Upload NLLB zh-vi model
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- config.json +33 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +56 -0
- tokenizer.json +3 -0
- tokenizer_config.json +93 -0
- trainer_state.json +2743 -0
- training_args.bin +0 -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
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 55001
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "relu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"M2M100ForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_attention_heads": 16,
|
| 11 |
+
"decoder_ffn_dim": 8192,
|
| 12 |
+
"decoder_layerdrop": 0,
|
| 13 |
+
"decoder_layers": 24,
|
| 14 |
+
"decoder_start_token_id": 2,
|
| 15 |
+
"dropout": 0.1,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
+
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"init_std": 0.02,
|
| 23 |
+
"is_encoder_decoder": true,
|
| 24 |
+
"max_length": null,
|
| 25 |
+
"max_position_embeddings": 1024,
|
| 26 |
+
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"scale_embedding": true,
|
| 30 |
+
"transformers_version": "4.57.3",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 55002
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
2
|
| 7 |
+
],
|
| 8 |
+
"max_length": 200,
|
| 9 |
+
"pad_token_id": 1,
|
| 10 |
+
"transformers_version": "4.57.3"
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94e8ee5c399bbd866d3f01b31ad642166e21b071eecddef849cd6a4ab111ddd5
|
| 3 |
+
size 2329331808
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3214125b55810ea6cad3a2a25f4fa73af74a63bccf84c62aa355800a55e434ce
|
| 3 |
+
size 1098834
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"zho_Hans",
|
| 4 |
+
"eng_Latn",
|
| 5 |
+
"vie_Latn"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"cls_token": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"eos_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"content": "<mask>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"pad_token": {
|
| 36 |
+
"content": "<pad>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
},
|
| 42 |
+
"sep_token": {
|
| 43 |
+
"content": "</s>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
},
|
| 49 |
+
"unk_token": {
|
| 50 |
+
"content": "<unk>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false
|
| 55 |
+
}
|
| 56 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:814d9aac5e07146b90dd656faccff0b54bf906c38de64ab866d22d36d0491b0a
|
| 3 |
+
size 4593242
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"4": {
|
| 36 |
+
"content": "zho_Hans",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "eng_Latn",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "vie_Latn",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"55001": {
|
| 60 |
+
"content": "<mask>",
|
| 61 |
+
"lstrip": true,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"additional_special_tokens": [
|
| 69 |
+
"zho_Hans",
|
| 70 |
+
"eng_Latn",
|
| 71 |
+
"vie_Latn"
|
| 72 |
+
],
|
| 73 |
+
"bos_token": "<s>",
|
| 74 |
+
"clean_up_tokenization_spaces": true,
|
| 75 |
+
"cls_token": "<s>",
|
| 76 |
+
"eos_token": "</s>",
|
| 77 |
+
"extra_special_tokens": {},
|
| 78 |
+
"legacy_behaviour": false,
|
| 79 |
+
"mask_token": "<mask>",
|
| 80 |
+
"max_length": null,
|
| 81 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 82 |
+
"pad_to_multiple_of": null,
|
| 83 |
+
"pad_token": "<pad>",
|
| 84 |
+
"pad_token_type_id": 0,
|
| 85 |
+
"padding_side": "right",
|
| 86 |
+
"return_tensors": "pt",
|
| 87 |
+
"sep_token": "</s>",
|
| 88 |
+
"sp_model_kwargs": {},
|
| 89 |
+
"src_lang": "zho_Hans",
|
| 90 |
+
"tgt_lang": "vie_Latn",
|
| 91 |
+
"tokenizer_class": "NllbTokenizer",
|
| 92 |
+
"unk_token": "<unk>"
|
| 93 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2743 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1548,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.010342598577892695,
|
| 14 |
+
"grad_norm": 0.27074137330055237,
|
| 15 |
+
"learning_rate": 1.5384615384615385e-07,
|
| 16 |
+
"loss": 0.5239,
|
| 17 |
+
"step": 4
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02068519715578539,
|
| 21 |
+
"grad_norm": 0.2690924108028412,
|
| 22 |
+
"learning_rate": 3.5897435897435896e-07,
|
| 23 |
+
"loss": 0.519,
|
| 24 |
+
"step": 8
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.031027795733678087,
|
| 28 |
+
"grad_norm": 0.28973960876464844,
|
| 29 |
+
"learning_rate": 5.641025641025641e-07,
|
| 30 |
+
"loss": 0.5216,
|
| 31 |
+
"step": 12
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04137039431157078,
|
| 35 |
+
"grad_norm": 0.2677304744720459,
|
| 36 |
+
"learning_rate": 7.692307692307693e-07,
|
| 37 |
+
"loss": 0.5403,
|
| 38 |
+
"step": 16
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.051712992889463474,
|
| 42 |
+
"grad_norm": 0.2680451571941376,
|
| 43 |
+
"learning_rate": 9.743589743589742e-07,
|
| 44 |
+
"loss": 0.518,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.062055591467356175,
|
| 49 |
+
"grad_norm": 0.25933119654655457,
|
| 50 |
+
"learning_rate": 1.1794871794871795e-06,
|
| 51 |
+
"loss": 0.5192,
|
| 52 |
+
"step": 24
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07239819004524888,
|
| 56 |
+
"grad_norm": 0.25746598839759827,
|
| 57 |
+
"learning_rate": 1.3846153846153844e-06,
|
| 58 |
+
"loss": 0.5164,
|
| 59 |
+
"step": 28
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08274078862314156,
|
| 63 |
+
"grad_norm": 0.2424672544002533,
|
| 64 |
+
"learning_rate": 1.5897435897435895e-06,
|
| 65 |
+
"loss": 0.5016,
|
| 66 |
+
"step": 32
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09308338720103426,
|
| 70 |
+
"grad_norm": 0.22520849108695984,
|
| 71 |
+
"learning_rate": 1.7948717948717948e-06,
|
| 72 |
+
"loss": 0.5133,
|
| 73 |
+
"step": 36
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.10342598577892695,
|
| 77 |
+
"grad_norm": 0.208700492978096,
|
| 78 |
+
"learning_rate": 2e-06,
|
| 79 |
+
"loss": 0.503,
|
| 80 |
+
"step": 40
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11376858435681965,
|
| 84 |
+
"grad_norm": 0.2092197686433792,
|
| 85 |
+
"learning_rate": 2.2051282051282052e-06,
|
| 86 |
+
"loss": 0.5016,
|
| 87 |
+
"step": 44
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12411118293471235,
|
| 91 |
+
"grad_norm": 0.20155887305736542,
|
| 92 |
+
"learning_rate": 2.41025641025641e-06,
|
| 93 |
+
"loss": 0.4955,
|
| 94 |
+
"step": 48
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13445378151260504,
|
| 98 |
+
"grad_norm": 0.20360776782035828,
|
| 99 |
+
"learning_rate": 2.6153846153846154e-06,
|
| 100 |
+
"loss": 0.51,
|
| 101 |
+
"step": 52
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14479638009049775,
|
| 105 |
+
"grad_norm": 0.20055116713047028,
|
| 106 |
+
"learning_rate": 2.8205128205128207e-06,
|
| 107 |
+
"loss": 0.5073,
|
| 108 |
+
"step": 56
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15513897866839044,
|
| 112 |
+
"grad_norm": 0.2022508680820465,
|
| 113 |
+
"learning_rate": 3.0256410256410256e-06,
|
| 114 |
+
"loss": 0.4918,
|
| 115 |
+
"step": 60
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16548157724628312,
|
| 119 |
+
"grad_norm": 0.1955750733613968,
|
| 120 |
+
"learning_rate": 3.230769230769231e-06,
|
| 121 |
+
"loss": 0.4917,
|
| 122 |
+
"step": 64
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17582417582417584,
|
| 126 |
+
"grad_norm": 0.18670685589313507,
|
| 127 |
+
"learning_rate": 3.4358974358974353e-06,
|
| 128 |
+
"loss": 0.4936,
|
| 129 |
+
"step": 68
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18616677440206852,
|
| 133 |
+
"grad_norm": 0.192545086145401,
|
| 134 |
+
"learning_rate": 3.6410256410256406e-06,
|
| 135 |
+
"loss": 0.4972,
|
| 136 |
+
"step": 72
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.1965093729799612,
|
| 140 |
+
"grad_norm": 0.1836402714252472,
|
| 141 |
+
"learning_rate": 3.846153846153846e-06,
|
| 142 |
+
"loss": 0.4823,
|
| 143 |
+
"step": 76
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2068519715578539,
|
| 147 |
+
"grad_norm": 0.18833868205547333,
|
| 148 |
+
"learning_rate": 3.993881715007257e-06,
|
| 149 |
+
"loss": 0.4825,
|
| 150 |
+
"step": 80
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2171945701357466,
|
| 154 |
+
"grad_norm": 0.18157020211219788,
|
| 155 |
+
"learning_rate": 3.969491760330399e-06,
|
| 156 |
+
"loss": 0.4829,
|
| 157 |
+
"step": 84
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2275371687136393,
|
| 161 |
+
"grad_norm": 0.17653386294841766,
|
| 162 |
+
"learning_rate": 3.945234630128603e-06,
|
| 163 |
+
"loss": 0.4886,
|
| 164 |
+
"step": 88
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23787976729153198,
|
| 168 |
+
"grad_norm": 0.18460187315940857,
|
| 169 |
+
"learning_rate": 3.9211099617411865e-06,
|
| 170 |
+
"loss": 0.491,
|
| 171 |
+
"step": 92
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2482223658694247,
|
| 175 |
+
"grad_norm": 0.17642319202423096,
|
| 176 |
+
"learning_rate": 3.897117392507468e-06,
|
| 177 |
+
"loss": 0.4857,
|
| 178 |
+
"step": 96
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2585649644473174,
|
| 182 |
+
"grad_norm": 0.17706429958343506,
|
| 183 |
+
"learning_rate": 3.873256559766764e-06,
|
| 184 |
+
"loss": 0.494,
|
| 185 |
+
"step": 100
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.2689075630252101,
|
| 189 |
+
"grad_norm": 0.1816156804561615,
|
| 190 |
+
"learning_rate": 3.8495271008583914e-06,
|
| 191 |
+
"loss": 0.4911,
|
| 192 |
+
"step": 104
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2792501616031028,
|
| 196 |
+
"grad_norm": 0.19248028099536896,
|
| 197 |
+
"learning_rate": 3.825928653121668e-06,
|
| 198 |
+
"loss": 0.4866,
|
| 199 |
+
"step": 108
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2895927601809955,
|
| 203 |
+
"grad_norm": 0.17712807655334473,
|
| 204 |
+
"learning_rate": 3.80246085389591e-06,
|
| 205 |
+
"loss": 0.4763,
|
| 206 |
+
"step": 112
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29993535875888816,
|
| 210 |
+
"grad_norm": 0.18759045004844666,
|
| 211 |
+
"learning_rate": 3.779123340520437e-06,
|
| 212 |
+
"loss": 0.4812,
|
| 213 |
+
"step": 116
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3102779573367809,
|
| 217 |
+
"grad_norm": 0.19693388044834137,
|
| 218 |
+
"learning_rate": 3.755915750334564e-06,
|
| 219 |
+
"loss": 0.4783,
|
| 220 |
+
"step": 120
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3206205559146736,
|
| 224 |
+
"grad_norm": 0.1827310472726822,
|
| 225 |
+
"learning_rate": 3.7328377206776083e-06,
|
| 226 |
+
"loss": 0.477,
|
| 227 |
+
"step": 124
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.33096315449256625,
|
| 231 |
+
"grad_norm": 0.18313142657279968,
|
| 232 |
+
"learning_rate": 3.7098888888888884e-06,
|
| 233 |
+
"loss": 0.496,
|
| 234 |
+
"step": 128
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.34130575307045896,
|
| 238 |
+
"grad_norm": 0.17326150834560394,
|
| 239 |
+
"learning_rate": 3.687068892307722e-06,
|
| 240 |
+
"loss": 0.4778,
|
| 241 |
+
"step": 132
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3516483516483517,
|
| 245 |
+
"grad_norm": 0.17738491296768188,
|
| 246 |
+
"learning_rate": 3.664377368273423e-06,
|
| 247 |
+
"loss": 0.4813,
|
| 248 |
+
"step": 136
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.36199095022624433,
|
| 252 |
+
"grad_norm": 0.18592627346515656,
|
| 253 |
+
"learning_rate": 3.6418139541253126e-06,
|
| 254 |
+
"loss": 0.4783,
