add best checkpoint
Browse files- .gitattributes +1 -0
- config.json +50 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +61 -0
- trainer_state.json +749 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dangvantuan/vietnamese-embedding-LongContext",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VietnameseForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "dangvantuan/Vietnamese_impl--configuration.VietnameseConfig",
|
| 9 |
+
"AutoModel": "dangvantuan/Vietnamese_impl--modeling.VietnameseModel",
|
| 10 |
+
"AutoModelForMaskedLM": "dangvantuan/Vietnamese_impl--modeling.VietnameseForMaskedLM",
|
| 11 |
+
"AutoModelForMultipleChoice": "dangvantuan/Vietnamese_impl--modeling.VietnameseForMultipleChoice",
|
| 12 |
+
"AutoModelForQuestionAnswering": "dangvantuan/Vietnamese_impl--modeling.VietnameseForQuestionAnswering",
|
| 13 |
+
"AutoModelForSequenceClassification": "dangvantuan/Vietnamese_impl--modeling.VietnameseForSequenceClassification",
|
| 14 |
+
"AutoModelForTokenClassification": "dangvantuan/Vietnamese_impl--modeling.VietnameseForTokenClassification"
|
| 15 |
+
},
|
| 16 |
+
"classifier_dropout": 0.0,
|
| 17 |
+
"hidden_act": "gelu",
|
| 18 |
+
"hidden_dropout_prob": 0.1,
|
| 19 |
+
"hidden_size": 768,
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "LABEL_0"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"layer_norm_type": "layer_norm",
|
| 30 |
+
"logn_attention_clip1": false,
|
| 31 |
+
"logn_attention_scale": false,
|
| 32 |
+
"max_position_embeddings": 8192,
|
| 33 |
+
"model_type": "Vietnamese",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pack_qkv": true,
|
| 37 |
+
"pad_token_id": 1,
|
| 38 |
+
"position_embedding_type": "rope",
|
| 39 |
+
"rope_scaling": {
|
| 40 |
+
"factor": 8.0,
|
| 41 |
+
"type": "ntk"
|
| 42 |
+
},
|
| 43 |
+
"rope_theta": 20000,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.45.1",
|
| 46 |
+
"type_vocab_size": 1,
|
| 47 |
+
"unpad_inputs": false,
|
| 48 |
+
"use_memory_efficient_attention": false,
|
| 49 |
+
"vocab_size": 250002
|
| 50 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57184ce961ad61ed3525edfa549b08b91858e8b437d72da3cfe3ab98aa6d6e22
|
| 3 |
+
size 1224717040
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe7c0a591d7470cfef6141b8ab50c9d73128f8f1212f832a8da087976bb5e4b8
|
| 3 |
+
size 2449519034
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:357bb9cb4eafbd51257eb3538d782f0d9715c2fd8692ee322772a1cfd4aba7e9
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cde91977c4ecd9ac899d17836f5b9b93e91041f60c5049deda9f805d66a03a2
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6f4bfef0fd9457498b433fe0b94a27c210f982888370dc0f4ed95c100267ea5
|
| 3 |
+
size 17082833
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 8192,
|
| 50 |
+
"model_max_length": 32768,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,749 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.091291069984436,
|
| 3 |
+
"best_model_checkpoint": "vietnamese-emb-long-mlm/checkpoint-8000",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05952380952380952,
|
| 13 |
+
"grad_norm": 7.383795261383057,
|
| 14 |
+
"learning_rate": 4.940476190476191e-05,
|
| 15 |
+
"loss": 6.9284,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11904761904761904,
|
| 20 |
+
"grad_norm": 11.806465148925781,
|
| 21 |
+
"learning_rate": 4.880952380952381e-05,
|
| 22 |
+
"loss": 5.4103,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17857142857142858,
|
| 27 |
+
"grad_norm": 10.51978588104248,
|
| 28 |
+
"learning_rate": 4.8214285714285716e-05,
|
| 29 |
+
"loss": 4.45,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.23809523809523808,
|
| 34 |
+
"grad_norm": 10.803540229797363,
