Upload folder using huggingface_hub
Browse files- added_tokens.json +4 -0
- config.json +91 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +19 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +13 -0
- spm_char.model +3 -0
- tokenizer_config.json +64 -0
- trainer_state.json +914 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<ctc_blank>": 80,
|
| 3 |
+
"<mask>": 79
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"apply_spec_augment": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"SpeechT5ForTextToSpeech"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"conv_bias": false,
|
| 10 |
+
"conv_dim": [
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512
|
| 18 |
+
],
|
| 19 |
+
"conv_kernel": [
|
| 20 |
+
10,
|
| 21 |
+
3,
|
| 22 |
+
3,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
2,
|
| 26 |
+
2
|
| 27 |
+
],
|
| 28 |
+
"conv_stride": [
|
| 29 |
+
5,
|
| 30 |
+
2,
|
| 31 |
+
2,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2
|
| 36 |
+
],
|
| 37 |
+
"decoder_attention_heads": 12,
|
| 38 |
+
"decoder_ffn_dim": 3072,
|
| 39 |
+
"decoder_layerdrop": 0.1,
|
| 40 |
+
"decoder_layers": 6,
|
| 41 |
+
"decoder_start_token_id": 2,
|
| 42 |
+
"encoder_attention_heads": 12,
|
| 43 |
+
"encoder_ffn_dim": 3072,
|
| 44 |
+
"encoder_layerdrop": 0.1,
|
| 45 |
+
"encoder_layers": 12,
|
| 46 |
+
"encoder_max_relative_position": 160,
|
| 47 |
+
"eos_token_id": 2,
|
| 48 |
+
"feat_extract_activation": "gelu",
|
| 49 |
+
"feat_extract_norm": "group",
|
| 50 |
+
"feat_proj_dropout": 0.0,
|
| 51 |
+
"guided_attention_loss_num_heads": 2,
|
| 52 |
+
"guided_attention_loss_scale": 10.0,
|
| 53 |
+
"guided_attention_loss_sigma": 0.4,
|
| 54 |
+
"hidden_act": "gelu",
|
| 55 |
+
"hidden_dropout": 0.1,
|
| 56 |
+
"hidden_size": 768,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"is_encoder_decoder": true,
|
| 59 |
+
"layer_norm_eps": 1e-05,
|
| 60 |
+
"mask_feature_length": 10,
|
| 61 |
+
"mask_feature_min_masks": 0,
|
| 62 |
+
"mask_feature_prob": 0.0,
|
| 63 |
+
"mask_time_length": 10,
|
| 64 |
+
"mask_time_min_masks": 2,
|
| 65 |
+
"mask_time_prob": 0.05,
|
| 66 |
+
"max_length": null,
|
| 67 |
+
"max_speech_positions": 1876,
|
| 68 |
+
"max_text_positions": 600,
|
| 69 |
+
"model_type": "speecht5",
|
| 70 |
+
"num_conv_pos_embedding_groups": 16,
|
| 71 |
+
"num_conv_pos_embeddings": 128,
|
| 72 |
+
"num_feat_extract_layers": 7,
|
| 73 |
+
"num_mel_bins": 80,
|
| 74 |
+
"pad_token_id": 1,
|
| 75 |
+
"positional_dropout": 0.1,
|
| 76 |
+
"reduction_factor": 2,
|
| 77 |
+
"scale_embedding": false,
|
| 78 |
+
"speaker_embedding_dim": 512,
|
| 79 |
+
"speech_decoder_postnet_dropout": 0.5,
|
| 80 |
+
"speech_decoder_postnet_kernel": 5,
|
| 81 |
+
"speech_decoder_postnet_layers": 5,
|
| 82 |
+
"speech_decoder_postnet_units": 256,
|
| 83 |
+
"speech_decoder_prenet_dropout": 0.5,
|
| 84 |
+
"speech_decoder_prenet_layers": 2,
|
| 85 |
+
"speech_decoder_prenet_units": 256,
|
| 86 |
+
"torch_dtype": "float32",
|
| 87 |
+
"transformers_version": "4.53.2",
|
| 88 |
+
"use_cache": false,
|
| 89 |
+
"use_guided_attention_loss": true,
|
| 90 |
+
"vocab_size": 81
|
| 91 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"max_length": 1876,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.53.2"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:310eb69143459d186c7f695497e573cf37c61f57082511bf9f63f513fdfa5aab
|
| 3 |
+
size 577789320
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41738eed34a1e48060ea60b952169c462d1ee8e66e4134d8943c21310081ca5e
|
| 3 |
+
size 1155772233
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": false,
|
| 3 |
+
"feature_extractor_type": "SpeechT5FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"fmax": 7600,
|
| 6 |
+
"fmin": 80,
|
| 7 |
+
"frame_signal_scale": 1.0,
|
| 8 |
+
"hop_length": 16,
|
| 9 |
+
"mel_floor": 1e-10,
|
| 10 |
+
"num_mel_bins": 80,
|
| 11 |
+
"padding_side": "right",
|
| 12 |
+
"padding_value": 0.0,
|
| 13 |
+
"processor_class": "SpeechT5Processor",