|
| 255 |
+
"step": 140
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.37233354880413705,
|
| 259 |
+
"grad_norm": 0.17538052797317505,
|
| 260 |
+
"learning_rate": 3.6193782872027053e-06,
|
| 261 |
+
"loss": 0.4726,
|
| 262 |
+
"step": 144
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3826761473820297,
|
| 266 |
+
"grad_norm": 0.1824338138103485,
|
| 267 |
+
"learning_rate": 3.5970700048449203e-06,
|
| 268 |
+
"loss": 0.4637,
|
| 269 |
+
"step": 148
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.3930187459599224,
|
| 273 |
+
"grad_norm": 0.1739794909954071,
|
| 274 |
+
"learning_rate": 3.5748887443912734e-06,
|
| 275 |
+
"loss": 0.4832,
|
| 276 |
+
"step": 152
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.40336134453781514,
|
| 280 |
+
"grad_norm": 0.19277994334697723,
|
| 281 |
+
"learning_rate": 3.552834143181082e-06,
|
| 282 |
+
"loss": 0.4773,
|
| 283 |
+
"step": 156
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4137039431157078,
|
| 287 |
+
"grad_norm": 0.1671997308731079,
|
| 288 |
+
"learning_rate": 3.5309058385536637e-06,
|
| 289 |
+
"loss": 0.4739,
|
| 290 |
+
"step": 160
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.4240465416936005,
|
| 294 |
+
"grad_norm": 0.17366255819797516,
|
| 295 |
+
"learning_rate": 3.5091034678483365e-06,
|
| 296 |
+
"loss": 0.4872,
|
| 297 |
+
"step": 164
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4343891402714932,
|
| 301 |
+
"grad_norm": 0.17070995271205902,
|
| 302 |
+
"learning_rate": 3.4874266684044155e-06,
|
| 303 |
+
"loss": 0.4593,
|
| 304 |
+
"step": 168
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4447317388493859,
|
| 308 |
+
"grad_norm": 0.1726539433002472,
|
| 309 |
+
"learning_rate": 3.4658750775612206e-06,
|
| 310 |
+
"loss": 0.4682,
|
| 311 |
+
"step": 172
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4550743374272786,
|
| 315 |
+
"grad_norm": 0.17803026735782623,
|
| 316 |
+
"learning_rate": 3.4444483326580667e-06,
|
| 317 |
+
"loss": 0.4623,
|
| 318 |
+
"step": 176
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.4654169360051713,
|
| 322 |
+
"grad_norm": 0.18144938349723816,
|
| 323 |
+
"learning_rate": 3.423146071034272e-06,
|
| 324 |
+
"loss": 0.4694,
|
| 325 |
+
"step": 180
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.47575953458306397,
|
| 329 |
+
"grad_norm": 0.18337614834308624,
|
| 330 |
+
"learning_rate": 3.401967930029155e-06,
|
| 331 |
+
"loss": 0.4697,
|
| 332 |
+
"step": 184
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4861021331609567,
|
| 336 |
+
"grad_norm": 0.18037910759449005,
|
| 337 |
+
"learning_rate": 3.3809135469820304e-06,
|
| 338 |
+
"loss": 0.4664,
|
| 339 |
+
"step": 188
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.4964447317388494,
|
| 343 |
+
"grad_norm": 0.1738828718662262,
|
| 344 |
+
"learning_rate": 3.3599825592322174e-06,
|
| 345 |
+
"loss": 0.4697,
|
| 346 |
+
"step": 192
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5067873303167421,
|
| 350 |
+
"grad_norm": 0.17767304182052612,
|
| 351 |
+
"learning_rate": 3.3391746041190326e-06,
|
| 352 |
+
"loss": 0.4866,
|
| 353 |
+
"step": 196
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5171299288946348,
|
| 357 |
+
"grad_norm": 0.17905977368354797,
|
| 358 |
+
"learning_rate": 3.3184893189817926e-06,
|
| 359 |
+
"loss": 0.4755,
|
| 360 |
+
"step": 200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5274725274725275,
|
| 364 |
+
"grad_norm": 0.18217241764068604,
|
| 365 |
+
"learning_rate": 3.2979263411598156e-06,
|
| 366 |
+
"loss": 0.4801,
|
| 367 |
+
"step": 204
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5378151260504201,
|
| 371 |
+
"grad_norm": 0.17312566936016083,
|
| 372 |
+
"learning_rate": 3.2774853079924182e-06,
|
| 373 |
+
"loss": 0.4772,
|
| 374 |
+
"step": 208
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5481577246283129,
|
| 378 |
+
"grad_norm": 0.17987386882305145,
|
| 379 |
+
"learning_rate": 3.257165856818918e-06,
|
| 380 |
+
"loss": 0.4731,
|
| 381 |
+
"step": 212
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5585003232062056,
|
| 385 |
+
"grad_norm": 0.17333056032657623,
|
| 386 |
+
"learning_rate": 3.236967624978633e-06,
|
| 387 |
+
"loss": 0.4725,
|
| 388 |
+
"step": 216
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5688429217840982,
|
| 392 |
+
"grad_norm": 0.18219755589962006,
|
| 393 |
+
"learning_rate": 3.2168902498108775e-06,
|
| 394 |
+
"loss": 0.4758,
|
| 395 |
+
"step": 220
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.579185520361991,
|
| 399 |
+
"grad_norm": 0.17562930285930634,
|
| 400 |
+
"learning_rate": 3.196933368654973e-06,
|
| 401 |
+
"loss": 0.4643,
|
| 402 |
+
"step": 224
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5895281189398837,
|
| 406 |
+
"grad_norm": 0.21644935011863708,
|
| 407 |
+
"learning_rate": 3.1770966188502337e-06,
|
| 408 |
+
"loss": 0.4794,
|
| 409 |
+
"step": 228
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5998707175177763,
|
| 413 |
+
"grad_norm": 0.18018363416194916,
|
| 414 |
+
"learning_rate": 3.157379637735977e-06,
|
| 415 |
+
"loss": 0.4668,
|
| 416 |
+
"step": 232
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6102133160956691,
|
| 420 |
+
"grad_norm": 0.1677103340625763,
|
| 421 |
+
"learning_rate": 3.137782062651522e-06,
|
| 422 |
+
"loss": 0.4564,
|
| 423 |
+
"step": 236
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6205559146735617,
|
| 427 |
+
"grad_norm": 0.17912864685058594,
|
| 428 |
+
"learning_rate": 3.1183035309361833e-06,
|
| 429 |
+
"loss": 0.4603,
|
| 430 |
+
"step": 240
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6308985132514544,
|
| 434 |
+
"grad_norm": 0.18761886656284332,
|
| 435 |
+
"learning_rate": 3.0989436799292814e-06,
|
| 436 |
+
"loss": 0.4799,
|
| 437 |
+
"step": 244
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6412411118293472,
|
| 441 |
+
"grad_norm": 0.17829325795173645,
|
| 442 |
+
"learning_rate": 3.079702146970131e-06,
|
| 443 |
+
"loss": 0.4718,
|
| 444 |
+
"step": 248
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6515837104072398,
|
| 448 |
+
"grad_norm": 0.19033263623714447,
|
| 449 |
+
"learning_rate": 3.060578569398049e-06,
|
| 450 |
+
"loss": 0.4751,
|
| 451 |
+
"step": 252
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6619263089851325,
|
| 455 |
+
"grad_norm": 0.1795780062675476,
|
| 456 |
+
"learning_rate": 3.0415725845523547e-06,
|
| 457 |
+
"loss": 0.4604,
|
| 458 |
+
"step": 256
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6722689075630253,
|
| 462 |
+
"grad_norm": 0.18677003681659698,
|
| 463 |
+
"learning_rate": 3.022683829772365e-06,
|
| 464 |
+
"loss": 0.4677,
|
| 465 |
+
"step": 260
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6826115061409179,
|
| 469 |
+
"grad_norm": 0.1794733852148056,
|
| 470 |
+
"learning_rate": 3.0039119423973945e-06,
|
| 471 |
+
"loss": 0.4671,
|
| 472 |
+
"step": 264
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6929541047188106,
|
| 476 |
+
"grad_norm": 0.1785053014755249,
|
| 477 |
+
"learning_rate": 2.9852565597667635e-06,
|
| 478 |
+
"loss": 0.4761,
|
| 479 |
+
"step": 268
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7032967032967034,
|
| 483 |
+
"grad_norm": 0.17754320800304413,
|
| 484 |
+
"learning_rate": 2.9667173192197887e-06,
|
| 485 |
+
"loss": 0.4707,
|
| 486 |
+
"step": 272
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.713639301874596,
|
| 490 |
+
"grad_norm": 0.17548543214797974,
|
| 491 |
+
"learning_rate": 2.9482938580957856e-06,
|
| 492 |
+
"loss": 0.4534,
|
| 493 |
+
"step": 276
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7239819004524887,
|
| 497 |
+
"grad_norm": 0.17609195411205292,
|
| 498 |
+
"learning_rate": 2.9299858137340735e-06,
|
| 499 |
+
"loss": 0.4591,
|
| 500 |
+
"step": 280
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7343244990303813,
|
| 504 |
+
"grad_norm": 0.17191891372203827,
|
| 505 |
+
"learning_rate": 2.911792823473968e-06,
|
| 506 |
+
"loss": 0.4697,
|
| 507 |
+
"step": 284
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7446670976082741,
|
| 511 |
+
"grad_norm": 0.18207724392414093,
|
| 512 |
+
"learning_rate": 2.8937145246547875e-06,
|
| 513 |
+
"loss": 0.4654,
|
| 514 |
+
"step": 288
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7550096961861668,
|
| 518 |
+
"grad_norm": 0.17942476272583008,
|
| 519 |
+
"learning_rate": 2.8757505546158493e-06,
|
| 520 |
+
"loss": 0.4688,
|
| 521 |
+
"step": 292
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7653522947640594,
|
| 525 |
+
"grad_norm": 0.18172645568847656,
|
| 526 |
+
"learning_rate": 2.857900550696469e-06,
|
| 527 |
+
"loss": 0.4616,
|
| 528 |
+
"step": 296
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.7756948933419522,
|
| 532 |
+
"grad_norm": 0.18675239384174347,
|
| 533 |
+
"learning_rate": 2.8401641502359657e-06,
|
| 534 |
+
"loss": 0.4612,
|
| 535 |
+
"step": 300
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7860374919198448,
|
| 539 |
+
"grad_norm": 0.18713857233524323,
|
| 540 |
+
"learning_rate": 2.822540990573655e-06,
|
| 541 |
+
"loss": 0.468,
|
| 542 |
+
"step": 304
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7963800904977375,
|
| 546 |
+
"grad_norm": 0.192363440990448,
|
| 547 |
+
"learning_rate": 2.805030709048856e-06,
|
| 548 |
+
"loss": 0.472,
|
| 549 |
+
"step": 308
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8067226890756303,
|
| 553 |
+
"grad_norm": 0.17535482347011566,
|
| 554 |
+
"learning_rate": 2.787632943000885e-06,
|
| 555 |
+
"loss": 0.4651,
|
| 556 |
+
"step": 312
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8170652876535229,
|
| 560 |
+
"grad_norm": 0.1680748015642166,
|
| 561 |
+
"learning_rate": 2.7703473297690585e-06,
|
| 562 |
+
"loss": 0.476,
|
| 563 |
+
"step": 316
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8274078862314156,
|
| 567 |
+
"grad_norm": 0.1780477613210678,
|
| 568 |
+
"learning_rate": 2.753173506692695e-06,
|
| 569 |
+
"loss": 0.4715,
|
| 570 |
+
"step": 320
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8377504848093084,
|
| 574 |
+
"grad_norm": 0.17565058171749115,
|
| 575 |
+
"learning_rate": 2.7361111111111114e-06,
|
| 576 |
+
"loss": 0.4724,
|
| 577 |
+
"step": 324
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.848093083387201,
|
| 581 |
+
"grad_norm": 0.17358048260211945,
|
| 582 |
+
"learning_rate": 2.719159780363624e-06,
|
| 583 |
+
"loss": 0.4819,
|
| 584 |
+
"step": 328
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8584356819650937,
|
| 588 |
+
"grad_norm": 0.1844065934419632,
|
| 589 |
+
"learning_rate": 2.702319151789551e-06,
|
| 590 |
+
"loss": 0.4769,
|
| 591 |
+
"step": 332
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8687782805429864,
|
| 595 |
+
"grad_norm": 0.1706087440252304,
|
| 596 |
+
"learning_rate": 2.6855888627282097e-06,
|
| 597 |
+
"loss": 0.4688,
|
| 598 |
+
"step": 336
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8791208791208791,
|
| 602 |
+
"grad_norm": 0.17604754865169525,
|
| 603 |
+
"learning_rate": 2.6689685505189168e-06,
|
| 604 |
+
"loss": 0.4604,
|
| 605 |
+
"step": 340
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8894634776987718,
|
| 609 |
+
"grad_norm": 0.19641447067260742,
|
| 610 |
+
"learning_rate": 2.6524578525009895e-06,
|
| 611 |
+
"loss": 0.4619,
|
| 612 |
+
"step": 344
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8998060762766645,
|
| 616 |
+
"grad_norm": 0.1839519441127777,
|
| 617 |
+