|
| 35 |
+
"learning_rate": 4.761904761904762e-05,
|
| 36 |
+
"loss": 3.7495,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2976190476190476,
|
| 41 |
+
"grad_norm": 10.87264347076416,
|
| 42 |
+
"learning_rate": 4.7023809523809525e-05,
|
| 43 |
+
"loss": 3.3683,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2976190476190476,
|
| 48 |
+
"eval_loss": 2.989553928375244,
|
| 49 |
+
"eval_runtime": 105.8686,
|
| 50 |
+
"eval_samples_per_second": 112.838,
|
| 51 |
+
"eval_steps_per_second": 1.766,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.35714285714285715,
|
| 56 |
+
"grad_norm": 9.709155082702637,
|
| 57 |
+
"learning_rate": 4.642857142857143e-05,
|
| 58 |
+
"loss": 3.0939,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.4166666666666667,
|
| 63 |
+
"grad_norm": 9.323984146118164,
|
| 64 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 65 |
+
"loss": 2.8534,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.47619047619047616,
|
| 70 |
+
"grad_norm": 10.167367935180664,
|
| 71 |
+
"learning_rate": 4.523809523809524e-05,
|
| 72 |
+
"loss": 2.7091,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5357142857142857,
|
| 77 |
+
"grad_norm": 10.095072746276855,
|
| 78 |
+
"learning_rate": 4.464285714285715e-05,
|
| 79 |
+
"loss": 2.5711,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5952380952380952,
|
| 84 |
+
"grad_norm": 9.4666109085083,
|
| 85 |
+
"learning_rate": 4.404761904761905e-05,
|
| 86 |
+
"loss": 2.4663,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5952380952380952,
|
| 91 |
+
"eval_loss": 2.2190322875976562,
|
| 92 |
+
"eval_runtime": 106.1834,
|
| 93 |
+
"eval_samples_per_second": 112.504,
|
| 94 |
+
"eval_steps_per_second": 1.761,
|
| 95 |
+
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.6547619047619048,
|
| 99 |
+
"grad_norm": 9.085387229919434,
|
| 100 |
+
"learning_rate": 4.345238095238096e-05,
|
| 101 |
+
"loss": 2.4001,
|
| 102 |
+
"step": 1100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.7142857142857143,
|
| 106 |
+
"grad_norm": 9.016592979431152,
|
| 107 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 108 |
+
"loss": 2.3036,
|
| 109 |
+
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.7738095238095238,
|
| 113 |
+
"grad_norm": 10.062590599060059,
|
| 114 |
+
"learning_rate": 4.226190476190476e-05,
|
| 115 |
+
"loss": 2.2139,
|
| 116 |
+
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.8333333333333334,
|
| 120 |
+
"grad_norm": 9.198400497436523,
|
| 121 |
+
"learning_rate": 4.166666666666667e-05,
|
| 122 |
+
"loss": 2.1477,
|
| 123 |
+
"step": 1400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.8928571428571429,
|
| 127 |
+
"grad_norm": 9.555102348327637,
|
| 128 |
+
"learning_rate": 4.107142857142857e-05,
|
| 129 |
+
"loss": 2.078,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.8928571428571429,
|
| 134 |
+
"eval_loss": 1.8398191928863525,
|
| 135 |
+
"eval_runtime": 106.2078,
|
| 136 |
+
"eval_samples_per_second": 112.478,
|
| 137 |
+
"eval_steps_per_second": 1.761,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.9523809523809523,
|
| 142 |
+
"grad_norm": 9.729957580566406,
|
| 143 |
+
"learning_rate": 4.047619047619048e-05,
|
| 144 |
+
"loss": 2.0146,
|
| 145 |
+
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.0119047619047619,
|
| 149 |
+
"grad_norm": 9.68885326385498,
|
| 150 |
+
"learning_rate": 3.9880952380952386e-05,
|
| 151 |
+
"loss": 1.9381,
|
| 152 |
+
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.0714285714285714,
|
| 156 |
+
"grad_norm": 8.330371856689453,
|
| 157 |
+
"learning_rate": 3.928571428571429e-05,
|
| 158 |
+
"loss": 1.8773,
|
| 159 |
+
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.130952380952381,
