- checkpoint-34368/config_sentence_transformers.json +14 -0
- checkpoint-34368/model.safetensors +3 -0
- checkpoint-34368/modules.json +20 -0
- checkpoint-34368/optimizer.pt +3 -0
- checkpoint-34368/rng_state.pth +3 -0
- checkpoint-34368/scaler.pt +3 -0
- checkpoint-34368/scheduler.pt +3 -0
- checkpoint-34368/sentence_bert_config.json +4 -0
- checkpoint-34368/special_tokens_map.json +37 -0
- checkpoint-34368/tokenizer.json +0 -0
- checkpoint-34368/tokenizer_config.json +65 -0
- checkpoint-34368/trainer_state.json +1129 -0
- checkpoint-34368/training_args.bin +3 -0
- checkpoint-34368/training_metrics.json +414 -0
- checkpoint-34368/vocab.txt +0 -0
checkpoint-34368/1_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-34368/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-34368/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-34368/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2864707c4b4db882ff174b6cd179394bf2111bbd9dccc96a49b49221424756e
|
| 3 |
+
size 90864192
|
checkpoint-34368/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-34368/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88aec13d8cdab32fbabe62609010d09305eb731dee09f11e43144992b60e29c6
|
| 3 |
+
size 180607738
|
checkpoint-34368/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd0e6225e412b60a19d2164313a9bca33ec2950e766a37e2765efc3e68ba1083
|
| 3 |
+
size 14244
|
checkpoint-34368/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:066904077dbace3d5ecf62d58eabaf01d750e7aca8f375be215cdc897469c808
|
| 3 |
+
size 988
|
checkpoint-34368/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a0ed956080d035823e1e40e048b12f68a5b05c8777e54176f86b856926684bf
|
| 3 |
+
size 1064
|
checkpoint-34368/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 256,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-34368/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-34368/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-34368/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-34368/trainer_state.json
ADDED
|
@@ -0,0 +1,1129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 34368,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00011638733705772812,
|
| 14 |
+
"grad_norm": Infinity,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 9.4531,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05819366852886406,
|
| 21 |
+
"grad_norm": 6.4754815101623535,
|
| 22 |
+
"learning_rate": 1.7390292166220463e-06,
|
| 23 |
+
"loss": 6.7666,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05819366852886406,
|
| 28 |
+
"eval_cosine_accuracy": 0.9417916536331177,
|
| 29 |
+
"eval_loss": 4.736684322357178,
|
| 30 |
+
"eval_runtime": 26.7399,
|
| 31 |
+
"eval_samples_per_second": 354.003,
|
| 32 |
+
"eval_steps_per_second": 1.384,
|
| 33 |
+
"step": 500
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11638733705772812,
|
| 37 |
+
"grad_norm": 5.042841911315918,
|
| 38 |
+
"learning_rate": 3.4850424863228964e-06,
|
| 39 |
+
"loss": 4.0612,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.11638733705772812,
|
| 44 |
+
"eval_cosine_accuracy": 0.9421085715293884,
|
| 45 |
+
"eval_loss": 4.456507682800293,
|
| 46 |
+
"eval_runtime": 27.0721,
|
| 47 |
+
"eval_samples_per_second": 349.659,
|
| 48 |
+
"eval_steps_per_second": 1.367,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.17458100558659218,
|
| 53 |
+
"grad_norm": 4.396075248718262,
|
| 54 |
+
"learning_rate": 5.2310557560237455e-06,
|
| 55 |
+
"loss": 3.8306,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.17458100558659218,
|
| 60 |
+
"eval_cosine_accuracy": 0.9389393329620361,
|
| 61 |
+
"eval_loss": 4.417118072509766,
|
| 62 |
+
"eval_runtime": 29.5299,
|
| 63 |
+
"eval_samples_per_second": 320.556,
|
| 64 |
+
"eval_steps_per_second": 1.253,
|
| 65 |
+
"step": 1500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.23277467411545624,
|
| 69 |
+
"grad_norm": 4.9983229637146,
|
| 70 |
+
"learning_rate": 6.9770690257245955e-06,
|
| 71 |
+
"loss": 3.7166,
|
| 72 |
+
"step": 2000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.23277467411545624,
|
| 76 |
+
"eval_cosine_accuracy": 0.9376716613769531,
|
| 77 |
+
"eval_loss": 4.384617805480957,
|
| 78 |
+
"eval_runtime": 27.1288,
|
| 79 |
+
"eval_samples_per_second": 348.928,
|
| 80 |
+
"eval_steps_per_second": 1.364,
|
| 81 |
+
"step": 2000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2909683426443203,
|
| 85 |
+
"grad_norm": 5.1397552490234375,
|
| 86 |
+
"learning_rate": 8.723082295425445e-06,
|
| 87 |
+
"loss": 3.5906,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2909683426443203,
|
| 92 |
+
"eval_cosine_accuracy": 0.929537296295166,
|
| 93 |
+
"eval_loss": 4.382342338562012,
|
| 94 |
+
"eval_runtime": 27.2377,
|
| 95 |
+
"eval_samples_per_second": 347.534,
|
| 96 |
+
"eval_steps_per_second": 1.358,
|
| 97 |
+
"step": 2500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.34916201117318435,
|
| 101 |
+
"grad_norm": 5.401367664337158,
|
| 102 |
+
"learning_rate": 1.0469095565126295e-05,
|
| 103 |
+
"loss": 3.504,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.34916201117318435,
|
| 108 |
+
"eval_cosine_accuracy": 0.9236213564872742,
|
| 109 |
+
"eval_loss": 4.398530006408691,
|
| 110 |
+
"eval_runtime": 27.2096,
|
| 111 |
+
"eval_samples_per_second": 347.891,
|
| 112 |
+
"eval_steps_per_second": 1.36,
|
| 113 |
+
"step": 3000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.4073556797020484,
|
| 117 |
+
"grad_norm": 5.506592273712158,
|
| 118 |
+
"learning_rate": 1.2215108834827144e-05,
|
| 119 |
+
"loss": 3.4064,
|
| 120 |
+
"step": 3500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.4073556797020484,
|
| 124 |
+
"eval_cosine_accuracy": 0.9207690954208374,
|
| 125 |
+
"eval_loss": 4.428633689880371,
|
| 126 |
+
"eval_runtime": 27.2549,
|
| 127 |
+
"eval_samples_per_second": 347.314,
|
| 128 |
+
"eval_steps_per_second": 1.358,
|
| 129 |
+
"step": 3500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4655493482309125,
|
| 133 |
+
"grad_norm": 6.144413471221924,
|
| 134 |
+
"learning_rate": 1.3961122104527995e-05,
|
| 135 |
+
"loss": 3.3219,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4655493482309125,
|
| 140 |
+
"eval_cosine_accuracy": 0.9240439534187317,
|
| 141 |
+
"eval_loss": 4.413504600524902,
|
| 142 |
+
"eval_runtime": 27.1733,
|
| 143 |
+
"eval_samples_per_second": 348.357,
|
| 144 |
+
"eval_steps_per_second": 1.362,
|
| 145 |
+
"step": 4000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.5237430167597765,
|
| 149 |
+
"grad_norm": 6.7739691734313965,
|
| 150 |
+
"learning_rate": 1.570364334768944e-05,
|
| 151 |
+
"loss": 3.2308,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.5237430167597765,
|
| 156 |
+
"eval_cosine_accuracy": 0.9183393120765686,
|
| 157 |
+