"learning_rate": 2.6360564060137445e-06,
|
| 618 |
+
"loss": 0.4658,
|
| 619 |
+
"step": 348
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.9101486748545572,
|
| 623 |
+
"grad_norm": 0.17227011919021606,
|
| 624 |
+
"learning_rate": 2.6197638483965012e-06,
|
| 625 |
+
"loss": 0.4657,
|
| 626 |
+
"step": 352
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.9204912734324499,
|
| 630 |
+
"grad_norm": 0.18372756242752075,
|
| 631 |
+
"learning_rate": 2.6035798169885755e-06,
|
| 632 |
+
"loss": 0.4752,
|
| 633 |
+
"step": 356
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9308338720103426,
|
| 637 |
+
"grad_norm": 0.17142316699028015,
|
| 638 |
+
"learning_rate": 2.5875039491292835e-06,
|
| 639 |
+
"loss": 0.4648,
|
| 640 |
+
"step": 360
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.9411764705882353,
|
| 644 |
+
"grad_norm": 0.20659951865673065,
|
| 645 |
+
"learning_rate": 2.5715358821579443e-06,
|
| 646 |
+
"loss": 0.4564,
|
| 647 |
+
"step": 364
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9515190691661279,
|
| 651 |
+
"grad_norm": 0.17238274216651917,
|
| 652 |
+
"learning_rate": 2.5556752534138737e-06,
|
| 653 |
+
"loss": 0.4509,
|
| 654 |
+
"step": 368
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9618616677440207,
|
| 658 |
+
"grad_norm": 0.1769212931394577,
|
| 659 |
+
"learning_rate": 2.5399217002363903e-06,
|
| 660 |
+
"loss": 0.4631,
|
| 661 |
+
"step": 372
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9722042663219134,
|
| 665 |
+
"grad_norm": 0.1703854501247406,
|
| 666 |
+
"learning_rate": 2.5242748599648104e-06,
|
| 667 |
+
"loss": 0.4665,
|
| 668 |
+
"step": 376
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.982546864899806,
|
| 672 |
+
"grad_norm": 0.17398501932621002,
|
| 673 |
+
"learning_rate": 2.5087343699384522e-06,
|
| 674 |
+
"loss": 0.4728,
|
| 675 |
+
"step": 380
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9928894634776988,
|
| 679 |
+
"grad_norm": 0.20379476249217987,
|
| 680 |
+
"learning_rate": 2.4932998674966306e-06,
|
| 681 |
+
"loss": 0.4647,
|
| 682 |
+
"step": 384
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0025856496444732,
|
| 686 |
+
"grad_norm": 0.172428697347641,
|
| 687 |
+
"learning_rate": 2.4779709899786656e-06,
|
| 688 |
+
"loss": 0.4485,
|
| 689 |
+
"step": 388
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.0129282482223658,
|
| 693 |
+
"grad_norm": 0.18400946259498596,
|
| 694 |
+
"learning_rate": 2.4627473747238725e-06,
|
| 695 |
+
"loss": 0.4546,
|
| 696 |
+
"step": 392
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.0232708468002585,
|
| 700 |
+
"grad_norm": 0.177312433719635,
|
| 701 |
+
"learning_rate": 2.44762865907157e-06,
|
| 702 |
+
"loss": 0.4642,
|
| 703 |
+
"step": 396
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0336134453781514,
|
| 707 |
+
"grad_norm": 0.19368407130241394,
|
| 708 |
+
"learning_rate": 2.4326144803610743e-06,
|
| 709 |
+
"loss": 0.4703,
|
| 710 |
+
"step": 400
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.043956043956044,
|
| 714 |
+
"grad_norm": 0.18584667146205902,
|
| 715 |
+
"learning_rate": 2.4177044759317023e-06,
|
| 716 |
+
"loss": 0.4672,
|
| 717 |
+
"step": 404
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.0542986425339367,
|
| 721 |
+
"grad_norm": 0.1793242245912552,
|
| 722 |
+
"learning_rate": 2.402898283122773e-06,
|
| 723 |
+
"loss": 0.4519,
|
| 724 |
+
"step": 408
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.0646412411118293,
|
| 728 |
+
"grad_norm": 0.17912016808986664,
|
| 729 |
+
"learning_rate": 2.3881955392736017e-06,
|
| 730 |
+
"loss": 0.4636,
|
| 731 |
+
"step": 412
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.074983839689722,
|
| 735 |
+
"grad_norm": 0.17298536002635956,
|
| 736 |
+
"learning_rate": 2.373595881723507e-06,
|
| 737 |
+
"loss": 0.4512,
|
| 738 |
+
"step": 416
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.0853264382676147,
|
| 742 |
+
"grad_norm": 0.1726359874010086,
|
| 743 |
+
"learning_rate": 2.3590989478118058e-06,
|
| 744 |
+
"loss": 0.4699,
|
| 745 |
+
"step": 420
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.0956690368455075,
|
| 749 |
+
"grad_norm": 0.17390099167823792,
|
| 750 |
+
"learning_rate": 2.3447043748778143e-06,
|
| 751 |
+
"loss": 0.4587,
|
| 752 |
+
"step": 424
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.1060116354234002,
|
| 756 |
+
"grad_norm": 0.25595802068710327,
|
| 757 |
+
"learning_rate": 2.3304118002608516e-06,
|
| 758 |
+
"loss": 0.4615,
|
| 759 |
+
"step": 428
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.1163542340012929,
|
| 763 |
+
"grad_norm": 0.17193318903446198,
|
| 764 |
+
"learning_rate": 2.3162208613002327e-06,
|
| 765 |
+
"loss": 0.4624,
|
| 766 |
+
"step": 432
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.1266968325791855,
|
| 770 |
+
"grad_norm": 0.19484907388687134,
|
| 771 |
+
"learning_rate": 2.302131195335277e-06,
|
| 772 |
+
"loss": 0.4623,
|
| 773 |
+
"step": 436
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1370394311570782,
|
| 777 |
+
"grad_norm": 0.1798972338438034,
|
| 778 |
+
"learning_rate": 2.2881424397053003e-06,
|
| 779 |
+
"loss": 0.4649,
|
| 780 |
+
"step": 440
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.1473820297349708,
|
| 784 |
+
"grad_norm": 0.18051382899284363,
|
| 785 |
+
"learning_rate": 2.274254231749621e-06,
|
| 786 |
+
"loss": 0.4601,
|
| 787 |
+
"step": 444
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.1577246283128635,
|
| 791 |
+
"grad_norm": 0.17082150280475616,
|
| 792 |
+
"learning_rate": 2.2604662088075545e-06,
|
| 793 |
+
"loss": 0.4499,
|
| 794 |
+
"step": 448
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.1680672268907564,
|
| 798 |
+
"grad_norm": 0.1901365965604782,
|
| 799 |
+
"learning_rate": 2.2467780082184194e-06,
|
| 800 |
+
"loss": 0.4593,
|
| 801 |
+
"step": 452
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.178409825468649,
|
| 805 |
+
"grad_norm": 0.1783684343099594,
|
| 806 |
+
"learning_rate": 2.2331892673215335e-06,
|
| 807 |
+
"loss": 0.4529,
|
| 808 |
+
"step": 456
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.1887524240465417,
|
| 812 |
+
"grad_norm": 0.19588534533977509,
|
| 813 |
+
"learning_rate": 2.219699623456213e-06,
|
| 814 |
+
"loss": 0.4602,
|
| 815 |
+
"step": 460
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.1990950226244343,
|
| 819 |
+
"grad_norm": 0.20320181548595428,
|
| 820 |
+
"learning_rate": 2.206308713961775e-06,
|
| 821 |
+
"loss": 0.4541,
|
| 822 |
+
"step": 464
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.209437621202327,
|
| 826 |
+
"grad_norm": 0.18522217869758606,
|
| 827 |
+
"learning_rate": 2.1930161761775375e-06,
|
| 828 |
+
"loss": 0.4607,
|
| 829 |
+
"step": 468
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.2197802197802199,
|
| 833 |
+
"grad_norm": 0.1711958944797516,
|
| 834 |
+
"learning_rate": 2.179821647442817e-06,
|
| 835 |
+
"loss": 0.4604,
|
| 836 |
+
"step": 472
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.2301228183581125,
|
| 840 |
+
"grad_norm": 0.1926986277103424,
|
| 841 |
+
"learning_rate": 2.166724765096931e-06,
|
| 842 |
+
"loss": 0.4687,
|
| 843 |
+
"step": 476
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.2404654169360052,
|
| 847 |
+
"grad_norm": 0.17525337636470795,
|
| 848 |
+
"learning_rate": 2.1537251664791973e-06,
|
| 849 |
+
"loss": 0.4597,
|
| 850 |
+
"step": 480
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.2508080155138979,
|
| 854 |
+
"grad_norm": 0.19414155185222626,
|
| 855 |
+
"learning_rate": 2.1408224889289327e-06,
|
| 856 |
+
"loss": 0.4511,
|
| 857 |
+
"step": 484
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.2611506140917905,
|
| 861 |
+
"grad_norm": 0.1930965930223465,
|
| 862 |
+
"learning_rate": 2.1280163697854547e-06,
|
| 863 |
+
"loss": 0.4648,
|
| 864 |
+
"step": 488
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.2714932126696832,
|
| 868 |
+
"grad_norm": 0.1782602071762085,
|
| 869 |
+
"learning_rate": 2.115306446388079e-06,
|
| 870 |
+
"loss": 0.4565,
|
| 871 |
+
"step": 492
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.2818358112475758,
|
| 875 |
+
"grad_norm": 0.1658431589603424,
|
| 876 |
+
"learning_rate": 2.1026923560761246e-06,
|
| 877 |
+
"loss": 0.4684,
|
| 878 |
+
"step": 496
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.2921784098254687,
|
| 882 |
+
"grad_norm": 0.17630533874034882,
|
| 883 |
+
"learning_rate": 2.090173736188908e-06,
|
| 884 |
+
"loss": 0.4689,
|
| 885 |
+
"step": 500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.3025210084033614,
|
| 889 |
+
"grad_norm": 0.16866503655910492,
|
| 890 |
+
"learning_rate": 2.0777502240657472e-06,
|
| 891 |
+
"loss": 0.4551,
|
| 892 |
+
"step": 504
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.312863606981254,
|
| 896 |
+
"grad_norm": 0.17106667160987854,
|
| 897 |
+
"learning_rate": 2.065421457045959e-06,
|
| 898 |
+
"loss": 0.4618,
|
| 899 |
+
"step": 508
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.3232062055591467,
|
| 903 |
+
"grad_norm": 0.17253316938877106,
|
| 904 |
+
"learning_rate": 2.0531870724688596e-06,
|
| 905 |
+
"loss": 0.4585,
|
| 906 |
+
"step": 512
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.3335488041370394,
|
| 910 |
+
"grad_norm": 0.19091737270355225,
|
| 911 |
+
"learning_rate": 2.0410467076737674e-06,
|
| 912 |
+
"loss": 0.4594,
|
| 913 |
+
"step": 516
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.3438914027149322,
|
| 917 |
+
"grad_norm": 0.17556996643543243,
|
| 918 |
+
"learning_rate": 2.0289999999999995e-06,
|
| 919 |
+
"loss": 0.449,
|
| 920 |
+
"step": 520
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.354234001292825,
|
| 924 |
+
"grad_norm": 0.17378376424312592,
|
| 925 |
+
"learning_rate": 2.017046586786874e-06,
|
| 926 |
+
"loss": 0.46,
|
| 927 |
+
"step": 524
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.3645765998707176,
|
| 931 |
+
"grad_norm": 0.17842325568199158,
|
| 932 |
+
"learning_rate": 2.005186105373706e-06,
|
| 933 |
+
"loss": 0.4457,
|
| 934 |
+
"step": 528
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.3749191984486102,
|
| 938 |
+
"grad_norm": 0.18024806678295135,
|
| 939 |
+
"learning_rate": 1.993418193099814e-06,
|
| 940 |
+
"loss": 0.4562,
|
| 941 |
+
"step": 532
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.3852617970265029,
|
| 945 |
+
"grad_norm": 0.1783292591571808,
|
| 946 |
+
"learning_rate": 1.9817424873045148e-06,
|
| 947 |
+
"loss": 0.4555,
|
| 948 |
+
"step": 536
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.3956043956043955,
|
| 952 |
+
"grad_norm": 0.19366991519927979,
|
| 953 |
+
"learning_rate": 1.970158625327126e-06,
|
| 954 |
+
"loss": 0.4619,
|
| 955 |
+
"step": 540
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.4059469941822882,
|
| 959 |
+
"grad_norm": 0.1875096708536148,
|
| 960 |
+
"learning_rate": 1.9586662445069657e-06,
|
| 961 |
+
"loss": 0.463,
|
| 962 |
+
"step": 544
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.416289592760181,
|
| 966 |
+
"grad_norm": 0.19434590637683868,
|
| 967 |
+
"learning_rate": 1.94726498218335e-06,
|
| 968 |
+
"loss": 0.4568,
|
| 969 |
+
"step": 548
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.4266321913380737,
|
| 973 |
+
"grad_norm": 0.18033798038959503,
|
| 974 |
+
"learning_rate": 1.9359544756955956e-06,
|
| 975 |
+
"loss": 0.4518,
|
| 976 |
+
"step": 552
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.4369747899159664,