|
| 14 |
+
"reduction_factor": 2,
|
| 15 |
+
"return_attention_mask": true,
|
| 16 |
+
"sampling_rate": 16000,
|
| 17 |
+
"win_function": "hann_window",
|
| 18 |
+
"win_length": 64
|
| 19 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23731a1431e441fa2babf1b269e657d01b317504056ab030399bb7758c6f52fa
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a1e3232c9dd0558d3b582345b4a537ca2d63d9ae2df7d7189cbdc92c4e384f
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"mask_token": {
|
| 5 |
+
"content": "<mask>",
|
| 6 |
+
"lstrip": true,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|
spm_char.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
|
| 3 |
+
size 238473
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"79": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"80": {
|
| 44 |
+
"content": "<ctc_blank>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<s>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"eos_token": "</s>",
|
| 55 |
+
"extra_special_tokens": {},
|
| 56 |
+
"mask_token": "<mask>",
|
| 57 |
+
"model_max_length": 600,
|
| 58 |
+
"normalize": false,
|
| 59 |
+
"pad_token": "<pad>",
|
| 60 |
+
"processor_class": "SpeechT5Processor",
|
| 61 |
+
"sp_model_kwargs": {},
|
| 62 |
+
"tokenizer_class": "SpeechT5Tokenizer",
|
| 63 |
+
"unk_token": "<unk>"
|
| 64 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,914 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1350,
|
| 3 |
+
"best_metric": 0.36149922013282776,
|
| 4 |
+
"best_model_checkpoint": "trainer_output/checkpoint-400",
|
| 5 |
+
"epoch": 22.22284122562674,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2785515320334262,
|
| 14 |
+
"grad_norm": 3.268444776535034,
|
| 15 |
+
"learning_rate": 2.4e-05,
|
| 16 |
+
"loss": 0.4348,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5571030640668524,
|
| 21 |
+
"grad_norm": 4.304715633392334,
|
| 22 |
+
"learning_rate": 4.9e-05,
|
| 23 |
+
"loss": 0.4346,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.5571030640668524,
|
| 28 |
+
"eval_loss": 0.3896651268005371,
|
| 29 |
+
"eval_runtime": 13.8517,
|
| 30 |
+
"eval_samples_per_second": 23.102,
|
| 31 |
+
"eval_steps_per_second": 23.102,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.8356545961002786,
|
| 36 |
+
"grad_norm": 8.992396354675293,
|
| 37 |
+
"learning_rate": 7.4e-05,
|
| 38 |
+
"loss": 0.4365,
|
| 39 |
+
"step": 75
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.1114206128133706,
|
| 43 |
+
"grad_norm": 4.0646514892578125,
|
| 44 |
+
"learning_rate": 9.900000000000001e-05,
|
| 45 |
+
"loss": 0.4438,
|
| 46 |
+
"step": 100
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.1114206128133706,
|
| 50 |
+
"eval_loss": 0.41089218854904175,
|
| 51 |
+
"eval_runtime": 14.0072,
|
| 52 |
+
"eval_samples_per_second": 22.845,
|
| 53 |
+
"eval_steps_per_second": 22.845,
|
| 54 |
+
"step": 100
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3899721448467965,
|
| 58 |
+
"grad_norm": 3.1883151531219482,
|
| 59 |
+
"learning_rate": 9.873684210526316e-05,
|
| 60 |
+
"loss": 0.4411,
|
| 61 |
+
"step": 125
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.668523676880223,
|
| 65 |
+
"grad_norm": 10.366960525512695,
|
| 66 |
+
"learning_rate": 9.742105263157896e-05,
|
| 67 |
+
"loss": 0.455,
|
| 68 |
+
"step": 150
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.668523676880223,
|
| 72 |
+
"eval_loss": 0.39505237340927124,
|
| 73 |
+
"eval_runtime": 13.684,
|
| 74 |
+
"eval_samples_per_second": 23.385,
|
| 75 |
+
"eval_steps_per_second": 23.385,
|
| 76 |
+
"step": 150
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.947075208913649,
|
| 80 |
+
"grad_norm": 5.3184027671813965,
|
| 81 |
+
"learning_rate": 9.610526315789474e-05,
|
| 82 |
+
"loss": 0.4315,
|
| 83 |
+
"step": 175
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.222841225626741,
|
| 87 |
+
"grad_norm": 7.163997173309326,
|
| 88 |
+
"learning_rate": 9.478947368421053e-05,
|
| 89 |
+
"loss": 0.4243,
|
| 90 |
+
"step": 200