"eval_loss": 4.584815979003906,
|
| 158 |
+
"eval_runtime": 27.4916,
|
| 159 |
+
"eval_samples_per_second": 344.324,
|
| 160 |
+
"eval_steps_per_second": 1.346,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.5819366852886406,
|
| 165 |
+
"grad_norm": 7.5280914306640625,
|
| 166 |
+
"learning_rate": 1.7449656617390294e-05,
|
| 167 |
+
"loss": 3.1167,
|
| 168 |
+
"step": 5000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.5819366852886406,
|
| 172 |
+
"eval_cosine_accuracy": 0.9231988191604614,
|
| 173 |
+
"eval_loss": 4.731673240661621,
|
| 174 |
+
"eval_runtime": 27.9733,
|
| 175 |
+
"eval_samples_per_second": 338.394,
|
| 176 |
+
"eval_steps_per_second": 1.323,
|
| 177 |
+
"step": 5000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6401303538175046,
|
| 181 |
+
"grad_norm": 8.379385948181152,
|
| 182 |
+
"learning_rate": 1.919217786055174e-05,
|
| 183 |
+
"loss": 3.0155,
|
| 184 |
+
"step": 5500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6401303538175046,
|
| 188 |
+
"eval_cosine_accuracy": 0.9202408790588379,
|
| 189 |
+
"eval_loss": 4.590743064880371,
|
| 190 |
+
"eval_runtime": 30.4387,
|
| 191 |
+
"eval_samples_per_second": 310.985,
|
| 192 |
+
"eval_steps_per_second": 1.216,
|
| 193 |
+
"step": 5500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.6983240223463687,
|
| 197 |
+
"grad_norm": 7.9107985496521,
|
| 198 |
+
"learning_rate": 2.093819113025259e-05,
|
| 199 |
+
"loss": 2.928,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.6983240223463687,
|
| 204 |
+
"eval_cosine_accuracy": 0.9188675284385681,
|
| 205 |
+
"eval_loss": 4.662985324859619,
|
| 206 |
+
"eval_runtime": 27.6404,
|
| 207 |
+
"eval_samples_per_second": 342.469,
|
| 208 |
+
"eval_steps_per_second": 1.339,
|
| 209 |
+
"step": 6000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.7565176908752328,
|
| 213 |
+
"grad_norm": 8.108757972717285,
|
| 214 |
+
"learning_rate": 2.268420439995344e-05,
|
| 215 |
+
"loss": 2.8455,
|
| 216 |
+
"step": 6500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.7565176908752328,
|
| 220 |
+
"eval_cosine_accuracy": 0.9199239611625671,
|
| 221 |
+
"eval_loss": 4.784646511077881,
|
| 222 |
+
"eval_runtime": 27.3827,
|
| 223 |
+
"eval_samples_per_second": 345.693,
|
| 224 |
+
"eval_steps_per_second": 1.351,
|
| 225 |
+
"step": 6500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8147113594040968,
|
| 229 |
+
"grad_norm": 8.092316627502441,
|
| 230 |
+
"learning_rate": 2.443021766965429e-05,
|
| 231 |
+
"loss": 2.7847,
|
| 232 |
+
"step": 7000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.8147113594040968,
|
| 236 |
+
"eval_cosine_accuracy": 0.9054510593414307,
|
| 237 |
+
"eval_loss": 4.925645351409912,
|
| 238 |
+
"eval_runtime": 27.6051,
|
| 239 |
+
"eval_samples_per_second": 342.908,
|
| 240 |
+
"eval_steps_per_second": 1.34,
|
| 241 |
+
"step": 7000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.8729050279329609,
|
| 245 |
+
"grad_norm": 8.676020622253418,
|
| 246 |
+
"learning_rate": 2.617623093935514e-05,
|
| 247 |
+
"loss": 2.7228,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.8729050279329609,
|
| 252 |
+
"eval_cosine_accuracy": 0.9056623578071594,
|
| 253 |
+
"eval_loss": 4.843690395355225,
|
| 254 |
+
"eval_runtime": 27.3545,
|
| 255 |
+
"eval_samples_per_second": 346.049,
|
| 256 |
+
"eval_steps_per_second": 1.353,
|
| 257 |
+
"step": 7500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.931098696461825,
|
| 261 |
+
"grad_norm": 9.083893775939941,
|
| 262 |
+
"learning_rate": 2.791875218251659e-05,
|
| 263 |
+
"loss": 2.6738,
|
| 264 |
+
"step": 8000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.931098696461825,
|
| 268 |
+
"eval_cosine_accuracy": 0.907247006893158,
|
| 269 |
+
"eval_loss": 4.833749771118164,
|
| 270 |
+
"eval_runtime": 27.6952,
|
| 271 |
+
"eval_samples_per_second": 341.791,
|
| 272 |
+
"eval_steps_per_second": 1.336,
|
| 273 |
+
"step": 8000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.9892923649906891,
|
| 277 |
+
"grad_norm": 7.430295944213867,
|
| 278 |
+
"learning_rate": 2.9664765452217438e-05,
|
| 279 |
+
"loss": 2.6174,
|
| 280 |
+
"step": 8500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.9892923649906891,
|
| 284 |
+
"eval_cosine_accuracy": 0.9006972312927246,
|
| 285 |
+
"eval_loss": 4.809013366699219,
|
| 286 |
+
"eval_runtime": 27.7002,
|
| 287 |
+
"eval_samples_per_second": 341.731,
|
| 288 |
+
"eval_steps_per_second": 1.336,
|
| 289 |
+
"step": 8500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.047486033519553,
|
| 293 |
+
"grad_norm": 8.466830253601074,
|
| 294 |
+
"learning_rate": 2.998182094709628e-05,
|
| 295 |
+
"loss": 2.5583,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.047486033519553,
|
| 300 |
+
"eval_cosine_accuracy": 0.8939362168312073,
|
| 301 |
+
"eval_loss": 4.823788166046143,
|
| 302 |
+
"eval_runtime": 27.5804,
|
| 303 |
+
"eval_samples_per_second": 343.214,
|
| 304 |
+
"eval_steps_per_second": 1.342,
|
| 305 |
+
"step": 9000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.105679702048417,
|
| 309 |
+
"grad_norm": 7.473945617675781,
|
| 310 |
+
"learning_rate": 2.9909051871166705e-05,
|
| 311 |
+
"loss": 2.5004,
|
| 312 |
+
"step": 9500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.105679702048417,
|
| 316 |
+
"eval_cosine_accuracy": 0.9032326340675354,
|
| 317 |
+
"eval_loss": 4.753988265991211,
|
| 318 |
+
"eval_runtime": 27.8285,
|
| 319 |
+
"eval_samples_per_second": 340.155,
|
| 320 |
+
"eval_steps_per_second": 1.33,
|
| 321 |
+
"step": 9500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.1638733705772812,
|
| 325 |
+
"grad_norm": 7.371562480926514,
|
| 326 |
+
"learning_rate": 2.9781247419540305e-05,
|
| 327 |
+
"loss": 2.4574,
|
| 328 |
+
"step": 10000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.1638733705772812,
|
| 332 |
+
"eval_cosine_accuracy": 0.9001690149307251,
|
| 333 |
+
"eval_loss": 4.775505065917969,
|
| 334 |
+
"eval_runtime": 27.7857,
|
| 335 |
+
"eval_samples_per_second": 340.679,
|
| 336 |
+
"eval_steps_per_second": 1.332,
|
| 337 |
+
"step": 10000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.2220670391061452,
|
| 341 |
+
"grad_norm": 8.302326202392578,
|
| 342 |
+
"learning_rate": 2.9598369954554405e-05,
|
| 343 |
+
"loss": 2.44,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.2220670391061452,
|
| 348 |
+
"eval_cosine_accuracy": 0.895415186882019,
|
| 349 |
+
"eval_loss": 4.801342010498047,
|
| 350 |
+
"eval_runtime": 27.4455,
|
| 351 |
+
"eval_samples_per_second": 344.902,
|
| 352 |
+
"eval_steps_per_second": 1.348,
|
| 353 |
+
"step": 10500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.2802607076350094,
|
| 357 |
+
"grad_norm": 7.892956733703613,
|
| 358 |
+
"learning_rate": 2.936129926675645e-05,
|
| 359 |
+