|
| 163 |
+
"grad_norm": 9.066886901855469,
|
| 164 |
+
"learning_rate": 3.8690476190476195e-05,
|
| 165 |
+
"loss": 1.8749,
|
| 166 |
+
"step": 1900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.1904761904761905,
|
| 170 |
+
"grad_norm": 10.275750160217285,
|
| 171 |
+
"learning_rate": 3.809523809523809e-05,
|
| 172 |
+
"loss": 1.8204,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.1904761904761905,
|
| 177 |
+
"eval_loss": 1.667816400527954,
|
| 178 |
+
"eval_runtime": 106.1061,
|
| 179 |
+
"eval_samples_per_second": 112.585,
|
| 180 |
+
"eval_steps_per_second": 1.762,
|
| 181 |
+
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.25,
|
| 185 |
+
"grad_norm": 9.68263053894043,
|
| 186 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 187 |
+
"loss": 1.8137,
|
| 188 |
+
"step": 2100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.3095238095238095,
|
| 192 |
+
"grad_norm": 10.254537582397461,
|
| 193 |
+
"learning_rate": 3.690476190476191e-05,
|
| 194 |
+
"loss": 1.8096,
|
| 195 |
+
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.369047619047619,
|
| 199 |
+
"grad_norm": 8.361231803894043,
|
| 200 |
+
"learning_rate": 3.630952380952381e-05,
|
| 201 |
+
"loss": 1.7509,
|
| 202 |
+
"step": 2300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.4285714285714286,
|
| 206 |
+
"grad_norm": 9.450984954833984,
|
| 207 |
+
"learning_rate": 3.571428571428572e-05,
|
| 208 |
+
"loss": 1.7277,
|
| 209 |
+
"step": 2400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.4880952380952381,
|
| 213 |
+
"grad_norm": 8.3367280960083,
|
| 214 |
+
"learning_rate": 3.511904761904762e-05,
|
| 215 |
+
"loss": 1.7063,
|
| 216 |
+
"step": 2500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.4880952380952381,
|
| 220 |
+
"eval_loss": 1.55353844165802,
|
| 221 |
+
"eval_runtime": 106.2169,
|
| 222 |
+
"eval_samples_per_second": 112.468,
|
| 223 |
+
"eval_steps_per_second": 1.761,
|
| 224 |
+
"step": 2500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.5476190476190477,
|
| 228 |
+
"grad_norm": 8.55213451385498,
|
| 229 |
+
"learning_rate": 3.4523809523809526e-05,
|
| 230 |
+
"loss": 1.6952,
|
| 231 |
+
"step": 2600
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.6071428571428572,
|
| 235 |
+
"grad_norm": 8.386811256408691,
|
| 236 |
+
"learning_rate": 3.392857142857143e-05,
|
| 237 |
+
"loss": 1.6654,
|
| 238 |
+
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.6666666666666665,
|
| 242 |
+
"grad_norm": 9.841432571411133,
|
| 243 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 244 |
+
"loss": 1.6662,
|
| 245 |
+
"step": 2800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.7261904761904763,
|
| 249 |
+
"grad_norm": 8.69044303894043,
|
| 250 |
+
"learning_rate": 3.273809523809524e-05,
|
| 251 |
+
"loss": 1.6291,
|
| 252 |
+
"step": 2900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.7857142857142856,
|
| 256 |
+
"grad_norm": 9.23985481262207,
|
| 257 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 258 |
+
"loss": 1.5943,
|
| 259 |
+
"step": 3000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.7857142857142856,
|
| 263 |
+
"eval_loss": 1.464246392250061,
|
| 264 |
+
"eval_runtime": 106.2444,
|
| 265 |
+
"eval_samples_per_second": 112.439,
|
| 266 |
+
"eval_steps_per_second": 1.76,
|
| 267 |
+
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.8452380952380953,
|
| 271 |
+
"grad_norm": 8.489648818969727,
|
| 272 |
+
"learning_rate": 3.154761904761905e-05,
|
| 273 |
+
"loss": 1.6024,
|
| 274 |
+
"step": 3100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.9047619047619047,
|
| 278 |
+
"grad_norm": 8.592900276184082,
|
| 279 |
+
"learning_rate": 3.095238095238095e-05,