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.222841225626741,
|
| 94 |
+
"eval_loss": 0.42486143112182617,
|
| 95 |
+
"eval_runtime": 13.6879,
|
| 96 |
+
"eval_samples_per_second": 23.378,
|
| 97 |
+
"eval_steps_per_second": 23.378,
|
| 98 |
+
"step": 200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.501392757660167,
|
| 102 |
+
"grad_norm": 4.934960842132568,
|
| 103 |
+
"learning_rate": 9.347368421052632e-05,
|
| 104 |
+
"loss": 0.4417,
|
| 105 |
+
"step": 225
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.779944289693593,
|
| 109 |
+
"grad_norm": 1.8761239051818848,
|
| 110 |
+
"learning_rate": 9.21578947368421e-05,
|
| 111 |
+
"loss": 0.4322,
|
| 112 |
+
"step": 250
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.779944289693593,
|
| 116 |
+
"eval_loss": 0.381044864654541,
|
| 117 |
+
"eval_runtime": 13.7455,
|
| 118 |
+
"eval_samples_per_second": 23.28,
|
| 119 |
+
"eval_steps_per_second": 23.28,
|
| 120 |
+
"step": 250
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.0557103064066853,
|
| 124 |
+
"grad_norm": 5.752270221710205,
|
| 125 |
+
"learning_rate": 9.08421052631579e-05,
|
| 126 |
+
"loss": 0.4214,
|
| 127 |
+
"step": 275
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.3342618384401113,
|
| 131 |
+
"grad_norm": 4.633335590362549,
|
| 132 |
+
"learning_rate": 8.95263157894737e-05,
|
| 133 |
+
"loss": 0.4256,
|
| 134 |
+
"step": 300
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.3342618384401113,
|
| 138 |
+
"eval_loss": 0.3811536431312561,
|
| 139 |
+
"eval_runtime": 13.4686,
|
| 140 |
+
"eval_samples_per_second": 23.759,
|
| 141 |
+
"eval_steps_per_second": 23.759,
|
| 142 |
+
"step": 300
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.6128133704735377,
|
| 146 |
+
"grad_norm": 6.349725723266602,
|
| 147 |
+
"learning_rate": 8.821052631578948e-05,
|
| 148 |
+
"loss": 0.4207,
|
| 149 |
+
"step": 325
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.8913649025069637,
|
| 153 |
+
"grad_norm": 6.114583492279053,
|
| 154 |
+
"learning_rate": 8.689473684210526e-05,
|
| 155 |
+
"loss": 0.4232,
|
| 156 |
+
"step": 350
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.8913649025069637,
|
| 160 |
+
"eval_loss": 0.41359782218933105,
|
| 161 |
+
"eval_runtime": 13.645,
|
| 162 |
+
"eval_samples_per_second": 23.452,
|
| 163 |
+
"eval_steps_per_second": 23.452,
|
| 164 |
+
"step": 350
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.167130919220056,
|
| 168 |
+
"grad_norm": 3.0233688354492188,
|
| 169 |
+
"learning_rate": 8.557894736842106e-05,
|
| 170 |
+
"loss": 0.4173,
|
| 171 |
+
"step": 375
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.445682451253482,
|
| 175 |
+
"grad_norm": 3.7900898456573486,
|
| 176 |
+
"learning_rate": 8.426315789473684e-05,
|
| 177 |
+
"loss": 0.4188,
|
| 178 |
+
"step": 400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.445682451253482,
|
| 182 |
+
"eval_loss": 0.37991732358932495,
|
| 183 |
+
"eval_runtime": 13.601,
|
| 184 |
+
"eval_samples_per_second": 23.528,
|
| 185 |
+
"eval_steps_per_second": 23.528,
|
| 186 |
+
"step": 400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 4.724233983286908,
|
| 190 |
+
"grad_norm": 4.321193218231201,
|
| 191 |
+
"learning_rate": 8.294736842105263e-05,
|
| 192 |
+
"loss": 0.4194,
|
| 193 |
+
"step": 425
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 5.0,
|
| 197 |
+
"grad_norm": 4.552373886108398,
|
| 198 |
+
"learning_rate": 8.163157894736843e-05,
|
| 199 |
+
"loss": 0.4045,
|
| 200 |
+
"step": 450
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 5.0,
|
| 204 |
+
"eval_loss": 0.37860995531082153,
|
| 205 |
+
"eval_runtime": 13.5918,
|
| 206 |
+
"eval_samples_per_second": 23.544,
|
| 207 |
+
"eval_steps_per_second": 23.544,
|
| 208 |
+
"step": 450
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 5.278551532033426,
|
| 212 |
+
"grad_norm": 1.4818230867385864,
|
| 213 |
+
"learning_rate": 8.031578947368421e-05,
|
| 214 |
+
"loss": 0.4053,
|
| 215 |
+
"step": 475