"loss": 2.3956,
|
| 360 |
+
"step": 11000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.2802607076350094,
|
| 364 |
+
"eval_cosine_accuracy": 0.9016479849815369,
|
| 365 |
+
"eval_loss": 4.581014156341553,
|
| 366 |
+
"eval_runtime": 27.82,
|
| 367 |
+
"eval_samples_per_second": 340.259,
|
| 368 |
+
"eval_steps_per_second": 1.33,
|
| 369 |
+
"step": 11000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.3384543761638734,
|
| 373 |
+
"grad_norm": 7.547521114349365,
|
| 374 |
+
"learning_rate": 2.9070915428691924e-05,
|
| 375 |
+
"loss": 2.3614,
|
| 376 |
+
"step": 11500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.3384543761638734,
|
| 380 |
+
"eval_cosine_accuracy": 0.8949925899505615,
|
| 381 |
+
"eval_loss": 4.6524434089660645,
|
| 382 |
+
"eval_runtime": 27.6717,
|
| 383 |
+
"eval_samples_per_second": 342.082,
|
| 384 |
+
"eval_steps_per_second": 1.337,
|
| 385 |
+
"step": 11500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.3966480446927374,
|
| 389 |
+
"grad_norm": 7.902958393096924,
|
| 390 |
+
"learning_rate": 2.872829642619667e-05,
|
| 391 |
+
"loss": 2.3639,
|
| 392 |
+
"step": 12000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.3966480446927374,
|
| 396 |
+
"eval_cosine_accuracy": 0.8828438520431519,
|
| 397 |
+
"eval_loss": 4.835806369781494,
|
| 398 |
+
"eval_runtime": 27.6782,
|
| 399 |
+
"eval_samples_per_second": 342.002,
|
| 400 |
+
"eval_steps_per_second": 1.337,
|
| 401 |
+
"step": 12000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.4548417132216014,
|
| 405 |
+
"grad_norm": 7.324765205383301,
|
| 406 |
+
"learning_rate": 2.833555124233596e-05,
|
| 407 |
+
"loss": 2.3222,
|
| 408 |
+
"step": 12500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.4548417132216014,
|
| 412 |
+
"eval_cosine_accuracy": 0.8947813510894775,
|
| 413 |
+
"eval_loss": 4.768213272094727,
|
| 414 |
+
"eval_runtime": 27.5948,
|
| 415 |
+
"eval_samples_per_second": 343.035,
|
| 416 |
+
"eval_steps_per_second": 1.341,
|
| 417 |
+
"step": 12500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.5130353817504656,
|
| 421 |
+
"grad_norm": 7.808898448944092,
|
| 422 |
+
"learning_rate": 2.7892564215952825e-05,
|
| 423 |
+
"loss": 2.2942,
|
| 424 |
+
"step": 13000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.5130353817504656,
|
| 428 |
+
"eval_cosine_accuracy": 0.8974223732948303,
|
| 429 |
+
"eval_loss": 4.828193664550781,
|
| 430 |
+
"eval_runtime": 27.5674,
|
| 431 |
+
"eval_samples_per_second": 343.377,
|
| 432 |
+
"eval_steps_per_second": 1.342,
|
| 433 |
+
"step": 13000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.5712290502793296,
|
| 437 |
+
"grad_norm": 6.751107692718506,
|
| 438 |
+
"learning_rate": 2.7401716393648702e-05,
|
| 439 |
+
"loss": 2.2723,
|
| 440 |
+
"step": 13500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.5712290502793296,
|
| 444 |
+
"eval_cosine_accuracy": 0.8914008140563965,
|
| 445 |
+
"eval_loss": 4.6300153732299805,
|
| 446 |
+
"eval_runtime": 27.5296,
|
| 447 |
+
"eval_samples_per_second": 343.848,
|
| 448 |
+
"eval_steps_per_second": 1.344,
|
| 449 |
+
"step": 13500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.6294227188081938,
|
| 453 |
+
"grad_norm": 7.299578666687012,
|
| 454 |
+
"learning_rate": 2.6864829939506563e-05,
|
| 455 |
+
"loss": 2.2473,
|
| 456 |
+
"step": 14000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.6294227188081938,
|
| 460 |
+
"eval_cosine_accuracy": 0.892034649848938,
|
| 461 |
+
"eval_loss": 4.730409145355225,
|
| 462 |
+
"eval_runtime": 27.5527,
|
| 463 |
+
"eval_samples_per_second": 343.56,
|
| 464 |
+
"eval_steps_per_second": 1.343,
|
| 465 |
+
"step": 14000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6876163873370578,
|
| 469 |
+
"grad_norm": 6.653262138366699,
|
| 470 |
+
"learning_rate": 2.6283897925857392e-05,
|
| 471 |
+
"loss": 2.236,
|
| 472 |
+
"step": 14500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.6876163873370578,
|
| 476 |
+
"eval_cosine_accuracy": 0.9077752232551575,
|
| 477 |
+
"eval_loss": 4.478672981262207,
|
| 478 |
+
"eval_runtime": 27.5484,
|
| 479 |
+
"eval_samples_per_second": 343.613,
|
| 480 |
+
"eval_steps_per_second": 1.343,
|
| 481 |
+
"step": 14500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.7458100558659218,
|
| 485 |
+
"grad_norm": 7.958475112915039,
|
| 486 |
+
"learning_rate": 2.566107693443959e-05,
|
| 487 |
+
"loss": 2.2211,
|
| 488 |
+
"step": 15000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.7458100558659218,
|
| 492 |
+
"eval_cosine_accuracy": 0.8841115832328796,
|
| 493 |
+
"eval_loss": 4.705593109130859,
|
| 494 |
+
"eval_runtime": 27.838,
|
| 495 |
+
"eval_samples_per_second": 340.039,
|
| 496 |
+
"eval_steps_per_second": 1.329,
|
| 497 |
+
"step": 15000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.8040037243947857,
|
| 501 |
+
"grad_norm": 6.931536674499512,
|
| 502 |
+
"learning_rate": 2.499867905056577e-05,
|
| 503 |
+
"loss": 2.2015,
|
| 504 |
+
"step": 15500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.8040037243947857,
|
| 508 |
+
"eval_cosine_accuracy": 0.8960490226745605,
|
| 509 |
+
"eval_loss": 4.561342716217041,
|
| 510 |
+
"eval_runtime": 27.6406,
|
| 511 |
+
"eval_samples_per_second": 342.467,
|
| 512 |
+
"eval_steps_per_second": 1.339,
|
| 513 |
+
"step": 15500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.86219739292365,
|
| 517 |
+
"grad_norm": 6.317222595214844,
|
| 518 |
+
"learning_rate": 2.4300597651196786e-05,
|
| 519 |
+
"loss": 2.1922,
|
| 520 |
+
"step": 16000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.86219739292365,
|
| 524 |
+
"eval_cosine_accuracy": 0.9019649028778076,
|
| 525 |
+
"eval_loss": 4.534769535064697,
|
| 526 |
+
"eval_runtime": 27.5599,
|
| 527 |
+
"eval_samples_per_second": 343.47,
|
| 528 |
+
"eval_steps_per_second": 1.343,
|
| 529 |
+
"step": 16000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.920391061452514,
|
| 533 |
+
"grad_norm": 5.440205097198486,
|
| 534 |
+
"learning_rate": 2.3566627155448065e-05,
|
| 535 |
+
"loss": 2.1537,
|
| 536 |
+
"step": 16500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.920391061452514,
|
| 540 |
+
"eval_cosine_accuracy": 0.913057267665863,
|
| 541 |
+
"eval_loss": 4.725633144378662,
|
| 542 |
+
"eval_runtime": 27.6819,
|
| 543 |
+
"eval_samples_per_second": 341.957,
|
| 544 |
+
"eval_steps_per_second": 1.337,
|
| 545 |
+
"step": 16500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.9785847299813781,
|
| 549 |
+
"grad_norm": 6.925086498260498,
|
| 550 |
+
"learning_rate": 2.2800854949259868e-05,
|
| 551 |
+
"loss": 2.1493,
|
| 552 |
+
"step": 17000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.9785847299813781,
|
| 556 |
+
"eval_cosine_accuracy": 0.8949925899505615,
|
| 557 |
+
"eval_loss": 4.73307991027832,
|
| 558 |