|
| 980 |
+
"grad_norm": 0.17548328638076782,
|
| 981 |
+
"learning_rate": 1.9247343623830206e-06,
|
| 982 |
+
"loss": 0.4563,
|
| 983 |
+
"step": 556
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.447317388493859,
|
| 987 |
+
"grad_norm": 0.18100734055042267,
|
| 988 |
+
"learning_rate": 1.913604279584942e-06,
|
| 989 |
+
"loss": 0.453,
|
| 990 |
+
"step": 560
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.4576599870717517,
|
| 994 |
+
"grad_norm": 0.17302066087722778,
|
| 995 |
+
"learning_rate": 1.9025638646406777e-06,
|
| 996 |
+
"loss": 0.4497,
|
| 997 |
+
"step": 564
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.4680025856496446,
|
| 1001 |
+
"grad_norm": 0.17910614609718323,
|
| 1002 |
+
"learning_rate": 1.8916127548895444e-06,
|
| 1003 |
+
"loss": 0.4588,
|
| 1004 |
+
"step": 568
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.4783451842275372,
|
| 1008 |
+
"grad_norm": 0.1921713948249817,
|
| 1009 |
+
"learning_rate": 1.8807505876708593e-06,
|
| 1010 |
+
"loss": 0.4631,
|
| 1011 |
+
"step": 572
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.48868778280543,
|
| 1015 |
+
"grad_norm": 0.18404294550418854,
|
| 1016 |
+
"learning_rate": 1.8699770003239392e-06,
|
| 1017 |
+
"loss": 0.4686,
|
| 1018 |
+
"step": 576
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.4990303813833226,
|
| 1022 |
+
"grad_norm": 0.1868065893650055,
|
| 1023 |
+
"learning_rate": 1.859291630188102e-06,
|
| 1024 |
+
"loss": 0.4594,
|
| 1025 |
+
"step": 580
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.5093729799612152,
|
| 1029 |
+
"grad_norm": 0.42297038435935974,
|
| 1030 |
+
"learning_rate": 1.8486941146026646e-06,
|
| 1031 |
+
"loss": 0.4635,
|
| 1032 |
+
"step": 584
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.5197155785391079,
|
| 1036 |
+
"grad_norm": 0.17838597297668457,
|
| 1037 |
+
"learning_rate": 1.8381840909069446e-06,
|
| 1038 |
+
"loss": 0.4479,
|
| 1039 |
+
"step": 588
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.5300581771170005,
|
| 1043 |
+
"grad_norm": 0.16778771579265594,
|
| 1044 |
+
"learning_rate": 1.8277611964402589e-06,
|
| 1045 |
+
"loss": 0.4583,
|
| 1046 |
+
"step": 592
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.5404007756948932,
|
| 1050 |
+
"grad_norm": 0.16617390513420105,
|
| 1051 |
+
"learning_rate": 1.817425068541925e-06,
|
| 1052 |
+
"loss": 0.4544,
|
| 1053 |
+
"step": 596
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.550743374272786,
|
| 1057 |
+
"grad_norm": 0.1774096041917801,
|
| 1058 |
+
"learning_rate": 1.8071753445512594e-06,
|
| 1059 |
+
"loss": 0.4451,
|
| 1060 |
+
"step": 600
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.5610859728506787,
|
| 1064 |
+
"grad_norm": 0.19082525372505188,
|
| 1065 |
+
"learning_rate": 1.7970116618075802e-06,
|
| 1066 |
+
"loss": 0.4666,
|
| 1067 |
+
"step": 604
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.5714285714285714,
|
| 1071 |
+
"grad_norm": 0.26731783151626587,
|
| 1072 |
+
"learning_rate": 1.7869336576502043e-06,
|
| 1073 |
+
"loss": 0.4504,
|
| 1074 |
+
"step": 608
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.5817711700064643,
|
| 1078 |
+
"grad_norm": 0.17997735738754272,
|
| 1079 |
+
"learning_rate": 1.7769409694184493e-06,
|
| 1080 |
+
"loss": 0.4505,
|
| 1081 |
+
"step": 612
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.592113768584357,
|
| 1085 |
+
"grad_norm": 0.1862158477306366,
|
| 1086 |
+
"learning_rate": 1.7670332344516319e-06,
|
| 1087 |
+
"loss": 0.4554,
|
| 1088 |
+
"step": 616
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.6024563671622496,
|
| 1092 |
+
"grad_norm": 0.18264687061309814,
|
| 1093 |
+
"learning_rate": 1.757210090089069e-06,
|
| 1094 |
+
"loss": 0.4568,
|
| 1095 |
+
"step": 620
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.6127989657401423,
|
| 1099 |
+
"grad_norm": 0.18124184012413025,
|
| 1100 |
+
"learning_rate": 1.7474711736700786e-06,
|
| 1101 |
+
"loss": 0.4562,
|
| 1102 |
+
"step": 624
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.623141564318035,
|
| 1106 |
+
"grad_norm": 0.18057860434055328,
|
| 1107 |
+
"learning_rate": 1.737816122533978e-06,
|
| 1108 |
+
"loss": 0.4584,
|
| 1109 |
+
"step": 628
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.6334841628959276,
|
| 1113 |
+
"grad_norm": 0.1704379767179489,
|
| 1114 |
+
"learning_rate": 1.7282445740200844e-06,
|
| 1115 |
+
"loss": 0.4565,
|
| 1116 |
+
"step": 632
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.6438267614738202,
|
| 1120 |
+
"grad_norm": 0.17907528579235077,
|
| 1121 |
+
"learning_rate": 1.7187561654677143e-06,
|
| 1122 |
+
"loss": 0.4551,
|
| 1123 |
+
"step": 636
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.654169360051713,
|
| 1127 |
+
"grad_norm": 0.1727352887392044,
|
| 1128 |
+
"learning_rate": 1.7093505342161853e-06,
|
| 1129 |
+
"loss": 0.4626,
|
| 1130 |
+
"step": 640
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.6645119586296055,
|
| 1134 |
+
"grad_norm": 0.192378431558609,
|
| 1135 |
+
"learning_rate": 1.7000273176048153e-06,
|
| 1136 |
+
"loss": 0.4609,
|
| 1137 |
+
"step": 644
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.6748545572074984,
|
| 1141 |
+
"grad_norm": 0.21348994970321655,
|
| 1142 |
+
"learning_rate": 1.6907861529729202e-06,
|
| 1143 |
+
"loss": 0.4581,
|
| 1144 |
+
"step": 648
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.685197155785391,
|
| 1148 |
+
"grad_norm": 0.17903228104114532,
|
| 1149 |
+
"learning_rate": 1.6816266776598186e-06,
|
| 1150 |
+
"loss": 0.4628,
|
| 1151 |
+
"step": 652
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.6955397543632837,
|
| 1155 |
+
"grad_norm": 0.17800310254096985,
|
| 1156 |
+
"learning_rate": 1.672548529004827e-06,
|
| 1157 |
+
"loss": 0.4625,
|
| 1158 |
+
"step": 656
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.7058823529411766,
|
| 1162 |
+
"grad_norm": 0.17950348556041718,
|
| 1163 |
+
"learning_rate": 1.663551344347263e-06,
|
| 1164 |
+
"loss": 0.4595,
|
| 1165 |
+
"step": 660
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.7162249515190693,
|
| 1169 |
+
"grad_norm": 0.17900501191616058,
|
| 1170 |
+
"learning_rate": 1.654634761026443e-06,
|
| 1171 |
+
"loss": 0.4574,
|
| 1172 |
+
"step": 664
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.726567550096962,
|
| 1176 |
+
"grad_norm": 0.17247159779071808,
|
| 1177 |
+
"learning_rate": 1.645798416381685e-06,
|
| 1178 |
+
"loss": 0.4517,
|
| 1179 |
+
"step": 668
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.7369101486748546,
|
| 1183 |
+
"grad_norm": 0.18945126235485077,
|
| 1184 |
+
"learning_rate": 1.6370419477523063e-06,
|
| 1185 |
+
"loss": 0.4609,
|
| 1186 |
+
"step": 672
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.7472527472527473,
|
| 1190 |
+
"grad_norm": 0.1901276856660843,
|
| 1191 |
+
"learning_rate": 1.628364992477624e-06,
|
| 1192 |
+
"loss": 0.4538,
|
| 1193 |
+
"step": 676
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.75759534583064,
|
| 1197 |
+
"grad_norm": 0.17829464375972748,
|
| 1198 |
+
"learning_rate": 1.6197671878969554e-06,
|
| 1199 |
+
"loss": 0.4481,
|
| 1200 |
+
"step": 680
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.7679379444085326,
|
| 1204 |
+
"grad_norm": 0.1853664517402649,
|
| 1205 |
+
"learning_rate": 1.6112481713496172e-06,
|
| 1206 |
+
"loss": 0.4597,
|
| 1207 |
+
"step": 684
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.7782805429864252,
|
| 1211 |
+
"grad_norm": 0.17670245468616486,
|
| 1212 |
+
"learning_rate": 1.6028075801749268e-06,
|
| 1213 |
+
"loss": 0.4559,
|
| 1214 |
+
"step": 688
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.788623141564318,
|
| 1218 |
+
"grad_norm": 0.16995681822299957,
|
| 1219 |
+
"learning_rate": 1.594445051712202e-06,
|
| 1220 |
+
"loss": 0.4516,
|
| 1221 |
+
"step": 692
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.7989657401422108,
|
| 1225 |
+
"grad_norm": 0.18131399154663086,
|
| 1226 |
+
"learning_rate": 1.58616022330076e-06,
|
| 1227 |
+
"loss": 0.4574,
|
| 1228 |
+
"step": 696
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.8093083387201034,
|
| 1232 |
+
"grad_norm": 0.16902993619441986,
|
| 1233 |
+
"learning_rate": 1.5779527322799175e-06,
|
| 1234 |
+
"loss": 0.4506,
|
| 1235 |
+
"step": 700
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.819650937297996,
|
| 1239 |
+
"grad_norm": 0.18973788619041443,
|
| 1240 |
+
"learning_rate": 1.5698222159889919e-06,
|
| 1241 |
+
"loss": 0.4542,
|
| 1242 |
+
"step": 704
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.829993535875889,
|
| 1246 |
+
"grad_norm": 0.17884907126426697,
|
| 1247 |
+
"learning_rate": 1.5617683117673004e-06,
|
| 1248 |
+
"loss": 0.4627,
|
| 1249 |
+
"step": 708
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.8403361344537816,
|
| 1253 |
+
"grad_norm": 0.1736602783203125,
|
| 1254 |
+
"learning_rate": 1.55379065695416e-06,
|
| 1255 |
+
"loss": 0.447,
|
| 1256 |
+
"step": 712
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.8506787330316743,
|
| 1260 |
+
"grad_norm": 0.1826103925704956,
|
| 1261 |
+
"learning_rate": 1.5458888888888889e-06,
|
| 1262 |
+
"loss": 0.4634,
|
| 1263 |
+
"step": 716
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.861021331609567,
|
| 1267 |
+
"grad_norm": 0.17924711108207703,
|
| 1268 |
+
"learning_rate": 1.5380626449108035e-06,
|
| 1269 |
+
"loss": 0.4436,
|
| 1270 |
+
"step": 720
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.8713639301874596,
|
| 1274 |
+
"grad_norm": 0.17868177592754364,
|
| 1275 |
+
"learning_rate": 1.5303115623592214e-06,
|
| 1276 |
+
"loss": 0.4394,
|
| 1277 |
+
"step": 724
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.8817065287653523,
|
| 1281 |
+
"grad_norm": 0.18871541321277618,
|
| 1282 |
+
"learning_rate": 1.522635278573459e-06,
|
| 1283 |
+
"loss": 0.4698,
|
| 1284 |
+
"step": 728
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.892049127343245,
|
| 1288 |
+
"grad_norm": 0.17588797211647034,
|
| 1289 |
+
"learning_rate": 1.5150334308928344e-06,
|
| 1290 |
+
"loss": 0.4591,
|
| 1291 |
+
"step": 732
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.9023917259211376,
|
| 1295 |
+
"grad_norm": 0.18185260891914368,
|
| 1296 |
+
"learning_rate": 1.507505656656665e-06,
|
| 1297 |
+
"loss": 0.465,
|
| 1298 |
+
"step": 736
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.9127343244990302,
|
| 1302 |
+
"grad_norm": 0.18905200064182281,
|
| 1303 |
+
"learning_rate": 1.5000515932042678e-06,
|
| 1304 |
+
"loss": 0.4609,
|
| 1305 |
+
"step": 740
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.9230769230769231,
|
| 1309 |
+
"grad_norm": 0.19702599942684174,
|
| 1310 |
+
"learning_rate": 1.4926708778749595e-06,
|
| 1311 |
+
"loss": 0.4444,
|
| 1312 |
+
"step": 744
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.9334195216548158,
|
| 1316 |
+
"grad_norm": 0.18513160943984985,
|
| 1317 |
+
"learning_rate": 1.4853631480080578e-06,
|
| 1318 |
+
"loss": 0.4565,
|
| 1319 |
+
"step": 748
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.9437621202327084,
|
| 1323 |
+
"grad_norm": 0.17975644767284393,
|
| 1324 |
+
"learning_rate": 1.4781280409428802e-06,
|
| 1325 |
+
"loss": 0.4474,
|
| 1326 |
+
"step": 752
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.9541047188106013,
|
| 1330 |
+
"grad_norm": 0.1855587661266327,
|
| 1331 |
+
"learning_rate": 1.4709651940187429e-06,
|
| 1332 |
+
"loss": 0.4517,
|
| 1333 |
+
"step": 756