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.557103064066853,
|
| 219 |
+
"grad_norm": 6.262104511260986,
|
| 220 |
+
"learning_rate": 7.900000000000001e-05,
|
| 221 |
+
"loss": 0.4057,
|
| 222 |
+
"step": 500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.557103064066853,
|
| 226 |
+
"eval_loss": 0.3852214217185974,
|
| 227 |
+
"eval_runtime": 13.5514,
|
| 228 |
+
"eval_samples_per_second": 23.614,
|
| 229 |
+
"eval_steps_per_second": 23.614,
|
| 230 |
+
"step": 500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.835654596100278,
|
| 234 |
+
"grad_norm": 5.743201732635498,
|
| 235 |
+
"learning_rate": 7.768421052631579e-05,
|
| 236 |
+
"loss": 0.409,
|
| 237 |
+
"step": 525
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 6.111420612813371,
|
| 241 |
+
"grad_norm": 4.577704906463623,
|
| 242 |
+
"learning_rate": 7.636842105263157e-05,
|
| 243 |
+
"loss": 0.404,
|
| 244 |
+
"step": 550
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 6.111420612813371,
|
| 248 |
+
"eval_loss": 0.3758087754249573,
|
| 249 |
+
"eval_runtime": 13.5075,
|
| 250 |
+
"eval_samples_per_second": 23.691,
|
| 251 |
+
"eval_steps_per_second": 23.691,
|
| 252 |
+
"step": 550
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 6.389972144846797,
|
| 256 |
+
"grad_norm": 2.2797679901123047,
|
| 257 |
+
"learning_rate": 7.505263157894737e-05,
|
| 258 |
+
"loss": 0.4036,
|
| 259 |
+
"step": 575
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.6685236768802225,
|
| 263 |
+
"grad_norm": 2.6362528800964355,
|
| 264 |
+
"learning_rate": 7.373684210526317e-05,
|
| 265 |
+
"loss": 0.4013,
|
| 266 |
+
"step": 600
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.6685236768802225,
|
| 270 |
+
"eval_loss": 0.3783581852912903,
|
| 271 |
+
"eval_runtime": 13.7273,
|
| 272 |
+
"eval_samples_per_second": 23.311,
|
| 273 |
+
"eval_steps_per_second": 23.311,
|
| 274 |
+
"step": 600
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 6.947075208913649,
|
| 278 |
+
"grad_norm": 2.8619472980499268,
|
| 279 |
+
"learning_rate": 7.242105263157896e-05,
|
| 280 |
+
"loss": 0.401,
|
| 281 |
+
"step": 625
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 7.222841225626741,
|
| 285 |
+
"grad_norm": 2.071786403656006,
|
| 286 |
+
"learning_rate": 7.110526315789474e-05,
|
| 287 |
+
"loss": 0.3919,
|
| 288 |
+
"step": 650
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 7.222841225626741,
|
| 292 |
+
"eval_loss": 0.3806610703468323,
|
| 293 |
+
"eval_runtime": 13.6224,
|
| 294 |
+
"eval_samples_per_second": 23.491,
|
| 295 |
+
"eval_steps_per_second": 23.491,
|
| 296 |
+
"step": 650
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.501392757660167,
|
| 300 |
+
"grad_norm": 5.365797519683838,
|
| 301 |
+
"learning_rate": 6.978947368421053e-05,
|
| 302 |
+
"loss": 0.4018,
|
| 303 |
+
"step": 675
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.779944289693593,
|
| 307 |
+
"grad_norm": 5.850217819213867,
|
| 308 |
+
"learning_rate": 6.847368421052632e-05,
|
| 309 |
+
"loss": 0.4055,
|
| 310 |
+
"step": 700
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 7.779944289693593,
|
| 314 |
+
"eval_loss": 0.3773684501647949,
|
| 315 |
+
"eval_runtime": 13.6955,
|
| 316 |
+
"eval_samples_per_second": 23.365,
|
| 317 |
+
"eval_steps_per_second": 23.365,
|
| 318 |
+
"step": 700
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 8.055710306406684,
|
| 322 |
+
"grad_norm": 2.516648530960083,
|
| 323 |
+
"learning_rate": 6.71578947368421e-05,
|
| 324 |
+
"loss": 0.3867,
|
| 325 |
+
"step": 725
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 8.334261838440112,
|
| 329 |
+
"grad_norm": 3.2627480030059814,
|
| 330 |
+
"learning_rate": 6.584210526315789e-05,
|
| 331 |
+
"loss": 0.3919,
|
| 332 |
+
"step": 750
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.334261838440112,
|
| 336 |
+
"eval_loss": 0.381404310464859,
|
| 337 |
+
"eval_runtime": 13.6865,
|
| 338 |
+
"eval_samples_per_second": 23.381,
|
| 339 |
+