+
"eval_runtime": 27.5609,
|
| 559 |
+
"eval_samples_per_second": 343.457,
|
| 560 |
+
"eval_steps_per_second": 1.342,
|
| 561 |
+
"step": 17000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.036778398510242,
|
| 565 |
+
"grad_norm": 9.615991592407227,
|
| 566 |
+
"learning_rate": 2.200612379274325e-05,
|
| 567 |
+
"loss": 2.12,
|
| 568 |
+
"step": 17500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.036778398510242,
|
| 572 |
+
"eval_cosine_accuracy": 0.8875977396965027,
|
| 573 |
+
"eval_loss": 4.846031188964844,
|
| 574 |
+
"eval_runtime": 27.5584,
|
| 575 |
+
"eval_samples_per_second": 343.488,
|
| 576 |
+
"eval_steps_per_second": 1.343,
|
| 577 |
+
"step": 17500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.094972067039106,
|
| 581 |
+
"grad_norm": 6.895238399505615,
|
| 582 |
+
"learning_rate": 2.1185383949713617e-05,
|
| 583 |
+
"loss": 2.0944,
|
| 584 |
+
"step": 18000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.094972067039106,
|
| 588 |
+
"eval_cosine_accuracy": 0.8969997763633728,
|
| 589 |
+
"eval_loss": 4.649144649505615,
|
| 590 |
+
"eval_runtime": 30.2381,
|
| 591 |
+
"eval_samples_per_second": 313.049,
|
| 592 |
+
"eval_steps_per_second": 1.224,
|
| 593 |
+
"step": 18000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.15316573556797,
|
| 597 |
+
"grad_norm": 7.440585136413574,
|
| 598 |
+
"learning_rate": 2.03416822354882e-05,
|
| 599 |
+
"loss": 2.093,
|
| 600 |
+
"step": 18500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.15316573556797,
|
| 604 |
+
"eval_cosine_accuracy": 0.8948869705200195,
|
| 605 |
+
"eval_loss": 4.538448810577393,
|
| 606 |
+
"eval_runtime": 27.8445,
|
| 607 |
+
"eval_samples_per_second": 339.96,
|
| 608 |
+
"eval_steps_per_second": 1.329,
|
| 609 |
+
"step": 18500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.211359404096834,
|
| 613 |
+
"grad_norm": 7.8712639808654785,
|
| 614 |
+
"learning_rate": 1.9479895439841827e-05,
|
| 615 |
+
"loss": 2.0801,
|
| 616 |
+
"step": 19000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.211359404096834,
|
| 620 |
+
"eval_cosine_accuracy": 0.9011197686195374,
|
| 621 |
+
"eval_loss": 4.58160400390625,
|
| 622 |
+
"eval_runtime": 27.5957,
|
| 623 |
+
"eval_samples_per_second": 343.024,
|
| 624 |
+
"eval_steps_per_second": 1.341,
|
| 625 |
+
"step": 19000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.2695530726256985,
|
| 629 |
+
"grad_norm": 9.599085807800293,
|
| 630 |
+
"learning_rate": 1.859976977160929e-05,
|
| 631 |
+
"loss": 2.081,
|
| 632 |
+
"step": 19500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.2695530726256985,
|
| 636 |
+
"eval_cosine_accuracy": 0.9015423655509949,
|
| 637 |
+
"eval_loss": 4.580519199371338,
|
| 638 |
+
"eval_runtime": 27.8327,
|
| 639 |
+
"eval_samples_per_second": 340.103,
|
| 640 |
+
"eval_steps_per_second": 1.329,
|
| 641 |
+
"step": 19500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.3277467411545625,
|
| 645 |
+
"grad_norm": 7.2574238777160645,
|
| 646 |
+
"learning_rate": 1.770628075350192e-05,
|
| 647 |
+
"loss": 2.0818,
|
| 648 |
+
"step": 20000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.3277467411545625,
|
| 652 |
+
"eval_cosine_accuracy": 0.8975279927253723,
|
| 653 |
+
"eval_loss": 4.5440673828125,
|
| 654 |
+
"eval_runtime": 27.5922,
|
| 655 |
+
"eval_samples_per_second": 343.068,
|
| 656 |
+
"eval_steps_per_second": 1.341,
|
| 657 |
+
"step": 20000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.3859404096834265,
|
| 661 |
+
"grad_norm": 7.82363748550415,
|
| 662 |
+
"learning_rate": 1.6802745266074818e-05,
|
| 663 |
+
"loss": 2.0571,
|
| 664 |
+
"step": 20500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.3859404096834265,
|
| 668 |
+
"eval_cosine_accuracy": 0.8922459483146667,
|
| 669 |
+
"eval_loss": 4.727934837341309,
|
| 670 |
+
"eval_runtime": 27.6474,
|
| 671 |
+
"eval_samples_per_second": 342.383,
|
| 672 |
+
"eval_steps_per_second": 1.338,
|
| 673 |
+
"step": 20500
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.4441340782122905,
|
| 677 |
+
"grad_norm": 6.985836982727051,
|
| 678 |
+
"learning_rate": 1.5892517485180574e-05,
|
| 679 |
+
"loss": 2.0463,
|
| 680 |
+
"step": 21000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.4441340782122905,
|
| 684 |
+
"eval_cosine_accuracy": 0.9073526263237,
|
| 685 |
+
"eval_loss": 4.589358806610107,
|
| 686 |
+
"eval_runtime": 27.4789,
|
| 687 |
+
"eval_samples_per_second": 344.483,
|
| 688 |
+
"eval_steps_per_second": 1.346,
|
| 689 |
+
"step": 21000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.5023277467411544,
|
| 693 |
+
"grad_norm": 7.737358093261719,
|
| 694 |
+
"learning_rate": 1.4978976430332556e-05,
|
| 695 |
+
"loss": 2.0326,
|
| 696 |
+
"step": 21500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.5023277467411544,
|
| 700 |
+
"eval_cosine_accuracy": 0.8977392911911011,
|
| 701 |
+
"eval_loss": 4.702400207519531,
|
| 702 |
+
"eval_runtime": 27.6834,
|
| 703 |
+
"eval_samples_per_second": 341.937,
|
| 704 |
+
"eval_steps_per_second": 1.337,
|
| 705 |
+
"step": 21500
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.560521415270019,
|
| 709 |
+
"grad_norm": 6.782015800476074,
|
| 710 |
+
"learning_rate": 1.4065513420841569e-05,
|
| 711 |
+
"loss": 2.0332,
|
| 712 |
+
"step": 22000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.560521415270019,
|
| 716 |
+
"eval_cosine_accuracy": 0.9057680368423462,
|
| 717 |
+
"eval_loss": 4.601651668548584,
|
| 718 |
+
"eval_runtime": 27.6133,
|
| 719 |
+
"eval_samples_per_second": 342.806,
|
| 720 |
+
"eval_steps_per_second": 1.34,
|
| 721 |
+
"step": 22000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.618715083798883,
|
| 725 |
+
"grad_norm": 7.085362911224365,
|
| 726 |
+
"learning_rate": 1.3155519486292301e-05,
|
| 727 |
+
"loss": 2.0155,
|
| 728 |
+
"step": 22500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.618715083798883,
|
| 732 |
+
"eval_cosine_accuracy": 0.9074582457542419,
|
| 733 |
+
"eval_loss": 4.483080863952637,
|
| 734 |
+
"eval_runtime": 27.8124,
|
| 735 |
+
"eval_samples_per_second": 340.352,
|
| 736 |
+
"eval_steps_per_second": 1.33,
|
| 737 |
+
"step": 22500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.676908752327747,
|
| 741 |
+
"grad_norm": 6.544814109802246,
|
| 742 |
+
"learning_rate": 1.2254170004046857e-05,
|
| 743 |
+
"loss": 2.0111,
|
| 744 |
+
"step": 23000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.676908752327747,
|
| 748 |
+
"eval_cosine_accuracy": 0.8939362168312073,
|
| 749 |
+
"eval_loss": 4.641151428222656,
|
| 750 |
+
"eval_runtime": 27.6114,
|
| 751 |
+
"eval_samples_per_second": 342.829,
|
| 752 |
+
"eval_steps_per_second": 1.34,
|
| 753 |
+
"step": 23000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.735102420856611,
|