|
| 280 |
+
"loss": 1.5711,
|
| 281 |
+
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.9642857142857144,
|
| 285 |
+
"grad_norm": 8.73353099822998,
|
| 286 |
+
"learning_rate": 3.0357142857142857e-05,
|
| 287 |
+
"loss": 1.561,
|
| 288 |
+
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.0238095238095237,
|
| 292 |
+
"grad_norm": 7.832152843475342,
|
| 293 |
+
"learning_rate": 2.9761904761904762e-05,
|
| 294 |
+
"loss": 1.4996,
|
| 295 |
+
"step": 3400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.0833333333333335,
|
| 299 |
+
"grad_norm": 8.37968921661377,
|
| 300 |
+
"learning_rate": 2.916666666666667e-05,
|
| 301 |
+
"loss": 1.5235,
|
| 302 |
+
"step": 3500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0833333333333335,
|
| 306 |
+
"eval_loss": 1.3883955478668213,
|
| 307 |
+
"eval_runtime": 106.3163,
|
| 308 |
+
"eval_samples_per_second": 112.363,
|
| 309 |
+
"eval_steps_per_second": 1.759,
|
| 310 |
+
"step": 3500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.142857142857143,
|
| 314 |
+
"grad_norm": 9.074413299560547,
|
| 315 |
+
"learning_rate": 2.857142857142857e-05,
|
| 316 |
+
"loss": 1.4867,
|
| 317 |
+
"step": 3600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.2023809523809526,
|
| 321 |
+
"grad_norm": 8.715752601623535,
|
| 322 |
+
"learning_rate": 2.797619047619048e-05,
|
| 323 |
+
"loss": 1.481,
|
| 324 |
+
"step": 3700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.261904761904762,
|
| 328 |
+
"grad_norm": 8.675792694091797,
|
| 329 |
+
"learning_rate": 2.7380952380952383e-05,
|
| 330 |
+
"loss": 1.4462,
|
| 331 |
+
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.3214285714285716,
|
| 335 |
+
"grad_norm": 8.826884269714355,
|
| 336 |
+
"learning_rate": 2.6785714285714288e-05,
|
| 337 |
+
"loss": 1.449,
|
| 338 |
+
"step": 3900
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.380952380952381,
|
| 342 |
+
"grad_norm": 8.927966117858887,
|
| 343 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 344 |
+
"loss": 1.4307,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.380952380952381,
|
| 349 |
+
"eval_loss": 1.3017064332962036,
|
| 350 |
+
"eval_runtime": 106.1765,
|
| 351 |
+
"eval_samples_per_second": 112.511,
|
| 352 |
+
"eval_steps_per_second": 1.761,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.4404761904761907,
|
| 357 |
+
"grad_norm": 7.1491804122924805,
|
| 358 |
+
"learning_rate": 2.5595238095238093e-05,
|
| 359 |
+
"loss": 1.4789,
|
| 360 |
+
"step": 4100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.5,
|
| 364 |
+
"grad_norm": 7.50277853012085,
|
| 365 |
+
"learning_rate": 2.5e-05,
|
| 366 |
+
"loss": 1.4296,
|
| 367 |
+
"step": 4200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.5595238095238093,
|
| 371 |
+
"grad_norm": 8.132680892944336,
|
| 372 |
+
"learning_rate": 2.4404761904761906e-05,
|
| 373 |
+
"loss": 1.4177,
|
| 374 |
+
"step": 4300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.619047619047619,
|
| 378 |
+
"grad_norm": 8.233142852783203,
|
| 379 |
+
"learning_rate": 2.380952380952381e-05,
|
| 380 |
+
"loss": 1.3953,
|
| 381 |
+
"step": 4400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.678571428571429,
|
| 385 |
+
"grad_norm": 7.6400628089904785,
|
| 386 |
+
"learning_rate": 2.3214285714285715e-05,
|
| 387 |
+
"loss": 1.4063,
|
| 388 |
+
"step": 4500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.678571428571429,
|
| 392 |
+
"eval_loss": 1.2739932537078857,
|
| 393 |
+
"eval_runtime": 106.1766,
|
| 394 |
+
"eval_samples_per_second": 112.511,
|
| 395 |
+
"eval_steps_per_second": 1.761,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.738095238095238,
|
| 400 |
+
"grad_norm": 7.416648864746094,