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.964447317388494,
|
| 1337 |
+
"grad_norm": 0.18554966151714325,
|
| 1338 |
+
"learning_rate": 1.4638742445749645e-06,
|
| 1339 |
+
"loss": 0.4654,
|
| 1340 |
+
"step": 760
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.9747899159663866,
|
| 1344 |
+
"grad_norm": 0.18967655301094055,
|
| 1345 |
+
"learning_rate": 1.4568548299508615e-06,
|
| 1346 |
+
"loss": 0.463,
|
| 1347 |
+
"step": 764
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.9851325145442793,
|
| 1351 |
+
"grad_norm": 0.17238129675388336,
|
| 1352 |
+
"learning_rate": 1.4499065874857511e-06,
|
| 1353 |
+
"loss": 0.4525,
|
| 1354 |
+
"step": 768
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.995475113122172,
|
| 1358 |
+
"grad_norm": 0.17824146151542664,
|
| 1359 |
+
"learning_rate": 1.4430291545189505e-06,
|
| 1360 |
+
"loss": 0.4443,
|
| 1361 |
+
"step": 772
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.0051712992889463,
|
| 1365 |
+
"grad_norm": 0.1638309806585312,
|
| 1366 |
+
"learning_rate": 1.4362221683897769e-06,
|
| 1367 |
+
"loss": 0.4533,
|
| 1368 |
+
"step": 776
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.015513897866839,
|
| 1372 |
+
"grad_norm": 0.19044017791748047,
|
| 1373 |
+
"learning_rate": 1.4294852664375482e-06,
|
| 1374 |
+
"loss": 0.4434,
|
| 1375 |
+
"step": 780
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.0258564964447316,
|
| 1379 |
+
"grad_norm": 0.18576934933662415,
|
| 1380 |
+
"learning_rate": 1.422818086001581e-06,
|
| 1381 |
+
"loss": 0.4486,
|
| 1382 |
+
"step": 784
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.0361990950226243,
|
| 1386 |
+
"grad_norm": 0.17555150389671326,
|
| 1387 |
+
"learning_rate": 1.4162202644211928e-06,
|
| 1388 |
+
"loss": 0.4619,
|
| 1389 |
+
"step": 788
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.046541693600517,
|
| 1393 |
+
"grad_norm": 0.18890970945358276,
|
| 1394 |
+
"learning_rate": 1.4096914390357005e-06,
|
| 1395 |
+
"loss": 0.449,
|
| 1396 |
+
"step": 792
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.0568842921784096,
|
| 1400 |
+
"grad_norm": 0.17668835818767548,
|
| 1401 |
+
"learning_rate": 1.4032312471844212e-06,
|
| 1402 |
+
"loss": 0.4613,
|
| 1403 |
+
"step": 796
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.0672268907563027,
|
| 1407 |
+
"grad_norm": 0.17829003930091858,
|
| 1408 |
+
"learning_rate": 1.3968393262066731e-06,
|
| 1409 |
+
"loss": 0.4578,
|
| 1410 |
+
"step": 800
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.0775694893341954,
|
| 1414 |
+
"grad_norm": 0.1794648915529251,
|
| 1415 |
+
"learning_rate": 1.3905153134417726e-06,
|
| 1416 |
+
"loss": 0.4615,
|
| 1417 |
+
"step": 804
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.087912087912088,
|
| 1421 |
+
"grad_norm": 0.1816921979188919,
|
| 1422 |
+
"learning_rate": 1.3842588462290373e-06,
|
| 1423 |
+
"loss": 0.4431,
|
| 1424 |
+
"step": 808
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.0982546864899807,
|
| 1428 |
+
"grad_norm": 0.16857373714447021,
|
| 1429 |
+
"learning_rate": 1.378069561907784e-06,
|
| 1430 |
+
"loss": 0.4508,
|
| 1431 |
+
"step": 812
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.1085972850678734,
|
| 1435 |
+
"grad_norm": 0.18902304768562317,
|
| 1436 |
+
"learning_rate": 1.3719470978173305e-06,
|
| 1437 |
+
"loss": 0.4578,
|
| 1438 |
+
"step": 816
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.118939883645766,
|
| 1442 |
+
"grad_norm": 0.17235969007015228,
|
| 1443 |
+
"learning_rate": 1.3658910912969934e-06,
|
| 1444 |
+
"loss": 0.4504,
|
| 1445 |
+
"step": 820
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.1292824822236587,
|
| 1449 |
+
"grad_norm": 0.1716686636209488,
|
| 1450 |
+
"learning_rate": 1.3599011796860908e-06,
|
| 1451 |
+
"loss": 0.452,
|
| 1452 |
+
"step": 824
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.1396250808015513,
|
| 1456 |
+
"grad_norm": 0.17327377200126648,
|
| 1457 |
+
"learning_rate": 1.3539770003239391e-06,
|
| 1458 |
+
"loss": 0.446,
|
| 1459 |
+
"step": 828
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.149967679379444,
|
| 1463 |
+
"grad_norm": 0.1813182234764099,
|
| 1464 |
+
"learning_rate": 1.3481181905498559e-06,
|
| 1465 |
+
"loss": 0.4481,
|
| 1466 |
+
"step": 832
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.1603102779573367,
|
| 1470 |
+
"grad_norm": 0.17645367980003357,
|
| 1471 |
+
"learning_rate": 1.3423243877031582e-06,
|
| 1472 |
+
"loss": 0.4566,
|
| 1473 |
+
"step": 836
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.1706528765352293,
|
| 1477 |
+
"grad_norm": 0.17306523025035858,
|
| 1478 |
+
"learning_rate": 1.336595229123164e-06,
|
| 1479 |
+
"loss": 0.4514,
|
| 1480 |
+
"step": 840
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.180995475113122,
|
| 1484 |
+
"grad_norm": 0.17180515825748444,
|
| 1485 |
+
"learning_rate": 1.3309303521491894e-06,
|
| 1486 |
+
"loss": 0.4501,
|
| 1487 |
+
"step": 844
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.191338073691015,
|
| 1491 |
+
"grad_norm": 0.17196668684482574,
|
| 1492 |
+
"learning_rate": 1.3253293941205526e-06,
|
| 1493 |
+
"loss": 0.4539,
|
| 1494 |
+
"step": 848
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.2016806722689077,
|
| 1498 |
+
"grad_norm": 0.16701729595661163,
|
| 1499 |
+
"learning_rate": 1.3197919923765701e-06,
|
| 1500 |
+
"loss": 0.4557,
|
| 1501 |
+
"step": 852
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.2120232708468004,
|
| 1505 |
+
"grad_norm": 0.18192018568515778,
|
| 1506 |
+
"learning_rate": 1.3143177842565595e-06,
|
| 1507 |
+
"loss": 0.4508,
|
| 1508 |
+
"step": 856
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.222365869424693,
|
| 1512 |
+
"grad_norm": 0.17954544723033905,
|
| 1513 |
+
"learning_rate": 1.3089064070998384e-06,
|
| 1514 |
+
"loss": 0.4428,
|
| 1515 |
+
"step": 860
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.2327084680025857,
|
| 1519 |
+
"grad_norm": 0.185075044631958,
|
| 1520 |
+
"learning_rate": 1.3035574982457233e-06,
|
| 1521 |
+
"loss": 0.4536,
|
| 1522 |
+
"step": 864
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.2430510665804784,
|
| 1526 |
+
"grad_norm": 0.19131481647491455,
|
| 1527 |
+
"learning_rate": 1.298270695033532e-06,
|
| 1528 |
+
"loss": 0.4552,
|
| 1529 |
+
"step": 868
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.253393665158371,
|
| 1533 |
+
"grad_norm": 0.18936187028884888,
|
| 1534 |
+
"learning_rate": 1.2930456348025814e-06,
|
| 1535 |
+
"loss": 0.4478,
|
| 1536 |
+
"step": 872
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.2637362637362637,
|
| 1540 |
+
"grad_norm": 0.2016269713640213,
|
| 1541 |
+
"learning_rate": 1.2878819548921887e-06,
|
| 1542 |
+
"loss": 0.4534,
|
| 1543 |
+
"step": 876
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.2740788623141563,
|
| 1547 |
+
"grad_norm": 0.21272307634353638,
|
| 1548 |
+
"learning_rate": 1.2827792926416714e-06,
|
| 1549 |
+
"loss": 0.4434,
|
| 1550 |
+
"step": 880
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.284421460892049,
|
| 1554 |
+
"grad_norm": 0.18152523040771484,
|
| 1555 |
+
"learning_rate": 1.2777372853903463e-06,
|
| 1556 |
+
"loss": 0.4502,
|
| 1557 |
+
"step": 884
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.2947640594699417,
|
| 1561 |
+
"grad_norm": 0.17132383584976196,
|
| 1562 |
+
"learning_rate": 1.2727555704775317e-06,
|
| 1563 |
+
"loss": 0.4402,
|
| 1564 |
+
"step": 888
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.3051066580478343,
|
| 1568 |
+
"grad_norm": 0.17692337930202484,
|
| 1569 |
+
"learning_rate": 1.2678337852425434e-06,
|
| 1570 |
+
"loss": 0.4509,
|
| 1571 |
+
"step": 892
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.315449256625727,
|
| 1575 |
+
"grad_norm": 0.18354307115077972,
|
| 1576 |
+
"learning_rate": 1.2629715670246996e-06,
|
| 1577 |
+
"loss": 0.4508,
|
| 1578 |
+
"step": 896
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.32579185520362,
|
| 1582 |
+
"grad_norm": 0.17618027329444885,
|
| 1583 |
+
"learning_rate": 1.258168553163317e-06,
|
| 1584 |
+
"loss": 0.4469,
|
| 1585 |
+
"step": 900
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.3361344537815127,
|
| 1589 |
+
"grad_norm": 0.1840873807668686,
|
| 1590 |
+
"learning_rate": 1.2534243809977136e-06,
|
| 1591 |
+
"loss": 0.4485,
|
| 1592 |
+
"step": 904
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.3464770523594054,
|
| 1596 |
+
"grad_norm": 0.1692686676979065,
|
| 1597 |
+
"learning_rate": 1.2487386878672057e-06,
|
| 1598 |
+
"loss": 0.4532,
|
| 1599 |
+
"step": 908
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.356819650937298,
|
| 1603 |
+
"grad_norm": 0.17941194772720337,
|
| 1604 |
+
"learning_rate": 1.244111111111111e-06,
|
| 1605 |
+
"loss": 0.4601,
|
| 1606 |
+
"step": 912
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.3671622495151907,
|
| 1610 |
+
"grad_norm": 0.17824317514896393,
|
| 1611 |
+
"learning_rate": 1.2395412880687467e-06,
|
| 1612 |
+
"loss": 0.4653,
|
| 1613 |
+
"step": 916
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.3775048480930834,
|
| 1617 |
+
"grad_norm": 0.17118173837661743,
|
| 1618 |
+
"learning_rate": 1.2350288560794302e-06,
|
| 1619 |
+
"loss": 0.4535,
|
| 1620 |
+
"step": 920
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.387847446670976,
|
| 1624 |
+
"grad_norm": 0.19625437259674072,
|
| 1625 |
+
"learning_rate": 1.2305734524824784e-06,
|
| 1626 |
+
"loss": 0.456,
|
| 1627 |
+
"step": 924
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.3981900452488687,
|
| 1631 |
+
"grad_norm": 0.17811912298202515,
|
| 1632 |
+
"learning_rate": 1.2261747146172087e-06,
|
| 1633 |
+
"loss": 0.4428,
|
| 1634 |
+
"step": 928
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.4085326438267614,
|
| 1638 |
+
"grad_norm": 0.17827966809272766,
|
| 1639 |
+
"learning_rate": 1.2218322798229384e-06,
|
| 1640 |
+
"loss": 0.461,
|
| 1641 |
+
"step": 932
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.418875242404654,
|
| 1645 |
+
"grad_norm": 0.19108909368515015,
|
| 1646 |
+
"learning_rate": 1.2175457854389847e-06,
|
| 1647 |
+
"loss": 0.4569,
|
| 1648 |
+
"step": 936
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.4292178409825467,
|
| 1652 |
+
"grad_norm": 0.16872255504131317,
|
| 1653 |
+
"learning_rate": 1.2133148688046646e-06,
|
| 1654 |
+
"loss": 0.4529,
|
| 1655 |
+
"step": 940
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.4395604395604398,
|
| 1659 |
+
"grad_norm": 0.17768999934196472,
|
| 1660 |
+
"learning_rate": 1.2091391672592957e-06,
|
| 1661 |
+
"loss": 0.4512,
|
| 1662 |
+
"step": 944
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.4499030381383324,
|
| 1666 |
+
"grad_norm": 0.17542874813079834,
|
| 1667 |
+
"learning_rate": 1.205018318142195e-06,
|
| 1668 |
+
"loss": 0.4488,
|
| 1669 |
+
"step": 948
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.460245636716225,
|
| 1673 |
+
"grad_norm": 0.18069233000278473,
|
| 1674 |
+
"learning_rate": 1.20095195879268e-06,
|
| 1675 |
+
"loss": 0.4512,
|
| 1676 |
+
"step": 952
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.4705882352941178,
|
| 1680 |
+
"grad_norm": 0.17639058828353882,
|
| 1681 |
+
"learning_rate": 1.1969397265500675e-06,
|
| 1682 |
+
"loss": 0.4489,
|
| 1683 |
+
"step": 956
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.4809308338720104,
|
| 1687 |
+
"grad_norm": 0.17847612500190735,
|
| 1688 |
+