| 757 |
+
"grad_norm": 6.633194446563721,
|
| 758 |
+
"learning_rate": 1.1361199531960475e-05,
|
| 759 |
+
"loss": 2.0176,
|
| 760 |
+
"step": 23500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.735102420856611,
|
| 764 |
+
"eval_cosine_accuracy": 0.8949925899505615,
|
| 765 |
+
"eval_loss": 4.60220193862915,
|
| 766 |
+
"eval_runtime": 27.6158,
|
| 767 |
+
"eval_samples_per_second": 342.775,
|
| 768 |
+
"eval_steps_per_second": 1.34,
|
| 769 |
+
"step": 23500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.793296089385475,
|
| 773 |
+
"grad_norm": 8.512932777404785,
|
| 774 |
+
"learning_rate": 1.0481737302585223e-05,
|
| 775 |
+
"loss": 2.0028,
|
| 776 |
+
"step": 24000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.793296089385475,
|
| 780 |
+
"eval_cosine_accuracy": 0.8974223732948303,
|
| 781 |
+
"eval_loss": 4.529559135437012,
|
| 782 |
+
"eval_runtime": 27.968,
|
| 783 |
+
"eval_samples_per_second": 338.459,
|
| 784 |
+
"eval_steps_per_second": 1.323,
|
| 785 |
+
"step": 24000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.851489757914339,
|
| 789 |
+
"grad_norm": 7.090054988861084,
|
| 790 |
+
"learning_rate": 9.619048125122396e-06,
|
| 791 |
+
"loss": 1.9965,
|
| 792 |
+
"step": 24500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.851489757914339,
|
| 796 |
+
"eval_cosine_accuracy": 0.8923515677452087,
|
| 797 |
+
"eval_loss": 4.752791881561279,
|
| 798 |
+
"eval_runtime": 27.5418,
|
| 799 |
+
"eval_samples_per_second": 343.696,
|
| 800 |
+
"eval_steps_per_second": 1.343,
|
| 801 |
+
"step": 24500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.9096834264432028,
|
| 805 |
+
"grad_norm": 8.278507232666016,
|
| 806 |
+
"learning_rate": 8.777997941190181e-06,
|
| 807 |
+
"loss": 2.0011,
|
| 808 |
+
"step": 25000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.9096834264432028,
|
| 812 |
+
"eval_cosine_accuracy": 0.8986900448799133,
|
| 813 |
+
"eval_loss": 4.698167324066162,
|
| 814 |
+
"eval_runtime": 27.6911,
|
| 815 |
+
"eval_samples_per_second": 341.842,
|
| 816 |
+
"eval_steps_per_second": 1.336,
|
| 817 |
+
"step": 25000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.967877094972067,
|
| 821 |
+
"grad_norm": 7.455854892730713,
|
| 822 |
+
"learning_rate": 7.958339066434103e-06,
|
| 823 |
+
"loss": 1.9851,
|
| 824 |
+
"step": 25500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.967877094972067,
|
| 828 |
+
"eval_cosine_accuracy": 0.8960490226745605,
|
| 829 |
+
"eval_loss": 4.680306434631348,
|
| 830 |
+
"eval_runtime": 27.9245,
|
| 831 |
+
"eval_samples_per_second": 338.986,
|
| 832 |
+
"eval_steps_per_second": 1.325,
|
| 833 |
+
"step": 25500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 3.026070763500931,
|
| 837 |
+
"grad_norm": 6.495429039001465,
|
| 838 |
+
"learning_rate": 7.164820801974087e-06,
|
| 839 |
+
"loss": 1.9658,
|
| 840 |
+
"step": 26000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 3.026070763500931,
|
| 844 |
+
"eval_cosine_accuracy": 0.8993238806724548,
|
| 845 |
+
"eval_loss": 4.683339595794678,
|
| 846 |
+
"eval_runtime": 27.8555,
|
| 847 |
+
"eval_samples_per_second": 339.825,
|
| 848 |
+
"eval_steps_per_second": 1.328,
|
| 849 |
+
"step": 26000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.084264432029795,
|
| 853 |
+
"grad_norm": 8.352217674255371,
|
| 854 |
+
"learning_rate": 6.400388909031767e-06,
|
| 855 |
+
"loss": 1.9651,
|
| 856 |
+
"step": 26500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.084264432029795,
|
| 860 |
+
"eval_cosine_accuracy": 0.896682858467102,
|
| 861 |
+
"eval_loss": 4.631614685058594,
|
| 862 |
+
"eval_runtime": 27.6286,
|
| 863 |
+
"eval_samples_per_second": 342.616,
|
| 864 |
+
"eval_steps_per_second": 1.339,
|
| 865 |
+
"step": 26500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 3.142458100558659,
|
| 869 |
+
"grad_norm": 7.33491325378418,
|
| 870 |
+
"learning_rate": 5.669312499098547e-06,
|
| 871 |
+
"loss": 1.9609,
|
| 872 |
+
"step": 27000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.142458100558659,
|
| 876 |
+
"eval_cosine_accuracy": 0.8975279927253723,
|
| 877 |
+
"eval_loss": 4.696747779846191,
|
| 878 |
+
"eval_runtime": 27.5958,
|
| 879 |
+
"eval_samples_per_second": 343.023,
|
| 880 |
+
"eval_steps_per_second": 1.341,
|
| 881 |
+
"step": 27000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.200651769087523,
|
| 885 |
+
"grad_norm": 7.817756652832031,
|
| 886 |
+
"learning_rate": 4.9727358335650156e-06,
|
| 887 |
+
"loss": 1.9588,
|
| 888 |
+
"step": 27500
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.200651769087523,
|
| 892 |
+
"eval_cosine_accuracy": 0.896682858467102,
|
| 893 |
+
"eval_loss": 4.715923309326172,
|
| 894 |
+
"eval_runtime": 27.6817,
|
| 895 |
+
"eval_samples_per_second": 341.958,
|
| 896 |
+
"eval_steps_per_second": 1.337,
|
| 897 |
+
"step": 27500
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.2588454376163876,
|
| 901 |
+
"grad_norm": 6.541388034820557,
|
| 902 |
+
"learning_rate": 4.3119517050406135e-06,
|
| 903 |
+
"loss": 1.958,
|
| 904 |
+
"step": 28000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.2588454376163876,
|
| 908 |
+
"eval_cosine_accuracy": 0.9014367461204529,
|
| 909 |
+
"eval_loss": 4.600804328918457,
|
| 910 |
+
"eval_runtime": 27.8473,
|
| 911 |
+
"eval_samples_per_second": 339.925,
|
| 912 |
+
"eval_steps_per_second": 1.329,
|
| 913 |
+
"step": 28000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.3170391061452515,
|
| 917 |
+
"grad_norm": 7.466308116912842,
|
| 918 |
+
"learning_rate": 3.6908445941885822e-06,
|
| 919 |
+
"loss": 1.9494,
|
| 920 |
+
"step": 28500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.3170391061452515,
|
| 924 |
+
"eval_cosine_accuracy": 0.9018592834472656,
|
| 925 |
+
"eval_loss": 4.584753036499023,
|
| 926 |
+
"eval_runtime": 27.8346,
|
| 927 |
+
"eval_samples_per_second": 340.08,
|
| 928 |
+
"eval_steps_per_second": 1.329,
|
| 929 |
+
"step": 28500
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 3.3752327746741155,
|
| 933 |
+
"grad_norm": 7.9546990394592285,
|
| 934 |
+
"learning_rate": 3.1117202239186415e-06,
|
| 935 |
+
"loss": 1.9541,
|
| 936 |
+
"step": 29000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 3.3752327746741155,
|
| 940 |
+
"eval_cosine_accuracy": 0.9040777683258057,
|
| 941 |
+
"eval_loss": 4.553245544433594,
|
| 942 |
+
"eval_runtime": 27.7545,
|
| 943 |
+
"eval_samples_per_second": 341.062,
|
| 944 |
+
"eval_steps_per_second": 1.333,
|
| 945 |
+
"step": 29000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.4334264432029795,
|
| 949 |
+
"grad_norm": 6.409430027008057,
|
| 950 |
+
"learning_rate": 2.5767284654925557e-06,
|
| 951 |
+
"loss": 1.9563,
|
| 952 |
+
"step": 29500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.4334264432029795,