|
| 401 |
+
"learning_rate": 2.261904761904762e-05,
|
| 402 |
+
"loss": 1.4008,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.7976190476190474,
|
| 407 |
+
"grad_norm": 7.283276081085205,
|
| 408 |
+
"learning_rate": 2.2023809523809524e-05,
|
| 409 |
+
"loss": 1.3818,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.857142857142857,
|
| 414 |
+
"grad_norm": 8.360782623291016,
|
| 415 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 416 |
+
"loss": 1.379,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.9166666666666665,
|
| 421 |
+
"grad_norm": 9.960053443908691,
|
| 422 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 423 |
+
"loss": 1.3479,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.9761904761904763,
|
| 428 |
+
"grad_norm": 8.903584480285645,
|
| 429 |
+
"learning_rate": 2.023809523809524e-05,
|
| 430 |
+
"loss": 1.3389,
|
| 431 |
+
"step": 5000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.9761904761904763,
|
| 435 |
+
"eval_loss": 1.2187227010726929,
|
| 436 |
+
"eval_runtime": 106.0745,
|
| 437 |
+
"eval_samples_per_second": 112.619,
|
| 438 |
+
"eval_steps_per_second": 1.763,
|
| 439 |
+
"step": 5000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.0357142857142856,
|
| 443 |
+
"grad_norm": 8.299568176269531,
|
| 444 |
+
"learning_rate": 1.9642857142857145e-05,
|
| 445 |
+
"loss": 1.3336,
|
| 446 |
+
"step": 5100
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.0952380952380953,
|
| 450 |
+
"grad_norm": 8.194002151489258,
|
| 451 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 452 |
+
"loss": 1.3102,
|
| 453 |
+
"step": 5200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.1547619047619047,
|
| 457 |
+
"grad_norm": 7.804888725280762,
|
| 458 |
+
"learning_rate": 1.8452380952380954e-05,
|
| 459 |
+
"loss": 1.3354,
|
| 460 |
+
"step": 5300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.2142857142857144,
|
| 464 |
+
"grad_norm": 7.510008811950684,
|
| 465 |
+
"learning_rate": 1.785714285714286e-05,
|
| 466 |
+
"loss": 1.3382,
|
| 467 |
+
"step": 5400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.2738095238095237,
|
| 471 |
+
"grad_norm": 7.9406023025512695,
|
| 472 |
+
"learning_rate": 1.7261904761904763e-05,
|
| 473 |
+
"loss": 1.2996,
|
| 474 |
+
"step": 5500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.2738095238095237,
|
| 478 |
+
"eval_loss": 1.2163845300674438,
|
| 479 |
+
"eval_runtime": 106.2374,
|
| 480 |
+
"eval_samples_per_second": 112.446,
|
| 481 |
+
"eval_steps_per_second": 1.76,
|
| 482 |
+
"step": 5500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.3333333333333335,
|
| 486 |
+
"grad_norm": 7.935986042022705,
|
| 487 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 488 |
+
"loss": 1.2889,
|
| 489 |
+
"step": 5600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.392857142857143,
|
| 493 |
+
"grad_norm": 7.514946937561035,
|
| 494 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 495 |
+
"loss": 1.3353,
|
| 496 |
+
"step": 5700
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.4523809523809526,
|
| 500 |
+
"grad_norm": 8.081690788269043,
|
| 501 |
+
"learning_rate": 1.5476190476190476e-05,
|
| 502 |
+
"loss": 1.2959,
|
| 503 |
+
"step": 5800
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.511904761904762,
|
| 507 |
+
"grad_norm": 8.02477741241455,
|
| 508 |
+
"learning_rate": 1.4880952380952381e-05,
|
| 509 |
+
"loss": 1.2467,
|
| 510 |
+
"step": 5900
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.571428571428571,
|
| 514 |
+
"grad_norm": 8.462018013000488,
|
| 515 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 516 |
+
"loss": 1.2899,
|
| 517 |
+