"learning_rate": 1.192981258753675e-06,
|
| 1689 |
+
"loss": 0.45,
|
| 1690 |
+
"step": 960
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.491273432449903,
|
| 1694 |
+
"grad_norm": 0.1748712956905365,
|
| 1695 |
+
"learning_rate": 1.1890761927428197e-06,
|
| 1696 |
+
"loss": 0.438,
|
| 1697 |
+
"step": 964
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.5016160310277957,
|
| 1701 |
+
"grad_norm": 0.1816711723804474,
|
| 1702 |
+
"learning_rate": 1.185224165856819e-06,
|
| 1703 |
+
"loss": 0.4513,
|
| 1704 |
+
"step": 968
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.5119586296056884,
|
| 1708 |
+
"grad_norm": 0.17945519089698792,
|
| 1709 |
+
"learning_rate": 1.1814248154349897e-06,
|
| 1710 |
+
"loss": 0.4505,
|
| 1711 |
+
"step": 972
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.522301228183581,
|
| 1715 |
+
"grad_norm": 0.1755056381225586,
|
| 1716 |
+
"learning_rate": 1.1776777788166495e-06,
|
| 1717 |
+
"loss": 0.4587,
|
| 1718 |
+
"step": 976
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.5326438267614737,
|
| 1722 |
+
"grad_norm": 0.2565567195415497,
|
| 1723 |
+
"learning_rate": 1.1739826933411155e-06,
|
| 1724 |
+
"loss": 0.4578,
|
| 1725 |
+
"step": 980
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.5429864253393664,
|
| 1729 |
+
"grad_norm": 0.1997365802526474,
|
| 1730 |
+
"learning_rate": 1.1703391963477048e-06,
|
| 1731 |
+
"loss": 0.4487,
|
| 1732 |
+
"step": 984
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.553329023917259,
|
| 1736 |
+
"grad_norm": 0.18262676894664764,
|
| 1737 |
+
"learning_rate": 1.1667469251757346e-06,
|
| 1738 |
+
"loss": 0.4453,
|
| 1739 |
+
"step": 988
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.5636716224951517,
|
| 1743 |
+
"grad_norm": 0.17584246397018433,
|
| 1744 |
+
"learning_rate": 1.1632055171645223e-06,
|
| 1745 |
+
"loss": 0.4427,
|
| 1746 |
+
"step": 992
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.5740142210730443,
|
| 1750 |
+
"grad_norm": 0.1811375468969345,
|
| 1751 |
+
"learning_rate": 1.1597146096533852e-06,
|
| 1752 |
+
"loss": 0.4574,
|
| 1753 |
+
"step": 996
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.5843568196509374,
|
| 1757 |
+
"grad_norm": 0.1873408406972885,
|
| 1758 |
+
"learning_rate": 1.1562738399816404e-06,
|
| 1759 |
+
"loss": 0.4562,
|
| 1760 |
+
"step": 1000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.59469941822883,
|
| 1764 |
+
"grad_norm": 0.18968404829502106,
|
| 1765 |
+
"learning_rate": 1.152882845488605e-06,
|
| 1766 |
+
"loss": 0.4468,
|
| 1767 |
+
"step": 1004
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.6050420168067228,
|
| 1771 |
+
"grad_norm": 0.1783261001110077,
|
| 1772 |
+
"learning_rate": 1.1495412635135963e-06,
|
| 1773 |
+
"loss": 0.4539,
|
| 1774 |
+
"step": 1008
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.6153846153846154,
|
| 1778 |
+
"grad_norm": 0.1903458833694458,
|
| 1779 |
+
"learning_rate": 1.146248731395932e-06,
|
| 1780 |
+
"loss": 0.4578,
|
| 1781 |
+
"step": 1012
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.625727213962508,
|
| 1785 |
+
"grad_norm": 0.17537672817707062,
|
| 1786 |
+
"learning_rate": 1.1430048864749287e-06,
|
| 1787 |
+
"loss": 0.4566,
|
| 1788 |
+
"step": 1016
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.6360698125404007,
|
| 1792 |
+
"grad_norm": 0.1887020617723465,
|
| 1793 |
+
"learning_rate": 1.139809366089904e-06,
|
| 1794 |
+
"loss": 0.4464,
|
| 1795 |
+
"step": 1020
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.6464124111182934,
|
| 1799 |
+
"grad_norm": 0.18123377859592438,
|
| 1800 |
+
"learning_rate": 1.136661807580175e-06,
|
| 1801 |
+
"loss": 0.4593,
|
| 1802 |
+
"step": 1024
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.656755009696186,
|
| 1806 |
+
"grad_norm": 0.1783813238143921,
|
| 1807 |
+
"learning_rate": 1.133561848285059e-06,
|
| 1808 |
+
"loss": 0.4499,
|
| 1809 |
+
"step": 1028
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.6670976082740787,
|
| 1813 |
+
"grad_norm": 0.17778170108795166,
|
| 1814 |
+
"learning_rate": 1.130509125543873e-06,
|
| 1815 |
+
"loss": 0.4486,
|
| 1816 |
+
"step": 1032
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.677440206851972,
|
| 1820 |
+
"grad_norm": 0.18150880932807922,
|
| 1821 |
+
"learning_rate": 1.1275032766959346e-06,
|
| 1822 |
+
"loss": 0.4515,
|
| 1823 |
+
"step": 1036
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.6877828054298645,
|
| 1827 |
+
"grad_norm": 0.17898158729076385,
|
| 1828 |
+
"learning_rate": 1.1245439390805607e-06,
|
| 1829 |
+
"loss": 0.4434,
|
| 1830 |
+
"step": 1040
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.698125404007757,
|
| 1834 |
+
"grad_norm": 0.18532375991344452,
|
| 1835 |
+
"learning_rate": 1.1216307500370688e-06,
|
| 1836 |
+
"loss": 0.4486,
|
| 1837 |
+
"step": 1044
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.70846800258565,
|
| 1841 |
+
"grad_norm": 0.1722891479730606,
|
| 1842 |
+
"learning_rate": 1.118763346904776e-06,
|
| 1843 |
+
"loss": 0.4548,
|
| 1844 |
+
"step": 1048
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.7188106011635425,
|
| 1848 |
+
"grad_norm": 0.1772516816854477,
|
| 1849 |
+
"learning_rate": 1.1159413670229997e-06,
|
| 1850 |
+
"loss": 0.4555,
|
| 1851 |
+
"step": 1052
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.729153199741435,
|
| 1855 |
+
"grad_norm": 0.17695064842700958,
|
| 1856 |
+
"learning_rate": 1.1131644477310569e-06,
|
| 1857 |
+
"loss": 0.4607,
|
| 1858 |
+
"step": 1056
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.7394957983193278,
|
| 1862 |
+
"grad_norm": 0.17609025537967682,
|
| 1863 |
+
"learning_rate": 1.110432226368265e-06,
|
| 1864 |
+
"loss": 0.4446,
|
| 1865 |
+
"step": 1060
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.7498383968972204,
|
| 1869 |
+
"grad_norm": 0.17976413667201996,
|
| 1870 |
+
"learning_rate": 1.107744340273941e-06,
|
| 1871 |
+
"loss": 0.4467,
|
| 1872 |
+
"step": 1064
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.760180995475113,
|
| 1876 |
+
"grad_norm": 0.18428538739681244,
|
| 1877 |
+
"learning_rate": 1.1051004267874023e-06,
|
| 1878 |
+
"loss": 0.4555,
|
| 1879 |
+
"step": 1068
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.7705235940530057,
|
| 1883 |
+
"grad_norm": 0.17254601418972015,
|
| 1884 |
+
"learning_rate": 1.1025001232479663e-06,
|
| 1885 |
+
"loss": 0.4432,
|
| 1886 |
+
"step": 1072
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.7808661926308984,
|
| 1890 |
+
"grad_norm": 0.17763815820217133,
|
| 1891 |
+
"learning_rate": 1.09994306699495e-06,
|
| 1892 |
+
"loss": 0.4533,
|
| 1893 |
+
"step": 1076
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.791208791208791,
|
| 1897 |
+
"grad_norm": 0.18219688534736633,
|
| 1898 |
+
"learning_rate": 1.097428895367671e-06,
|
| 1899 |
+
"loss": 0.455,
|
| 1900 |
+
"step": 1080
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.8015513897866837,
|
| 1904 |
+
"grad_norm": 0.17637620866298676,
|
| 1905 |
+
"learning_rate": 1.0949572457054458e-06,
|
| 1906 |
+
"loss": 0.4406,
|
| 1907 |
+
"step": 1084
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.8118939883645764,
|
| 1911 |
+
"grad_norm": 0.1767360419034958,
|
| 1912 |
+
"learning_rate": 1.0925277553475922e-06,
|
| 1913 |
+
"loss": 0.4504,
|
| 1914 |
+
"step": 1088
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.822236586942469,
|
| 1918 |
+
"grad_norm": 0.1777689903974533,
|
| 1919 |
+
"learning_rate": 1.0901400616334274e-06,
|
| 1920 |
+
"loss": 0.4443,
|
| 1921 |
+
"step": 1092
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.832579185520362,
|
| 1925 |
+
"grad_norm": 0.17348885536193848,
|
| 1926 |
+
"learning_rate": 1.0877938019022687e-06,
|
| 1927 |
+
"loss": 0.455,
|
| 1928 |
+
"step": 1096
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.842921784098255,
|
| 1932 |
+
"grad_norm": 0.16941364109516144,
|
| 1933 |
+
"learning_rate": 1.0854886134934328e-06,
|
| 1934 |
+
"loss": 0.4463,
|
| 1935 |
+
"step": 1100
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.8532643826761475,
|
| 1939 |
+
"grad_norm": 0.1874593198299408,
|
| 1940 |
+
"learning_rate": 1.0832241337462376e-06,
|
| 1941 |
+
"loss": 0.4498,
|
| 1942 |
+
"step": 1104
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.86360698125404,
|
| 1946 |
+
"grad_norm": 0.17837406694889069,
|
| 1947 |
+
"learning_rate": 1.081e-06,
|
| 1948 |
+
"loss": 0.454,
|
| 1949 |
+
"step": 1108
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.8739495798319328,
|
| 1953 |
+
"grad_norm": 0.19155140221118927,
|
| 1954 |
+
"learning_rate": 1.0788158495940373e-06,
|
| 1955 |
+
"loss": 0.4595,
|
| 1956 |
+
"step": 1112
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.8842921784098254,
|
| 1960 |
+
"grad_norm": 0.17509421706199646,
|
| 1961 |
+
"learning_rate": 1.0766713198676667e-06,
|
| 1962 |
+
"loss": 0.4567,
|
| 1963 |
+
"step": 1116
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.894634776987718,
|
| 1967 |
+
"grad_norm": 0.17931582033634186,
|
| 1968 |
+
"learning_rate": 1.0745660481602052e-06,
|
| 1969 |
+
"loss": 0.4536,
|
| 1970 |
+
"step": 1120
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.9049773755656108,
|
| 1974 |
+
"grad_norm": 0.1758774369955063,
|
| 1975 |
+
"learning_rate": 1.0724996718109706e-06,
|
| 1976 |
+
"loss": 0.4532,
|
| 1977 |
+
"step": 1124
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.9153199741435034,
|
| 1981 |
+
"grad_norm": 0.176919624209404,
|
| 1982 |
+
"learning_rate": 1.0704718281592797e-06,
|
| 1983 |
+
"loss": 0.4529,
|
| 1984 |
+
"step": 1128
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.9256625727213965,
|
| 1988 |
+
"grad_norm": 0.1802259087562561,
|
| 1989 |
+
"learning_rate": 1.06848215454445e-06,
|
| 1990 |
+
"loss": 0.4455,
|
| 1991 |
+
"step": 1132
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.936005171299289,
|
| 1995 |
+
"grad_norm": 0.16593530774116516,
|
| 1996 |
+
"learning_rate": 1.0665302883057984e-06,
|
| 1997 |
+
"loss": 0.4459,
|
| 1998 |
+
"step": 1136
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.946347769877182,
|
| 2002 |
+
"grad_norm": 0.17818193137645721,
|
| 2003 |
+
"learning_rate": 1.0646158667826425e-06,
|
| 2004 |
+
"loss": 0.4566,
|
| 2005 |
+
"step": 1140
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.9566903684550745,
|
| 2009 |
+
"grad_norm": 0.17576196789741516,
|
| 2010 |
+
"learning_rate": 1.0627385273142993e-06,
|
| 2011 |
+
"loss": 0.439,
|
| 2012 |
+
"step": 1144
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.967032967032967,
|
| 2016 |
+
"grad_norm": 0.1871625781059265,
|
| 2017 |
+
"learning_rate": 1.0608979072400862e-06,
|
| 2018 |
+
"loss": 0.4507,
|
| 2019 |
+
"step": 1148
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.97737556561086,
|
| 2023 |
+
"grad_norm": 0.18743683397769928,
|
| 2024 |
+
"learning_rate": 1.05909364389932e-06,
|
| 2025 |
+
"loss": 0.449,
|
| 2026 |
+
"step": 1152
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.9877181641887525,
|
| 2030 |
+
"grad_norm": 0.1833522915840149,
|
| 2031 |
+
"learning_rate": 1.0573253746313186e-06,
|
| 2032 |
+
"loss": 0.4577,
|
| 2033 |
+
"step": 1156
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.998060762766645,
|
| 2037 |
+
"grad_norm": 0.17550155520439148,
|
| 2038 |
+
"learning_rate": 1.0555927367753988e-06,
|
| 2039 |
+
"loss": 0.4523,
|
| 2040 |
+
"step": 1160
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 3.0077569489334195,
|