"eval_steps_per_second": 23.381,
|
| 340 |
+
"step": 750
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 8.612813370473537,
|
| 344 |
+
"grad_norm": 1.986242651939392,
|
| 345 |
+
"learning_rate": 6.452631578947368e-05,
|
| 346 |
+
"loss": 0.3972,
|
| 347 |
+
"step": 775
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 8.891364902506965,
|
| 351 |
+
"grad_norm": 2.2203171253204346,
|
| 352 |
+
"learning_rate": 6.321052631578948e-05,
|
| 353 |
+
"loss": 0.3939,
|
| 354 |
+
"step": 800
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.891364902506965,
|
| 358 |
+
"eval_loss": 0.38715943694114685,
|
| 359 |
+
"eval_runtime": 13.4294,
|
| 360 |
+
"eval_samples_per_second": 23.828,
|
| 361 |
+
"eval_steps_per_second": 23.828,
|
| 362 |
+
"step": 800
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 9.167130919220055,
|
| 366 |
+
"grad_norm": 2.0610949993133545,
|
| 367 |
+
"learning_rate": 6.189473684210526e-05,
|
| 368 |
+
"loss": 0.3908,
|
| 369 |
+
"step": 825
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.445682451253482,
|
| 373 |
+
"grad_norm": 1.9484410285949707,
|
| 374 |
+
"learning_rate": 6.057894736842106e-05,
|
| 375 |
+
"loss": 0.3863,
|
| 376 |
+
"step": 850
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 9.445682451253482,
|
| 380 |
+
"eval_loss": 0.36479219794273376,
|
| 381 |
+
"eval_runtime": 13.6905,
|
| 382 |
+
"eval_samples_per_second": 23.374,
|
| 383 |
+
"eval_steps_per_second": 23.374,
|
| 384 |
+
"step": 850
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.724233983286908,
|
| 388 |
+
"grad_norm": 3.732637882232666,
|
| 389 |
+
"learning_rate": 5.926315789473684e-05,
|
| 390 |
+
"loss": 0.3912,
|
| 391 |
+
"step": 875
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 10.0,
|
| 395 |
+
"grad_norm": 2.3195526599884033,
|
| 396 |
+
"learning_rate": 5.794736842105264e-05,
|
| 397 |
+
"loss": 0.3868,
|
| 398 |
+
"step": 900
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 10.0,
|
| 402 |
+
"eval_loss": 0.36887454986572266,
|
| 403 |
+
"eval_runtime": 13.6683,
|
| 404 |
+
"eval_samples_per_second": 23.412,
|
| 405 |
+
"eval_steps_per_second": 23.412,
|
| 406 |
+
"step": 900
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 10.278551532033426,
|
| 410 |
+
"grad_norm": 1.2468181848526,
|
| 411 |
+
"learning_rate": 5.6631578947368426e-05,
|
| 412 |
+
"loss": 0.3929,
|
| 413 |
+
"step": 925
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 10.557103064066853,
|
| 417 |
+
"grad_norm": 2.238741159439087,
|
| 418 |
+
"learning_rate": 5.531578947368421e-05,
|
| 419 |
+
"loss": 0.3863,
|
| 420 |
+
"step": 950
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 10.557103064066853,
|
| 424 |
+
"eval_loss": 0.3635193407535553,
|
| 425 |
+
"eval_runtime": 13.8549,
|
| 426 |
+
"eval_samples_per_second": 23.097,
|
| 427 |
+
"eval_steps_per_second": 23.097,
|
| 428 |
+
"step": 950
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 10.835654596100278,
|
| 432 |
+
"grad_norm": 1.6164511442184448,
|
| 433 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 434 |
+
"loss": 0.3888,
|
| 435 |
+
"step": 975
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 11.11142061281337,
|
| 439 |
+
"grad_norm": 3.874614715576172,
|
| 440 |
+
"learning_rate": 5.2684210526315794e-05,
|
| 441 |
+
"loss": 0.3789,
|
| 442 |
+
"step": 1000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 11.11142061281337,
|
| 446 |
+
"eval_loss": 0.3707486689090729,
|
| 447 |
+
"eval_runtime": 13.6538,
|
| 448 |
+
"eval_samples_per_second": 23.437,
|
| 449 |
+
"eval_steps_per_second": 23.437,
|
| 450 |
+
"step": 1000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 11.389972144846796,
|
| 454 |
+
"grad_norm": 2.4590909481048584,
|
| 455 |
+
"learning_rate": 5.1368421052631576e-05,
|
| 456 |
+
"loss": 0.3864,
|
| 457 |
+
"step": 1025
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 11.668523676880223,
|
| 461 |
+
"grad_norm": 2.916522741317749,
|
| 462 |
+
"learning_rate": 5.005263157894737e-05,
|