"step": 6000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 3.571428571428571,
|
| 521 |
+
"eval_loss": 1.1731750965118408,
|
| 522 |
+
"eval_runtime": 106.1002,
|
| 523 |
+
"eval_samples_per_second": 112.592,
|
| 524 |
+
"eval_steps_per_second": 1.762,
|
| 525 |
+
"step": 6000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.630952380952381,
|
| 529 |
+
"grad_norm": 7.650486469268799,
|
| 530 |
+
"learning_rate": 1.3690476190476192e-05,
|
| 531 |
+
"loss": 1.2878,
|
| 532 |
+
"step": 6100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.6904761904761907,
|
| 536 |
+
"grad_norm": 8.889339447021484,
|
| 537 |
+
"learning_rate": 1.3095238095238096e-05,
|
| 538 |
+
"loss": 1.2704,
|
| 539 |
+
"step": 6200
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.75,
|
| 543 |
+
"grad_norm": 9.502975463867188,
|
| 544 |
+
"learning_rate": 1.25e-05,
|
| 545 |
+
"loss": 1.2406,
|
| 546 |
+
"step": 6300
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.8095238095238093,
|
| 550 |
+
"grad_norm": 9.480072975158691,
|
| 551 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 552 |
+
"loss": 1.2707,
|
| 553 |
+
"step": 6400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.869047619047619,
|
| 557 |
+
"grad_norm": 7.378728866577148,
|
| 558 |
+
"learning_rate": 1.130952380952381e-05,
|
| 559 |
+
"loss": 1.2343,
|
| 560 |
+
"step": 6500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.869047619047619,
|
| 564 |
+
"eval_loss": 1.1631048917770386,
|
| 565 |
+
"eval_runtime": 106.023,
|
| 566 |
+
"eval_samples_per_second": 112.674,
|
| 567 |
+
"eval_steps_per_second": 1.764,
|
| 568 |
+
"step": 6500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.928571428571429,
|
| 572 |
+
"grad_norm": 8.64068603515625,
|
| 573 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 574 |
+
"loss": 1.2478,
|
| 575 |
+
"step": 6600
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.988095238095238,
|
| 579 |
+
"grad_norm": 8.00733470916748,
|
| 580 |
+
"learning_rate": 1.011904761904762e-05,
|
| 581 |
+
"loss": 1.2414,
|
| 582 |
+
"step": 6700
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.0476190476190474,
|
| 586 |
+
"grad_norm": 7.568075180053711,
|
| 587 |
+
"learning_rate": 9.523809523809523e-06,
|
| 588 |
+
"loss": 1.2533,
|
| 589 |
+
"step": 6800
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 4.107142857142857,
|
| 593 |
+
"grad_norm": 7.190471649169922,
|
| 594 |
+
"learning_rate": 8.92857142857143e-06,
|
| 595 |
+
"loss": 1.2495,
|
| 596 |
+
"step": 6900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.166666666666667,
|
| 600 |
+
"grad_norm": 8.588766098022461,
|
| 601 |
+
"learning_rate": 8.333333333333334e-06,
|
| 602 |
+
"loss": 1.2095,
|
| 603 |
+
"step": 7000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.166666666666667,
|
| 607 |
+
"eval_loss": 1.0942662954330444,
|
| 608 |
+
"eval_runtime": 106.0638,
|
| 609 |
+
"eval_samples_per_second": 112.63,
|
| 610 |
+
"eval_steps_per_second": 1.763,
|
| 611 |
+
"step": 7000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.226190476190476,
|
| 615 |
+
"grad_norm": 8.47437858581543,
|
| 616 |
+
"learning_rate": 7.738095238095238e-06,
|
| 617 |
+
"loss": 1.2134,
|
| 618 |
+
"step": 7100
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.285714285714286,
|
| 622 |
+
"grad_norm": 7.481777191162109,
|
| 623 |
+
"learning_rate": 7.142857142857143e-06,
|
| 624 |
+
"loss": 1.1873,
|
| 625 |
+
"step": 7200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 4.345238095238095,
|
| 629 |
+
"grad_norm": 7.533321380615234,
|
| 630 |
+
"learning_rate": 6.547619047619048e-06,
|
| 631 |
+
"loss": 1.2022,
|
| 632 |
+
"step": 7300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.404761904761905,
|