| 2044 |
+
"grad_norm": 0.17497506737709045,
|
| 2045 |
+
"learning_rate": 1.0538953676708778e-06,
|
| 2046 |
+
"loss": 0.443,
|
| 2047 |
+
"step": 1164
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 3.018099547511312,
|
| 2051 |
+
"grad_norm": 0.18479323387145996,
|
| 2052 |
+
"learning_rate": 1.052232904657073e-06,
|
| 2053 |
+
"loss": 0.4476,
|
| 2054 |
+
"step": 1168
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 3.028442146089205,
|
| 2058 |
+
"grad_norm": 0.17023231089115143,
|
| 2059 |
+
"learning_rate": 1.0506049850733017e-06,
|
| 2060 |
+
"loss": 0.4446,
|
| 2061 |
+
"step": 1172
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 3.0387847446670975,
|
| 2065 |
+
"grad_norm": 0.194169819355011,
|
| 2066 |
+
"learning_rate": 1.0490112462588812e-06,
|
| 2067 |
+
"loss": 0.4436,
|
| 2068 |
+
"step": 1176
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 3.04912734324499,
|
| 2072 |
+
"grad_norm": 0.16968706250190735,
|
| 2073 |
+
"learning_rate": 1.0474513255531283e-06,
|
| 2074 |
+
"loss": 0.4445,
|
| 2075 |
+
"step": 1180
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 3.059469941822883,
|
| 2079 |
+
"grad_norm": 0.18906928598880768,
|
| 2080 |
+
"learning_rate": 1.0459248602953606e-06,
|
| 2081 |
+
"loss": 0.464,
|
| 2082 |
+
"step": 1184
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 3.069812540400776,
|
| 2086 |
+
"grad_norm": 0.17577582597732544,
|
| 2087 |
+
"learning_rate": 1.0444314878248952e-06,
|
| 2088 |
+
"loss": 0.4505,
|
| 2089 |
+
"step": 1188
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 3.0801551389786685,
|
| 2093 |
+
"grad_norm": 0.16838566958904266,
|
| 2094 |
+
"learning_rate": 1.0429708454810495e-06,
|
| 2095 |
+
"loss": 0.4438,
|
| 2096 |
+
"step": 1192
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 3.090497737556561,
|
| 2100 |
+
"grad_norm": 0.18139545619487762,
|
| 2101 |
+
"learning_rate": 1.0415425706031406e-06,
|
| 2102 |
+
"loss": 0.4515,
|
| 2103 |
+
"step": 1196
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 3.100840336134454,
|
| 2107 |
+
"grad_norm": 0.17523127794265747,
|
| 2108 |
+
"learning_rate": 1.0401463005304855e-06,
|
| 2109 |
+
"loss": 0.4475,
|
| 2110 |
+
"step": 1200
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 3.1111829347123465,
|
| 2114 |
+
"grad_norm": 0.18693816661834717,
|
| 2115 |
+
"learning_rate": 1.0387816726024021e-06,
|
| 2116 |
+
"loss": 0.4447,
|
| 2117 |
+
"step": 1204
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 3.121525533290239,
|
| 2121 |
+
"grad_norm": 0.16429254412651062,
|
| 2122 |
+
"learning_rate": 1.0374483241582069e-06,
|
| 2123 |
+
"loss": 0.4509,
|
| 2124 |
+
"step": 1208
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 3.131868131868132,
|
| 2128 |
+
"grad_norm": 0.18026259541511536,
|
| 2129 |
+
"learning_rate": 1.0361458925372175e-06,
|
| 2130 |
+
"loss": 0.4548,
|
| 2131 |
+
"step": 1212
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 3.1422107304460245,
|
| 2135 |
+
"grad_norm": 0.19680114090442657,
|
| 2136 |
+
"learning_rate": 1.034874015078751e-06,
|
| 2137 |
+
"loss": 0.4477,
|
| 2138 |
+
"step": 1216
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 3.152553329023917,
|
| 2142 |
+
"grad_norm": 0.17316031455993652,
|
| 2143 |
+
"learning_rate": 1.033632329122125e-06,
|
| 2144 |
+
"loss": 0.4493,
|
| 2145 |
+
"step": 1220
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 3.16289592760181,
|
| 2149 |
+
"grad_norm": 0.16267041862010956,
|
| 2150 |
+
"learning_rate": 1.0324204720066564e-06,
|
| 2151 |
+
"loss": 0.4409,
|
| 2152 |
+
"step": 1224
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 3.1732385261797025,
|
| 2156 |
+
"grad_norm": 0.2089986652135849,
|
| 2157 |
+
"learning_rate": 1.0312380810716623e-06,
|
| 2158 |
+
"loss": 0.4504,
|
| 2159 |
+
"step": 1228
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 3.183581124757595,
|
| 2163 |
+
"grad_norm": 0.16956327855587006,
|
| 2164 |
+
"learning_rate": 1.0300847936564602e-06,
|
| 2165 |
+
"loss": 0.4471,
|
| 2166 |
+
"step": 1232
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 3.1939237233354882,
|
| 2170 |
+
"grad_norm": 0.17798687517642975,
|
| 2171 |
+
"learning_rate": 1.0289602471003672e-06,
|
| 2172 |
+
"loss": 0.4507,
|
| 2173 |
+
"step": 1236
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 3.204266321913381,
|
| 2177 |
+
"grad_norm": 0.17512640357017517,
|
| 2178 |
+
"learning_rate": 1.0278640787427008e-06,
|
| 2179 |
+
"loss": 0.446,
|
| 2180 |
+
"step": 1240
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.2146089204912736,
|
| 2184 |
+
"grad_norm": 0.17578400671482086,
|
| 2185 |
+
"learning_rate": 1.0267959259227778e-06,
|
| 2186 |
+
"loss": 0.4484,
|
| 2187 |
+
"step": 1244
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 3.224951519069166,
|
| 2191 |
+
"grad_norm": 0.17712455987930298,
|
| 2192 |
+
"learning_rate": 1.0257554259799157e-06,
|
| 2193 |
+
"loss": 0.4481,
|
| 2194 |
+
"step": 1248
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 3.235294117647059,
|
| 2198 |
+
"grad_norm": 0.1793729066848755,
|
| 2199 |
+
"learning_rate": 1.0247422162534318e-06,
|
| 2200 |
+
"loss": 0.441,
|
| 2201 |
+
"step": 1252
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 3.2456367162249515,
|
| 2205 |
+
"grad_norm": 0.16967114806175232,
|
| 2206 |
+
"learning_rate": 1.0237559340826432e-06,
|
| 2207 |
+
"loss": 0.4525,
|
| 2208 |
+
"step": 1256
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 3.255979314802844,
|
| 2212 |
+
"grad_norm": 0.1762080043554306,
|
| 2213 |
+
"learning_rate": 1.022796216806867e-06,
|
| 2214 |
+
"loss": 0.4344,
|
| 2215 |
+
"step": 1260
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 3.266321913380737,
|
| 2219 |
+
"grad_norm": 0.1827186495065689,
|
| 2220 |
+
"learning_rate": 1.021862701765421e-06,
|
| 2221 |
+
"loss": 0.4519,
|
| 2222 |
+
"step": 1264
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 3.2766645119586295,
|
| 2226 |
+
"grad_norm": 0.17989112436771393,
|
| 2227 |
+
"learning_rate": 1.0209550262976217e-06,
|
| 2228 |
+
"loss": 0.4513,
|
| 2229 |
+
"step": 1268
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 3.287007110536522,
|
| 2233 |
+
"grad_norm": 0.18342699110507965,
|
| 2234 |
+
"learning_rate": 1.0200728277427867e-06,
|
| 2235 |
+
"loss": 0.4485,
|
| 2236 |
+
"step": 1272
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 3.297349709114415,
|
| 2240 |
+
"grad_norm": 0.19681668281555176,
|
| 2241 |
+
"learning_rate": 1.0192157434402333e-06,
|
| 2242 |
+
"loss": 0.4429,
|
| 2243 |
+
"step": 1276
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 3.3076923076923075,
|
| 2247 |
+
"grad_norm": 0.172057643532753,
|
| 2248 |
+
"learning_rate": 1.0183834107292785e-06,
|
| 2249 |
+
"loss": 0.4525,
|
| 2250 |
+
"step": 1280
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 3.3180349062702,
|
| 2254 |
+
"grad_norm": 0.16999749839305878,
|
| 2255 |
+
"learning_rate": 1.0175754669492397e-06,
|
| 2256 |
+
"loss": 0.4532,
|
| 2257 |
+
"step": 1284
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 3.3283775048480932,
|
| 2261 |
+
"grad_norm": 0.18436214327812195,
|
| 2262 |
+
"learning_rate": 1.0167915494394342e-06,
|
| 2263 |
+
"loss": 0.4566,
|
| 2264 |
+
"step": 1288
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 3.338720103425986,
|
| 2268 |
+
"grad_norm": 0.16745057702064514,
|
| 2269 |
+
"learning_rate": 1.016031295539179e-06,
|
| 2270 |
+
"loss": 0.4605,
|
| 2271 |
+
"step": 1292
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 3.3490627020038786,
|
| 2275 |
+
"grad_norm": 0.18557773530483246,
|
| 2276 |
+
"learning_rate": 1.0152943425877918e-06,
|
| 2277 |
+
"loss": 0.4457,
|
| 2278 |
+
"step": 1296
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 3.3594053005817712,
|
| 2282 |
+
"grad_norm": 0.181436225771904,
|
| 2283 |
+
"learning_rate": 1.0145803279245893e-06,
|
| 2284 |
+
"loss": 0.439,
|
| 2285 |
+
"step": 1300
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 3.369747899159664,
|
| 2289 |
+
"grad_norm": 0.17534784972667694,
|
| 2290 |
+
"learning_rate": 1.0138888888888887e-06,
|
| 2291 |
+
"loss": 0.4437,
|
| 2292 |
+
"step": 1304
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 3.3800904977375565,
|
| 2296 |
+
"grad_norm": 0.17567597329616547,
|
| 2297 |
+
"learning_rate": 1.0132196628200078e-06,
|
| 2298 |
+
"loss": 0.4405,
|
| 2299 |
+
"step": 1308
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 3.390433096315449,
|
| 2303 |
+
"grad_norm": 0.17782679200172424,
|
| 2304 |
+
"learning_rate": 1.0125722870572635e-06,
|
| 2305 |
+
"loss": 0.4468,
|
| 2306 |
+
"step": 1312
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 3.400775694893342,
|
| 2310 |
+
"grad_norm": 0.17457668483257294,
|
| 2311 |
+
"learning_rate": 1.011946398939973e-06,
|
| 2312 |
+
"loss": 0.454,
|
| 2313 |
+
"step": 1316
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 3.4111182934712345,
|
| 2317 |
+
"grad_norm": 0.16642296314239502,
|
| 2318 |
+
"learning_rate": 1.0113416358074535e-06,
|
| 2319 |
+
"loss": 0.4465,
|
| 2320 |
+
"step": 1320
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 3.421460892049127,
|
| 2324 |
+
"grad_norm": 0.17336755990982056,
|
| 2325 |
+
"learning_rate": 1.0107576349990224e-06,
|
| 2326 |
+
"loss": 0.456,
|
| 2327 |
+
"step": 1324
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 3.4318034906270203,
|
| 2331 |
+
"grad_norm": 0.18164758384227753,
|
| 2332 |
+
"learning_rate": 1.010194033853997e-06,
|
| 2333 |
+
"loss": 0.4469,
|
| 2334 |
+
"step": 1328
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 3.442146089204913,
|
| 2338 |
+
"grad_norm": 0.1722988784313202,
|
| 2339 |
+
"learning_rate": 1.009650469711694e-06,
|
| 2340 |
+
"loss": 0.4471,
|
| 2341 |
+
"step": 1332
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 3.4524886877828056,
|
| 2345 |
+
"grad_norm": 0.17613555490970612,
|
| 2346 |
+
"learning_rate": 1.0091265799114313e-06,
|
| 2347 |
+
"loss": 0.4473,
|
| 2348 |
+
"step": 1336
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 3.4628312863606983,
|
| 2352 |
+
"grad_norm": 0.17907673120498657,
|
| 2353 |
+
"learning_rate": 1.008622001792526e-06,
|
| 2354 |
+
"loss": 0.4611,
|
| 2355 |
+
"step": 1340
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 3.473173884938591,
|
| 2359 |
+
"grad_norm": 0.18107053637504578,
|
| 2360 |
+
"learning_rate": 1.0081363726942948e-06,
|
| 2361 |
+
"loss": 0.4415,
|
| 2362 |
+
"step": 1344
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 3.4835164835164836,
|
| 2366 |
+
"grad_norm": 0.19422635436058044,
|
| 2367 |
+
"learning_rate": 1.0076693299560557e-06,
|
| 2368 |
+
"loss": 0.4413,
|
| 2369 |
+
"step": 1348
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 3.4938590820943762,
|
| 2373 |
+
"grad_norm": 0.1928495168685913,
|
| 2374 |
+
"learning_rate": 1.0072205109171253e-06,
|
| 2375 |
+
"loss": 0.4525,
|
| 2376 |
+
"step": 1352
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 3.504201680672269,
|
| 2380 |
+
"grad_norm": 0.17438076436519623,
|
| 2381 |
+
"learning_rate": 1.0067895529168213e-06,
|
| 2382 |
+
"loss": 0.4435,
|
| 2383 |
+
"step": 1356
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 3.5145442792501616,
|
| 2387 |
+
"grad_norm": 0.17133189737796783,
|
| 2388 |
+
"learning_rate": 1.0063760932944606e-06,
|
| 2389 |
+
"loss": 0.4574,
|
| 2390 |
+
"step": 1360
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 3.524886877828054,
|
| 2394 |
+