| 463 |
+
"loss": 0.3829,
|
| 464 |
+
"step": 1050
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 11.668523676880223,
|
| 468 |
+
"eval_loss": 0.36959362030029297,
|
| 469 |
+
"eval_runtime": 13.6444,
|
| 470 |
+
"eval_samples_per_second": 23.453,
|
| 471 |
+
"eval_steps_per_second": 23.453,
|
| 472 |
+
"step": 1050
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 11.947075208913649,
|
| 476 |
+
"grad_norm": 2.2767789363861084,
|
| 477 |
+
"learning_rate": 4.873684210526316e-05,
|
| 478 |
+
"loss": 0.3811,
|
| 479 |
+
"step": 1075
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 12.222841225626741,
|
| 483 |
+
"grad_norm": 2.320681095123291,
|
| 484 |
+
"learning_rate": 4.742105263157895e-05,
|
| 485 |
+
"loss": 0.3771,
|
| 486 |
+
"step": 1100
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 12.222841225626741,
|
| 490 |
+
"eval_loss": 0.37226706743240356,
|
| 491 |
+
"eval_runtime": 13.6934,
|
| 492 |
+
"eval_samples_per_second": 23.369,
|
| 493 |
+
"eval_steps_per_second": 23.369,
|
| 494 |
+
"step": 1100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 12.501392757660167,
|
| 498 |
+
"grad_norm": 2.783123254776001,
|
| 499 |
+
"learning_rate": 4.610526315789474e-05,
|
| 500 |
+
"loss": 0.3785,
|
| 501 |
+
"step": 1125
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 12.779944289693594,
|
| 505 |
+
"grad_norm": 2.488577365875244,
|
| 506 |
+
"learning_rate": 4.478947368421053e-05,
|
| 507 |
+
"loss": 0.3811,
|
| 508 |
+
"step": 1150
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 12.779944289693594,
|
| 512 |
+
"eval_loss": 0.36161237955093384,
|
| 513 |
+
"eval_runtime": 13.7581,
|
| 514 |
+
"eval_samples_per_second": 23.259,
|
| 515 |
+
"eval_steps_per_second": 23.259,
|
| 516 |
+
"step": 1150
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 13.055710306406684,
|
| 520 |
+
"grad_norm": 2.4364013671875,
|
| 521 |
+
"learning_rate": 4.347368421052632e-05,
|
| 522 |
+
"loss": 0.3775,
|
| 523 |
+
"step": 1175
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 13.334261838440112,
|
| 527 |
+
"grad_norm": 4.950360298156738,
|
| 528 |
+
"learning_rate": 4.215789473684211e-05,
|
| 529 |
+
"loss": 0.3766,
|
| 530 |
+
"step": 1200
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 13.334261838440112,
|
| 534 |
+
"eval_loss": 0.3663933575153351,
|
| 535 |
+
"eval_runtime": 13.7363,
|
| 536 |
+
"eval_samples_per_second": 23.296,
|
| 537 |
+
"eval_steps_per_second": 23.296,
|
| 538 |
+
"step": 1200
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 13.612813370473537,
|
| 542 |
+
"grad_norm": 3.373661994934082,
|
| 543 |
+
"learning_rate": 4.08421052631579e-05,
|
| 544 |
+
"loss": 0.3736,
|
| 545 |
+
"step": 1225
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 13.891364902506965,
|
| 549 |
+
"grad_norm": 6.832035541534424,
|
| 550 |
+
"learning_rate": 3.9526315789473686e-05,
|
| 551 |
+
"loss": 0.3808,
|
| 552 |
+
"step": 1250
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 13.891364902506965,
|
| 556 |
+
"eval_loss": 0.36550408601760864,
|
| 557 |
+
"eval_runtime": 13.5552,
|
| 558 |
+
"eval_samples_per_second": 23.607,
|
| 559 |
+
"eval_steps_per_second": 23.607,
|
| 560 |
+
"step": 1250
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 14.167130919220055,
|
| 564 |
+
"grad_norm": 3.087953567504883,
|
| 565 |
+
"learning_rate": 3.8210526315789476e-05,
|
| 566 |
+
"loss": 0.3706,
|
| 567 |
+
"step": 1275
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 14.445682451253482,
|
| 571 |
+
"grad_norm": 2.505366802215576,
|
| 572 |
+
"learning_rate": 3.6894736842105265e-05,
|
| 573 |
+
"loss": 0.3748,
|
| 574 |
+
"step": 1300
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 14.445682451253482,
|
| 578 |
+
"eval_loss": 0.37319216132164,
|
| 579 |
+
"eval_runtime": 13.6213,
|
| 580 |
+
"eval_samples_per_second": 23.493,
|
| 581 |
+
"eval_steps_per_second": 23.493,
|
| 582 |
+
"step": 1300
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 14.724233983286908,
|