| 636 |
+
"grad_norm": 8.106829643249512,
|
| 637 |
+
"learning_rate": 5.9523809523809525e-06,
|
| 638 |
+
"loss": 1.2162,
|
| 639 |
+
"step": 7400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.464285714285714,
|
| 643 |
+
"grad_norm": 7.893404483795166,
|
| 644 |
+
"learning_rate": 5.357142857142857e-06,
|
| 645 |
+
"loss": 1.2078,
|
| 646 |
+
"step": 7500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.464285714285714,
|
| 650 |
+
"eval_loss": 1.1191558837890625,
|
| 651 |
+
"eval_runtime": 106.3099,
|
| 652 |
+
"eval_samples_per_second": 112.37,
|
| 653 |
+
"eval_steps_per_second": 1.759,
|
| 654 |
+
"step": 7500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.523809523809524,
|
| 658 |
+
"grad_norm": 8.90477466583252,
|
| 659 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 660 |
+
"loss": 1.219,
|
| 661 |
+
"step": 7600
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.583333333333333,
|
| 665 |
+
"grad_norm": 7.603702545166016,
|
| 666 |
+
"learning_rate": 4.166666666666667e-06,
|
| 667 |
+
"loss": 1.2,
|
| 668 |
+
"step": 7700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.642857142857143,
|
| 672 |
+
"grad_norm": 8.275321006774902,
|
| 673 |
+
"learning_rate": 3.5714285714285714e-06,
|
| 674 |
+
"loss": 1.1985,
|
| 675 |
+
"step": 7800
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.7023809523809526,
|
| 679 |
+
"grad_norm": 8.652661323547363,
|
| 680 |
+
"learning_rate": 2.9761904761904763e-06,
|
| 681 |
+
"loss": 1.2421,
|
| 682 |
+
"step": 7900
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.761904761904762,
|
| 686 |
+
"grad_norm": 8.569392204284668,
|
| 687 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 688 |
+
"loss": 1.208,
|
| 689 |
+
"step": 8000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.761904761904762,
|
| 693 |
+
"eval_loss": 1.091291069984436,
|
| 694 |
+
"eval_runtime": 106.5156,
|
| 695 |
+
"eval_samples_per_second": 112.153,
|
| 696 |
+
"eval_steps_per_second": 1.756,
|
| 697 |
+
"step": 8000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.821428571428571,
|
| 701 |
+
"grad_norm": 8.579488754272461,
|
| 702 |
+
"learning_rate": 1.7857142857142857e-06,
|
| 703 |
+
"loss": 1.2274,
|
| 704 |
+
"step": 8100
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.880952380952381,
|
| 708 |
+
"grad_norm": 9.347880363464355,
|
| 709 |
+
"learning_rate": 1.1904761904761904e-06,
|
| 710 |
+
"loss": 1.1833,
|
| 711 |
+
"step": 8200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.940476190476191,
|
| 715 |
+
"grad_norm": 7.7748894691467285,
|
| 716 |
+
"learning_rate": 5.952380952380952e-07,
|
| 717 |
+
"loss": 1.1919,
|
| 718 |
+
"step": 8300
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 5.0,
|
| 722 |
+
"grad_norm": 8.465712547302246,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 1.2069,
|
| 725 |
+
"step": 8400
|
| 726 |
+
}
|
| 727 |
+
],
|
| 728 |
+
"logging_steps": 100,
|
| 729 |
+
"max_steps": 8400,
|
| 730 |
+
"num_input_tokens_seen": 0,
|
| 731 |
+
"num_train_epochs": 5,
|
| 732 |
+
"save_steps": 2000,
|
| 733 |
+
"stateful_callbacks": {
|
| 734 |
+
"TrainerControl": {
|
| 735 |
+
"args": {
|
| 736 |
+
"should_epoch_stop": false,
|
| 737 |
+
"should_evaluate": false,
|
| 738 |
+
"should_log": false,
|
| 739 |
+
"should_save": true,
|
| 740 |
+
"should_training_stop": true
|
| 741 |
+
},
|
| 742 |
+
"attributes": {}
|
| 743 |
+
}
|
| 744 |
+
},
|
| 745 |
+
"total_flos": 1.5633072459126792e+16,
|
| 746 |
+
"train_batch_size": 64,
|
| 747 |
+
"trial_name": null,
|
| 748 |
+
"trial_params": null
|
| 749 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f8c45d08af0ee44560afc58d52049dd77ef5fe6673cec5f873bc5fe795169a2
|
| 3 |
+
size 5176
|