"grad_norm": 0.18594177067279816,
|
| 2395 |
+
"learning_rate": 1.0059797693893605e-06,
|
| 2396 |
+
"loss": 0.4434,
|
| 2397 |
+
"step": 1364
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 3.535229476405947,
|
| 2401 |
+
"grad_norm": 0.1890227347612381,
|
| 2402 |
+
"learning_rate": 1.0056002185408385e-06,
|
| 2403 |
+
"loss": 0.4556,
|
| 2404 |
+
"step": 1368
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 3.5455720749838395,
|
| 2408 |
+
"grad_norm": 0.17522525787353516,
|
| 2409 |
+
"learning_rate": 1.0052370780882114e-06,
|
| 2410 |
+
"loss": 0.4506,
|
| 2411 |
+
"step": 1372
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 3.555914673561732,
|
| 2415 |
+
"grad_norm": 0.18247763812541962,
|
| 2416 |
+
"learning_rate": 1.0048899853707968e-06,
|
| 2417 |
+
"loss": 0.4485,
|
| 2418 |
+
"step": 1376
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 3.566257272139625,
|
| 2422 |
+
"grad_norm": 0.18556474149227142,
|
| 2423 |
+
"learning_rate": 1.0045585777279118e-06,
|
| 2424 |
+
"loss": 0.4579,
|
| 2425 |
+
"step": 1380
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 3.5765998707175175,
|
| 2429 |
+
"grad_norm": 0.17300067842006683,
|
| 2430 |
+
"learning_rate": 1.0042424924988736e-06,
|
| 2431 |
+
"loss": 0.4512,
|
| 2432 |
+
"step": 1384
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 3.5869424692954106,
|
| 2436 |
+
"grad_norm": 0.18004953861236572,
|
| 2437 |
+
"learning_rate": 1.0039413670229995e-06,
|
| 2438 |
+
"loss": 0.4453,
|
| 2439 |
+
"step": 1388
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 3.5972850678733033,
|
| 2443 |
+
"grad_norm": 0.1785740703344345,
|
| 2444 |
+
"learning_rate": 1.0036548386396067e-06,
|
| 2445 |
+
"loss": 0.4449,
|
| 2446 |
+
"step": 1392
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 3.607627666451196,
|
| 2450 |
+
"grad_norm": 0.16730371117591858,
|
| 2451 |
+
"learning_rate": 1.0033825446880127e-06,
|
| 2452 |
+
"loss": 0.4485,
|
| 2453 |
+
"step": 1396
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 3.6179702650290886,
|
| 2457 |
+
"grad_norm": 0.18206489086151123,
|
| 2458 |
+
"learning_rate": 1.0031241225075341e-06,
|
| 2459 |
+
"loss": 0.4471,
|
| 2460 |
+
"step": 1400
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 3.6283128636069812,
|
| 2464 |
+
"grad_norm": 0.17622709274291992,
|
| 2465 |
+
"learning_rate": 1.0028792094374887e-06,
|
| 2466 |
+
"loss": 0.4436,
|
| 2467 |
+
"step": 1404
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 3.638655462184874,
|
| 2471 |
+
"grad_norm": 0.18737947940826416,
|
| 2472 |
+
"learning_rate": 1.0026474428171935e-06,
|
| 2473 |
+
"loss": 0.4389,
|
| 2474 |
+
"step": 1408
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 3.6489980607627666,
|
| 2478 |
+
"grad_norm": 0.17098890244960785,
|
| 2479 |
+
"learning_rate": 1.0024284599859658e-06,
|
| 2480 |
+
"loss": 0.4363,
|
| 2481 |
+
"step": 1412
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 3.659340659340659,
|
| 2485 |
+
"grad_norm": 0.17516440153121948,
|
| 2486 |
+
"learning_rate": 1.0022218982831228e-06,
|
| 2487 |
+
"loss": 0.4503,
|
| 2488 |
+
"step": 1416
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 3.669683257918552,
|
| 2492 |
+
"grad_norm": 0.18128778040409088,
|
| 2493 |
+
"learning_rate": 1.0020273950479815e-06,
|
| 2494 |
+
"loss": 0.441,
|
| 2495 |
+
"step": 1420
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 3.680025856496445,
|
| 2499 |
+
"grad_norm": 0.18445086479187012,
|
| 2500 |
+
"learning_rate": 1.0018445876198597e-06,
|
| 2501 |
+
"loss": 0.4389,
|
| 2502 |
+
"step": 1424
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 3.6903684550743376,
|
| 2506 |
+
"grad_norm": 0.18264997005462646,
|
| 2507 |
+
"learning_rate": 1.0016731133380744e-06,
|
| 2508 |
+
"loss": 0.4394,
|
| 2509 |
+
"step": 1428
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 3.7007110536522303,
|
| 2513 |
+
"grad_norm": 0.17699220776557922,
|
| 2514 |
+
"learning_rate": 1.0015126095419424e-06,
|
| 2515 |
+
"loss": 0.4494,
|
| 2516 |
+
"step": 1432
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 3.711053652230123,
|
| 2520 |
+
"grad_norm": 0.17461882531642914,
|
| 2521 |
+
"learning_rate": 1.0013627135707816e-06,
|
| 2522 |
+
"loss": 0.4521,
|
| 2523 |
+
"step": 1436
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 3.7213962508080156,
|
| 2527 |
+
"grad_norm": 0.17526471614837646,
|
| 2528 |
+
"learning_rate": 1.0012230627639088e-06,
|
| 2529 |
+
"loss": 0.4389,
|
| 2530 |
+
"step": 1440
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 3.7317388493859083,
|
| 2534 |
+
"grad_norm": 0.17140990495681763,
|
| 2535 |
+
"learning_rate": 1.0010932944606414e-06,
|
| 2536 |
+
"loss": 0.4489,
|
| 2537 |
+
"step": 1444
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 3.742081447963801,
|
| 2541 |
+
"grad_norm": 0.19351443648338318,
|
| 2542 |
+
"learning_rate": 1.0009730460002965e-06,
|
| 2543 |
+
"loss": 0.4436,
|
| 2544 |
+
"step": 1448
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 3.7524240465416936,
|
| 2548 |
+
"grad_norm": 0.1850733458995819,
|
| 2549 |
+
"learning_rate": 1.0008619547221914e-06,
|
| 2550 |
+
"loss": 0.4514,
|
| 2551 |
+
"step": 1452
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 3.7627666451195863,
|
| 2555 |
+
"grad_norm": 0.18625636398792267,
|
| 2556 |
+
"learning_rate": 1.0007596579656435e-06,
|
| 2557 |
+
"loss": 0.4484,
|
| 2558 |
+
"step": 1456
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 3.773109243697479,
|
| 2562 |
+
"grad_norm": 0.18134167790412903,
|
| 2563 |
+
"learning_rate": 1.00066579306997e-06,
|
| 2564 |
+
"loss": 0.4549,
|
| 2565 |
+
"step": 1460
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 3.7834518422753716,
|
| 2569 |
+
"grad_norm": 0.19236284494400024,
|
| 2570 |
+
"learning_rate": 1.0005799973744876e-06,
|
| 2571 |
+
"loss": 0.4433,
|
| 2572 |
+
"step": 1464
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 3.7937944408532642,
|
| 2576 |
+
"grad_norm": 0.1741548478603363,
|
| 2577 |
+
"learning_rate": 1.0005019082185143e-06,
|
| 2578 |
+
"loss": 0.4476,
|
| 2579 |
+
"step": 1468
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 3.804137039431157,
|
| 2583 |
+
"grad_norm": 0.17673614621162415,
|
| 2584 |
+
"learning_rate": 1.000431162941367e-06,
|
| 2585 |
+
"loss": 0.4462,
|
| 2586 |
+
"step": 1472
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 3.8144796380090495,
|
| 2590 |
+
"grad_norm": 0.1771819293498993,
|
| 2591 |
+
"learning_rate": 1.0003673988823628e-06,
|
| 2592 |
+
"loss": 0.4561,
|
| 2593 |
+
"step": 1476
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 3.824822236586942,
|
| 2597 |
+
"grad_norm": 0.17858363687992096,
|
| 2598 |
+
"learning_rate": 1.0003102533808192e-06,
|
| 2599 |
+
"loss": 0.4479,
|
| 2600 |
+
"step": 1480
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 3.8351648351648353,
|
| 2604 |
+
"grad_norm": 0.16550451517105103,
|
| 2605 |
+
"learning_rate": 1.0002593637760531e-06,
|
| 2606 |
+
"loss": 0.4488,
|
| 2607 |
+
"step": 1484
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 3.845507433742728,
|
| 2611 |
+
"grad_norm": 0.17858079075813293,
|
| 2612 |
+
"learning_rate": 1.0002143674073823e-06,
|
| 2613 |
+
"loss": 0.45,
|
| 2614 |
+
"step": 1488
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 3.8558500323206206,
|
| 2618 |
+
"grad_norm": 0.187116801738739,
|
| 2619 |
+
"learning_rate": 1.0001749016141235e-06,
|
| 2620 |
+
"loss": 0.4474,
|
| 2621 |
+
"step": 1492
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 3.8661926308985133,
|
| 2625 |
+
"grad_norm": 0.18668505549430847,
|
| 2626 |
+
"learning_rate": 1.0001406037355939e-06,
|
| 2627 |
+
"loss": 0.4432,
|
| 2628 |
+
"step": 1496
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 3.876535229476406,
|
| 2632 |
+
"grad_norm": 0.17585262656211853,
|
| 2633 |
+
"learning_rate": 1.0001111111111112e-06,
|
| 2634 |
+
"loss": 0.4439,
|
| 2635 |
+
"step": 1500
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 3.8868778280542986,
|
| 2639 |
+
"grad_norm": 0.17823632061481476,
|
| 2640 |
+
"learning_rate": 1.0000860610799922e-06,
|
| 2641 |
+
"loss": 0.4576,
|
| 2642 |
+
"step": 1504
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 3.8972204266321913,
|
| 2646 |
+
"grad_norm": 0.1767703890800476,
|
| 2647 |
+
"learning_rate": 1.0000650909815542e-06,
|
| 2648 |
+
"loss": 0.4542,
|
| 2649 |
+
"step": 1508
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 3.907563025210084,
|
| 2653 |
+
"grad_norm": 0.16956399381160736,
|
| 2654 |
+
"learning_rate": 1.0000478381551149e-06,
|
| 2655 |
+
"loss": 0.4533,
|
| 2656 |
+
"step": 1512
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 3.9179056237879766,
|
| 2660 |
+
"grad_norm": 0.17914198338985443,
|
| 2661 |
+
"learning_rate": 1.000033939939991e-06,
|
| 2662 |
+
"loss": 0.4456,
|
| 2663 |
+
"step": 1516
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 3.9282482223658697,
|
| 2667 |
+
"grad_norm": 0.1634252965450287,
|
| 2668 |
+
"learning_rate": 1.0000230336754998e-06,
|
| 2669 |
+
"loss": 0.4466,
|
| 2670 |
+
"step": 1520
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 3.9385908209437623,
|
| 2674 |
+
"grad_norm": 0.17150919139385223,
|
| 2675 |
+
"learning_rate": 1.0000147567009588e-06,
|
| 2676 |
+
"loss": 0.4466,
|
| 2677 |
+
"step": 1524
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 3.948933419521655,
|
| 2681 |
+
"grad_norm": 0.18172475695610046,
|
| 2682 |
+
"learning_rate": 1.0000087463556851e-06,
|
| 2683 |
+
"loss": 0.4431,
|
| 2684 |
+
"step": 1528
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 3.9592760180995477,
|
| 2688 |
+
"grad_norm": 0.1767711490392685,
|
| 2689 |
+
"learning_rate": 1.000004639978996e-06,
|
| 2690 |
+
"loss": 0.4512,
|
| 2691 |
+
"step": 1532
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 3.9696186166774403,
|
| 2695 |
+
"grad_norm": 0.1694304198026657,
|
| 2696 |
+
"learning_rate": 1.0000020749102083e-06,
|
| 2697 |
+
"loss": 0.4483,
|
| 2698 |
+
"step": 1536
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 3.979961215255333,
|
| 2702 |
+
"grad_norm": 0.18949837982654572,
|
| 2703 |
+
"learning_rate": 1.0000006884886399e-06,
|
| 2704 |
+
"loss": 0.4464,
|
| 2705 |
+
"step": 1540
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 3.9903038138332256,
|
| 2709 |
+
"grad_norm": 0.17919163405895233,
|
| 2710 |
+
"learning_rate": 1.0000001180536076e-06,
|
| 2711 |
+
"loss": 0.4572,
|
| 2712 |
+
"step": 1544
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 4.0,
|
| 2716 |
+
"grad_norm": 0.3023968040943146,
|
| 2717 |
+
"learning_rate": 1.0000000009444288e-06,
|
| 2718 |
+
"loss": 0.4456,
|
| 2719 |
+
"step": 1548
|
| 2720 |
+
}
|
| 2721 |
+
],
|
| 2722 |
+
"logging_steps": 4,
|
| 2723 |
+
"max_steps": 1548,
|
| 2724 |
+
"num_input_tokens_seen": 0,
|
| 2725 |
+
"num_train_epochs": 4,
|
| 2726 |
+
"save_steps": 15000,
|
| 2727 |
+
"stateful_callbacks": {
|
| 2728 |
+
"TrainerControl": {
|
| 2729 |
+
"args": {
|
| 2730 |
+
"should_epoch_stop": false,
|
| 2731 |
+
"should_evaluate": false,
|
| 2732 |
+
"should_log": false,
|
| 2733 |
+
"should_save": true,
|
| 2734 |
+
"should_training_stop": true
|
| 2735 |
+
},
|
| 2736 |
+
"attributes": {}
|
| 2737 |
+
}
|
| 2738 |
+
},
|
| 2739 |
+
"total_flos": 6.286572983201956e+17,
|
| 2740 |
+
"train_batch_size": 216,
|
| 2741 |
+
"trial_name": null,
|
| 2742 |
+
"trial_params": null
|
| 2743 |
+
}
|
training_args.bin
ADDED
|
Binary file (5.69 kB). View file
|
|
|