|
| 956 |
+
"eval_cosine_accuracy": 0.9052398204803467,
|
| 957 |
+
"eval_loss": 4.594734191894531,
|
| 958 |
+
"eval_runtime": 27.8799,
|
| 959 |
+
"eval_samples_per_second": 339.528,
|
| 960 |
+
"eval_steps_per_second": 1.327,
|
| 961 |
+
"step": 29500
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.4916201117318435,
|
| 965 |
+
"grad_norm": 6.676296234130859,
|
| 966 |
+
"learning_rate": 2.087855357602124e-06,
|
| 967 |
+
"loss": 1.9593,
|
| 968 |
+
"step": 30000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.4916201117318435,
|
| 972 |
+
"eval_cosine_accuracy": 0.9071413278579712,
|
| 973 |
+
"eval_loss": 4.592144012451172,
|
| 974 |
+
"eval_runtime": 27.8717,
|
| 975 |
+
"eval_samples_per_second": 339.628,
|
| 976 |
+
"eval_steps_per_second": 1.328,
|
| 977 |
+
"step": 30000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.5498137802607075,
|
| 981 |
+
"grad_norm": 6.646908283233643,
|
| 982 |
+
"learning_rate": 1.6469157336393776e-06,
|
| 983 |
+
"loss": 1.9416,
|
| 984 |
+
"step": 30500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.5498137802607075,
|
| 988 |
+
"eval_cosine_accuracy": 0.9049229025840759,
|
| 989 |
+
"eval_loss": 4.61123514175415,
|
| 990 |
+
"eval_runtime": 28.163,
|
| 991 |
+
"eval_samples_per_second": 336.114,
|
| 992 |
+
"eval_steps_per_second": 1.314,
|
| 993 |
+
"step": 30500
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.6080074487895715,
|
| 997 |
+
"grad_norm": 6.432226657867432,
|
| 998 |
+
"learning_rate": 1.2555464845286114e-06,
|
| 999 |
+
"loss": 1.9653,
|
| 1000 |
+
"step": 31000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.6080074487895715,
|
| 1004 |
+
"eval_cosine_accuracy": 0.9083033800125122,
|
| 1005 |
+
"eval_loss": 4.575016498565674,
|
| 1006 |
+
"eval_runtime": 27.7872,
|
| 1007 |
+
"eval_samples_per_second": 340.661,
|
| 1008 |
+
"eval_steps_per_second": 1.332,
|
| 1009 |
+
"step": 31000
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 3.666201117318436,
|
| 1013 |
+
"grad_norm": 6.147933006286621,
|
| 1014 |
+
"learning_rate": 9.15829381125019e-07,
|
| 1015 |
+
"loss": 1.9563,
|
| 1016 |
+
"step": 31500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.666201117318436,
|
| 1020 |
+
"eval_cosine_accuracy": 0.9043946862220764,
|
| 1021 |
+
"eval_loss": 4.594618320465088,
|
| 1022 |
+
"eval_runtime": 27.8051,
|
| 1023 |
+
"eval_samples_per_second": 340.441,
|
| 1024 |
+
"eval_steps_per_second": 1.331,
|
| 1025 |
+
"step": 31500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.7243947858473,
|
| 1029 |
+
"grad_norm": 6.538316249847412,
|
| 1030 |
+
"learning_rate": 6.276643787308245e-07,
|
| 1031 |
+
"loss": 1.9507,
|
| 1032 |
+
"step": 32000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 3.7243947858473,
|
| 1036 |
+
"eval_cosine_accuracy": 0.9060849547386169,
|
| 1037 |
+
"eval_loss": 4.5688347816467285,
|
| 1038 |
+
"eval_runtime": 27.7627,
|
| 1039 |
+
"eval_samples_per_second": 340.961,
|
| 1040 |
+
"eval_steps_per_second": 1.333,
|
| 1041 |
+
"step": 32000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 3.782588454376164,
|
| 1045 |
+
"grad_norm": 7.255917549133301,
|
| 1046 |
+
"learning_rate": 3.928534966307357e-07,
|
| 1047 |
+
"loss": 1.9378,
|
| 1048 |
+
"step": 32500
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 3.782588454376164,
|
| 1052 |
+
"eval_cosine_accuracy": 0.9062961935997009,
|
| 1053 |
+
"eval_loss": 4.608202934265137,
|
| 1054 |
+
"eval_runtime": 27.7075,
|
| 1055 |
+
"eval_samples_per_second": 341.641,
|
| 1056 |
+
"eval_steps_per_second": 1.335,
|
| 1057 |
+
"step": 32500
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 3.840782122905028,
|
| 1061 |
+
"grad_norm": 7.074450969696045,
|
| 1062 |
+
"learning_rate": 2.1257499177363416e-07,
|
| 1063 |
+
"loss": 1.9494,
|
| 1064 |
+
"step": 33000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.840782122905028,
|
| 1068 |
+
"eval_cosine_accuracy": 0.9059792757034302,
|
| 1069 |
+
"eval_loss": 4.594712734222412,
|
| 1070 |
+
"eval_runtime": 27.8802,
|
| 1071 |
+
"eval_samples_per_second": 339.524,
|
| 1072 |
+
"eval_steps_per_second": 1.327,
|
| 1073 |
+
"step": 33000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.898975791433892,
|
| 1077 |
+
"grad_norm": 6.569212436676025,
|
| 1078 |
+
"learning_rate": 8.677577319543827e-08,
|
| 1079 |
+
"loss": 1.9424,
|
| 1080 |
+
"step": 33500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.898975791433892,
|
| 1084 |
+
"eval_cosine_accuracy": 0.9069300889968872,
|
| 1085 |
+
"eval_loss": 4.600465297698975,
|
| 1086 |
+
"eval_runtime": 27.843,
|
| 1087 |
+
"eval_samples_per_second": 339.977,
|
| 1088 |
+
"eval_steps_per_second": 1.329,
|
| 1089 |
+
"step": 33500
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.9571694599627563,
|
| 1093 |
+
"grad_norm": 6.682833194732666,
|
| 1094 |
+
"learning_rate": 1.6338604345084162e-08,
|
| 1095 |
+
"loss": 1.9399,
|
| 1096 |
+
"step": 34000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 3.9571694599627563,
|
| 1100 |
+
"eval_cosine_accuracy": 0.9064018726348877,
|
| 1101 |
+
"eval_loss": 4.5989670753479,
|
| 1102 |
+
"eval_runtime": 28.0362,
|
| 1103 |
+
"eval_samples_per_second": 337.635,
|
| 1104 |
+
"eval_steps_per_second": 1.32,
|
| 1105 |
+
"step": 34000
|
| 1106 |
+
}
|
| 1107 |
+
],
|
| 1108 |
+
"logging_steps": 500,
|
| 1109 |
+
"max_steps": 34368,
|
| 1110 |
+
"num_input_tokens_seen": 0,
|
| 1111 |
+
"num_train_epochs": 4,
|
| 1112 |
+
"save_steps": 500,
|
| 1113 |
+
"stateful_callbacks": {
|
| 1114 |
+
"TrainerControl": {
|
| 1115 |
+
"args": {
|
| 1116 |
+
"should_epoch_stop": false,
|
| 1117 |
+
"should_evaluate": false,
|
| 1118 |
+
"should_log": false,
|
| 1119 |
+
"should_save": true,
|
| 1120 |
+
"should_training_stop": true
|
| 1121 |
+
},
|
| 1122 |
+
"attributes": {}
|
| 1123 |
+
}
|
| 1124 |
+
},
|
| 1125 |
+
"total_flos": 0.0,
|
| 1126 |
+
"train_batch_size": 256,
|
| 1127 |
+
"trial_name": null,
|
| 1128 |
+
"trial_params": null
|
| 1129 |
+
}
|
checkpoint-34368/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2efd1e792aece673d4f9c02b27251769a72b304f7949f137f2a4d2582ff9c2ea
|
| 3 |
+
size 5688
|
checkpoint-34368/training_metrics.json
ADDED
|
@@ -0,0 +1,414 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metrics_history": [
|
| 3 |
+
{
|
| 4 |
+
"epoch": 0.05819366852886406,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"eval_loss": 4.736684322357178,
|
| 7 |
+
"eval_cosine_accuracy": 0.9417916536331177
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"epoch": 0.11638733705772812,
|
| 11 |
+
"global_step": 1000,
|
| 12 |
+
"eval_loss": 4.456507682800293,
|
| 13 |
+
"eval_cosine_accuracy": 0.9421085715293884
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 0.17458100558659218,
|
| 17 |
+
"global_step": 1500,