| 586 |
+
"grad_norm": 3.5145950317382812,
|
| 587 |
+
"learning_rate": 3.5578947368421054e-05,
|
| 588 |
+
"loss": 0.3768,
|
| 589 |
+
"step": 1325
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 15.0,
|
| 593 |
+
"grad_norm": 1.5625571012496948,
|
| 594 |
+
"learning_rate": 3.426315789473684e-05,
|
| 595 |
+
"loss": 0.3694,
|
| 596 |
+
"step": 1350
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 15.0,
|
| 600 |
+
"eval_loss": 0.36149922013282776,
|
| 601 |
+
"eval_runtime": 13.6694,
|
| 602 |
+
"eval_samples_per_second": 23.41,
|
| 603 |
+
"eval_steps_per_second": 23.41,
|
| 604 |
+
"step": 1350
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 15.278551532033426,
|
| 608 |
+
"grad_norm": 2.3763480186462402,
|
| 609 |
+
"learning_rate": 3.294736842105263e-05,
|
| 610 |
+
"loss": 0.3698,
|
| 611 |
+
"step": 1375
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 15.557103064066853,
|
| 615 |
+
"grad_norm": 2.2418417930603027,
|
| 616 |
+
"learning_rate": 3.163157894736842e-05,
|
| 617 |
+
"loss": 0.3743,
|
| 618 |
+
"step": 1400
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 15.557103064066853,
|
| 622 |
+
"eval_loss": 0.3747350573539734,
|
| 623 |
+
"eval_runtime": 13.5269,
|
| 624 |
+
"eval_samples_per_second": 23.656,
|
| 625 |
+
"eval_steps_per_second": 23.656,
|
| 626 |
+
"step": 1400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 15.835654596100278,
|
| 630 |
+
"grad_norm": 1.8634096384048462,
|
| 631 |
+
"learning_rate": 3.0315789473684214e-05,
|
| 632 |
+
"loss": 0.3714,
|
| 633 |
+
"step": 1425
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 16.11142061281337,
|
| 637 |
+
"grad_norm": 2.3779730796813965,
|
| 638 |
+
"learning_rate": 2.9e-05,
|
| 639 |
+
"loss": 0.3698,
|
| 640 |
+
"step": 1450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 16.11142061281337,
|
| 644 |
+
"eval_loss": 0.37593525648117065,
|
| 645 |
+
"eval_runtime": 13.6244,
|
| 646 |
+
"eval_samples_per_second": 23.487,
|
| 647 |
+
"eval_steps_per_second": 23.487,
|
| 648 |
+
"step": 1450
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 16.389972144846798,
|
| 652 |
+
"grad_norm": 1.6371415853500366,
|
| 653 |
+
"learning_rate": 2.768421052631579e-05,
|
| 654 |
+
"loss": 0.3708,
|
| 655 |
+
"step": 1475
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 16.668523676880223,
|
| 659 |
+
"grad_norm": 2.469703435897827,
|
| 660 |
+
"learning_rate": 2.6368421052631582e-05,
|
| 661 |
+
"loss": 0.3708,
|
| 662 |
+
"step": 1500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 16.668523676880223,
|
| 666 |
+
"eval_loss": 0.36566680669784546,
|
| 667 |
+
"eval_runtime": 13.6076,
|
| 668 |
+
"eval_samples_per_second": 23.516,
|
| 669 |
+
"eval_steps_per_second": 23.516,
|
| 670 |
+
"step": 1500
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 16.94707520891365,
|
| 674 |
+
"grad_norm": 2.27885365486145,
|
| 675 |
+
"learning_rate": 2.505263157894737e-05,
|
| 676 |
+
"loss": 0.3688,
|
| 677 |
+
"step": 1525
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 17.22284122562674,
|
| 681 |
+
"grad_norm": 1.7022783756256104,
|
| 682 |
+
"learning_rate": 2.373684210526316e-05,
|
| 683 |
+
"loss": 0.3626,
|
| 684 |
+
"step": 1550
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 17.22284122562674,
|
| 688 |
+
"eval_loss": 0.366330623626709,
|
| 689 |
+
"eval_runtime": 13.6427,
|
| 690 |
+
"eval_samples_per_second": 23.456,
|
| 691 |
+
"eval_steps_per_second": 23.456,
|
| 692 |
+
"step": 1550
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 17.501392757660167,
|
| 696 |
+
"grad_norm": 2.10900616645813,
|
| 697 |
+
"learning_rate": 2.242105263157895e-05,
|
| 698 |
+
"loss": 0.3678,
|
| 699 |
+
"step": 1575
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 17.779944289693592,
|
| 703 |
+
"grad_norm": 1.427308201789856,
|
| 704 |
+
"learning_rate": 2.110526315789474e-05,
|
| 705 |
+
"loss": 0.3671,
|
| 706 |
+
"step": 1600
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 17.779944289693592,