|
| 18 |
+
"eval_loss": 4.417118072509766,
|
| 19 |
+
"eval_cosine_accuracy": 0.9389393329620361
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.23277467411545624,
|
| 23 |
+
"global_step": 2000,
|
| 24 |
+
"eval_loss": 4.384617805480957,
|
| 25 |
+
"eval_cosine_accuracy": 0.9376716613769531
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2909683426443203,
|
| 29 |
+
"global_step": 2500,
|
| 30 |
+
"eval_loss": 4.382342338562012,
|
| 31 |
+
"eval_cosine_accuracy": 0.929537296295166
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.34916201117318435,
|
| 35 |
+
"global_step": 3000,
|
| 36 |
+
"eval_loss": 4.398530006408691,
|
| 37 |
+
"eval_cosine_accuracy": 0.9236213564872742
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4073556797020484,
|
| 41 |
+
"global_step": 3500,
|
| 42 |
+
"eval_loss": 4.428633689880371,
|
| 43 |
+
"eval_cosine_accuracy": 0.9207690954208374
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.4655493482309125,
|
| 47 |
+
"global_step": 4000,
|
| 48 |
+
"eval_loss": 4.413504600524902,
|
| 49 |
+
"eval_cosine_accuracy": 0.9240439534187317
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.5237430167597765,
|
| 53 |
+
"global_step": 4500,
|
| 54 |
+
"eval_loss": 4.584815979003906,
|
| 55 |
+
"eval_cosine_accuracy": 0.9183393120765686
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.5819366852886406,
|
| 59 |
+
"global_step": 5000,
|
| 60 |
+
"eval_loss": 4.731673240661621,
|
| 61 |
+
"eval_cosine_accuracy": 0.9231988191604614
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.6401303538175046,
|
| 65 |
+
"global_step": 5500,
|
| 66 |
+
"eval_loss": 4.590743064880371,
|
| 67 |
+
"eval_cosine_accuracy": 0.9202408790588379
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.6983240223463687,
|
| 71 |
+
"global_step": 6000,
|
| 72 |
+
"eval_loss": 4.662985324859619,
|
| 73 |
+
"eval_cosine_accuracy": 0.9188675284385681
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7565176908752328,
|
| 77 |
+
"global_step": 6500,
|
| 78 |
+
"eval_loss": 4.784646511077881,
|
| 79 |
+
"eval_cosine_accuracy": 0.9199239611625671
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8147113594040968,
|
| 83 |
+
"global_step": 7000,
|
| 84 |
+
"eval_loss": 4.925645351409912,
|
| 85 |
+
"eval_cosine_accuracy": 0.9054510593414307
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.8729050279329609,
|
| 89 |
+
"global_step": 7500,
|
| 90 |
+
"eval_loss": 4.843690395355225,
|
| 91 |
+
"eval_cosine_accuracy": 0.9056623578071594
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.931098696461825,
|
| 95 |
+
"global_step": 8000,
|
| 96 |
+
"eval_loss": 4.833749771118164,
|
| 97 |
+
"eval_cosine_accuracy": 0.907247006893158
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.9892923649906891,
|
| 101 |
+
"global_step": 8500,
|
| 102 |
+
"eval_loss": 4.809013366699219,
|
| 103 |
+
"eval_cosine_accuracy": 0.9006972312927246
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.047486033519553,
|
| 107 |
+
"global_step": 9000,
|
| 108 |
+
"eval_loss": 4.823788166046143,
|
| 109 |
+
"eval_cosine_accuracy": 0.8939362168312073
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.105679702048417,
|
| 113 |
+
"global_step": 9500,
|
| 114 |
+
"eval_loss": 4.753988265991211,
|
| 115 |
+
"eval_cosine_accuracy": 0.9032326340675354
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.1638733705772812,
|
| 119 |
+
"global_step": 10000,
|
| 120 |
+
"eval_loss": 4.775505065917969,
|
| 121 |
+
"eval_cosine_accuracy": 0.9001690149307251
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.2220670391061452,
|
| 125 |
+
"global_step": 10500,
|
| 126 |
+
"eval_loss": 4.801342010498047,
|
| 127 |
+
"eval_cosine_accuracy": 0.895415186882019
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.2802607076350094,
|
| 131 |
+
"global_step": 11000,
|
| 132 |
+
"eval_loss": 4.581014156341553,
|
| 133 |
+
"eval_cosine_accuracy": 0.9016479849815369
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.3384543761638734,
|
| 137 |
+
"global_step": 11500,
|
| 138 |
+
"eval_loss": 4.6524434089660645,
|
| 139 |
+
"eval_cosine_accuracy": 0.8949925899505615
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.3966480446927374,
|
| 143 |
+
"global_step": 12000,
|
| 144 |
+
"eval_loss": 4.835806369781494,
|
| 145 |
+
"eval_cosine_accuracy": 0.8828438520431519
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.4548417132216014,
|
| 149 |
+
"global_step": 12500,
|
| 150 |
+
"eval_loss": 4.768213272094727,
|
| 151 |
+
"eval_cosine_accuracy": 0.8947813510894775
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.5130353817504656,
|
| 155 |
+
"global_step": 13000,
|
| 156 |
+
"eval_loss": 4.828193664550781,
|
| 157 |
+
"eval_cosine_accuracy": 0.8974223732948303
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.5712290502793296,
|
| 161 |
+
"global_step": 13500,
|
| 162 |
+
"eval_loss": 4.6300153732299805,
|
| 163 |
+
"eval_cosine_accuracy": 0.8914008140563965
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.6294227188081938,
|
| 167 |
+
"global_step": 14000,
|
| 168 |
+
"eval_loss": 4.730409145355225,
|
| 169 |
+
"eval_cosine_accuracy": 0.892034649848938
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.6876163873370578,
|
| 173 |
+
"global_step": 14500,
|
| 174 |
+
"eval_loss": 4.478672981262207,
|
| 175 |
+
"eval_cosine_accuracy": 0.9077752232551575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.7458100558659218,
|
| 179 |
+
"global_step": 15000,
|
| 180 |
+
"eval_loss": 4.705593109130859,
|
| 181 |
+
"eval_cosine_accuracy": 0.8841115832328796
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.8040037243947857,
|
| 185 |
+
"global_step": 15500,
|
| 186 |
+
"eval_loss": 4.561342716217041,
|
| 187 |
+
"eval_cosine_accuracy": 0.8960490226745605
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.86219739292365,
|
| 191 |
+
"global_step": 16000,
|
| 192 |
+
"eval_loss": 4.534769535064697,
|
| 193 |
+
"eval_cosine_accuracy": 0.9019649028778076
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.920391061452514,
|
| 197 |
+
"global_step": 16500,
|
| 198 |
+
"eval_loss": 4.725633144378662,
|
| 199 |
+
"eval_cosine_accuracy": 0.913057267665863
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.9785847299813781,
|
| 203 |
+
"global_step": 17000,
|
| 204 |
+
"eval_loss": 4.73307991027832,
|
| 205 |
+
"eval_cosine_accuracy": 0.8949925899505615
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.036778398510242,
|
| 209 |
+
"global_step": 17500,
|
| 210 |
+
"eval_loss": 4.846031188964844,
|
| 211 |
+
"eval_cosine_accuracy": 0.8875977396965027
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.094972067039106,
|
| 215 |
+
"global_step": 18000,
|
| 216 |
+
"eval_loss": 4.649144649505615,
|
| 217 |
+
"eval_cosine_accuracy": 0.8969997763633728
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.15316573556797,
|
| 221 |
+
"global_step": 18500,
|
| 222 |
+
"eval_loss": 4.538448810577393,
|
| 223 |
+
"eval_cosine_accuracy": 0.8948869705200195
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.211359404096834,
|
| 227 |
+
"global_step": 19000,
|
| 228 |
+
"eval_loss": 4.58160400390625,
|
| 229 |
+
"eval_cosine_accuracy": 0.9011197686195374
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.2695530726256985,
|
| 233 |
+
"global_step": 19500,
|
| 234 |
+
"eval_loss": 4.580519199371338,
|
| 235 |
+
"eval_cosine_accuracy": 0.9015423655509949
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.3277467411545625,
|
| 239 |
+
"global_step": 20000,
|
| 240 |
+
"eval_loss": 4.5440673828125,
|
| 241 |
+
"eval_cosine_accuracy": 0.8975279927253723
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.3859404096834265,
|
| 245 |
+
"global_step": 20500,
|
| 246 |
+
"eval_loss": 4.727934837341309,
|
| 247 |
+
"eval_cosine_accuracy": 0.8922459483146667
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.4441340782122905,
|
| 251 |
+
"global_step": 21000,
|
| 252 |
+
"eval_loss": 4.589358806610107,
|
| 253 |
+
"eval_cosine_accuracy": 0.9073526263237
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.5023277467411544,
|
| 257 |
+
"global_step": 21500,
|
| 258 |
+
"eval_loss": 4.702400207519531,
|
| 259 |
+
"eval_cosine_accuracy": 0.8977392911911011
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.560521415270019,
|
| 263 |
+
"global_step": 22000,
|
| 264 |
+
"eval_loss": 4.601651668548584,
|
| 265 |
+
"eval_cosine_accuracy": 0.9057680368423462
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.618715083798883,
|
| 269 |
+
"global_step": 22500,
|
| 270 |
+
"eval_loss": 4.483080863952637,
|
| 271 |
+
"eval_cosine_accuracy": 0.9074582457542419
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.676908752327747,
|
| 275 |
+
"global_step": 23000,
|
| 276 |
+
"eval_loss": 4.641151428222656,
|
| 277 |
+
"eval_cosine_accuracy": 0.8939362168312073
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.735102420856611,
|
| 281 |
+
"global_step": 23500,
|
| 282 |
+
"eval_loss": 4.60220193862915,
|
| 283 |
+
"eval_cosine_accuracy": 0.8949925899505615
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.793296089385475,
|
| 287 |
+
"global_step": 24000,
|
| 288 |
+
"eval_loss": 4.529559135437012,
|
| 289 |
+
"eval_cosine_accuracy": 0.8974223732948303
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.851489757914339,
|
| 293 |
+
"global_step": 24500,
|
| 294 |
+
"eval_loss": 4.752791881561279,
|
| 295 |
+
"eval_cosine_accuracy": 0.8923515677452087
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.9096834264432028,
|
| 299 |
+
"global_step": 25000,
|
| 300 |
+
"eval_loss": 4.698167324066162,
|
| 301 |
+
"eval_cosine_accuracy": 0.8986900448799133
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.967877094972067,
|
| 305 |
+
"global_step": 25500,
|
| 306 |
+
"eval_loss": 4.680306434631348,
|
| 307 |
+
"eval_cosine_accuracy": 0.8960490226745605
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.026070763500931,
|
| 311 |
+
"global_step": 26000,
|
| 312 |
+
"eval_loss": 4.683339595794678,
|
| 313 |
+
"eval_cosine_accuracy": 0.8993238806724548
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.084264432029795,
|
| 317 |
+
"global_step": 26500,
|
| 318 |
+
"eval_loss": 4.631614685058594,
|
| 319 |
+
"eval_cosine_accuracy": 0.896682858467102
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 3.142458100558659,
|
| 323 |
+
"global_step": 27000,
|
| 324 |
+
"eval_loss": 4.696747779846191,
|
| 325 |
+
"eval_cosine_accuracy": 0.8975279927253723
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.200651769087523,
|
| 329 |
+
"global_step": 27500,
|
| 330 |
+
"eval_loss": 4.715923309326172,
|
| 331 |
+
"eval_cosine_accuracy": 0.896682858467102
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.2588454376163876,
|
| 335 |
+
"global_step": 28000,
|
| 336 |
+
"eval_loss": 4.600804328918457,
|
| 337 |
+
"eval_cosine_accuracy": 0.9014367461204529
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.3170391061452515,
|
| 341 |
+
"global_step": 28500,
|
| 342 |
+
"eval_loss": 4.584753036499023,
|
| 343 |
+
"eval_cosine_accuracy": 0.9018592834472656
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 3.3752327746741155,
|
| 347 |
+
"global_step": 29000,
|
| 348 |
+
"eval_loss": 4.553245544433594,
|
| 349 |
+
"eval_cosine_accuracy": 0.9040777683258057
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.4334264432029795,
|
| 353 |
+
"global_step": 29500,
|
| 354 |
+
"eval_loss": 4.594734191894531,
|
| 355 |
+
"eval_cosine_accuracy": 0.9052398204803467
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 3.4916201117318435,
|
| 359 |
+
"global_step": 30000,
|
| 360 |
+
"eval_loss": 4.592144012451172,
|
| 361 |
+
"eval_cosine_accuracy": 0.9071413278579712
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 3.5498137802607075,
|
| 365 |
+
"global_step": 30500,
|
| 366 |
+
"eval_loss": 4.61123514175415,
|
| 367 |
+
"eval_cosine_accuracy": 0.9049229025840759
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.6080074487895715,
|
| 371 |
+
"global_step": 31000,
|
| 372 |
+
"eval_loss": 4.575016498565674,
|
| 373 |
+
"eval_cosine_accuracy": 0.9083033800125122
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.666201117318436,
|
| 377 |
+
"global_step": 31500,
|
| 378 |
+
"eval_loss": 4.594618320465088,
|
| 379 |
+
"eval_cosine_accuracy": 0.9043946862220764
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.7243947858473,
|
| 383 |
+
"global_step": 32000,
|
| 384 |
+
"eval_loss": 4.5688347816467285,
|
| 385 |
+
"eval_cosine_accuracy": 0.9060849547386169
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 3.782588454376164,
|
| 389 |
+
"global_step": 32500,
|
| 390 |
+
"eval_loss": 4.608202934265137,
|
| 391 |
+
"eval_cosine_accuracy": 0.9062961935997009
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 3.840782122905028,
|
| 395 |
+
"global_step": 33000,
|
| 396 |
+
"eval_loss": 4.594712734222412,
|
| 397 |
+
"eval_cosine_accuracy": 0.9059792757034302
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 3.898975791433892,
|
| 401 |
+
"global_step": 33500,
|
| 402 |
+
"eval_loss": 4.600465297698975,
|
| 403 |
+
"eval_cosine_accuracy": 0.9069300889968872
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.9571694599627563,
|
| 407 |
+
"global_step": 34000,
|
| 408 |
+
"eval_loss": 4.5989670753479,
|
| 409 |
+
"eval_cosine_accuracy": 0.9064018726348877
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"current_epoch": 4,
|
| 413 |
+
"global_step": 34368
|
| 414 |
+
}
|
checkpoint-34368/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|