|
| 710 |
+
"eval_loss": 0.3622135519981384,
|
| 711 |
+
"eval_runtime": 13.6336,
|
| 712 |
+
"eval_samples_per_second": 23.471,
|
| 713 |
+
"eval_steps_per_second": 23.471,
|
| 714 |
+
"step": 1600
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 18.055710306406684,
|
| 718 |
+
"grad_norm": 2.66011905670166,
|
| 719 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 720 |
+
"loss": 0.3629,
|
| 721 |
+
"step": 1625
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 18.33426183844011,
|
| 725 |
+
"grad_norm": 1.7077386379241943,
|
| 726 |
+
"learning_rate": 1.8473684210526317e-05,
|
| 727 |
+
"loss": 0.365,
|
| 728 |
+
"step": 1650
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 18.33426183844011,
|
| 732 |
+
"eval_loss": 0.3650280833244324,
|
| 733 |
+
"eval_runtime": 13.8977,
|
| 734 |
+
"eval_samples_per_second": 23.025,
|
| 735 |
+
"eval_steps_per_second": 23.025,
|
| 736 |
+
"step": 1650
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 18.61281337047354,
|
| 740 |
+
"grad_norm": 2.3039278984069824,
|
| 741 |
+
"learning_rate": 1.7157894736842107e-05,
|
| 742 |
+
"loss": 0.3657,
|
| 743 |
+
"step": 1675
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 18.891364902506965,
|
| 747 |
+
"grad_norm": 2.4378602504730225,
|
| 748 |
+
"learning_rate": 1.5842105263157896e-05,
|
| 749 |
+
"loss": 0.3614,
|
| 750 |
+
"step": 1700
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 18.891364902506965,
|
| 754 |
+
"eval_loss": 0.366611123085022,
|
| 755 |
+
"eval_runtime": 13.6276,
|
| 756 |
+
"eval_samples_per_second": 23.482,
|
| 757 |
+
"eval_steps_per_second": 23.482,
|
| 758 |
+
"step": 1700
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 19.167130919220057,
|
| 762 |
+
"grad_norm": 2.5396945476531982,
|
| 763 |
+
"learning_rate": 1.4526315789473685e-05,
|
| 764 |
+
"loss": 0.3588,
|
| 765 |
+
"step": 1725
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 19.445682451253482,
|
| 769 |
+
"grad_norm": 1.7115105390548706,
|
| 770 |
+
"learning_rate": 1.3210526315789473e-05,
|
| 771 |
+
"loss": 0.3647,
|
| 772 |
+
"step": 1750
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 19.445682451253482,
|
| 776 |
+
"eval_loss": 0.36524954438209534,
|
| 777 |
+
"eval_runtime": 13.6929,
|
| 778 |
+
"eval_samples_per_second": 23.37,
|
| 779 |
+
"eval_steps_per_second": 23.37,
|
| 780 |
+
"step": 1750
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 19.724233983286908,
|
| 784 |
+
"grad_norm": 3.1968226432800293,
|
| 785 |
+
"learning_rate": 1.1894736842105264e-05,
|
| 786 |
+
"loss": 0.3646,
|
| 787 |
+
"step": 1775
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 20.0,
|
| 791 |
+
"grad_norm": 3.1331191062927246,
|
| 792 |
+
"learning_rate": 1.0578947368421053e-05,
|
| 793 |
+
"loss": 0.3585,
|
| 794 |
+
"step": 1800
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 20.0,
|
| 798 |
+
"eval_loss": 0.3763583302497864,
|
| 799 |
+
"eval_runtime": 13.7144,
|
| 800 |
+
"eval_samples_per_second": 23.333,
|
| 801 |
+
"eval_steps_per_second": 23.333,
|
| 802 |
+
"step": 1800
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 20.278551532033426,
|
| 806 |
+
"grad_norm": 1.4660519361495972,
|
| 807 |
+
"learning_rate": 9.263157894736844e-06,
|
| 808 |
+
"loss": 0.3633,
|
| 809 |
+
"step": 1825
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 20.55710306406685,
|
| 813 |
+
"grad_norm": 1.6120601892471313,
|
| 814 |
+
"learning_rate": 7.947368421052633e-06,
|
| 815 |
+
"loss": 0.3606,
|
| 816 |
+
"step": 1850
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 20.55710306406685,
|
| 820 |
+
"eval_loss": 0.37242794036865234,
|
| 821 |
+
"eval_runtime": 13.6577,
|
| 822 |
+
"eval_samples_per_second": 23.43,
|
| 823 |
+
"eval_steps_per_second": 23.43,
|
| 824 |
+
"step": 1850
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 20.83565459610028,
|
| 828 |
+
"grad_norm": 1.7700914144515991,
|
| 829 |
+
"learning_rate": 6.631578947368422e-06,
|
| 830 |
+
"loss": 0.3592,
|
| 831 |
+
"step": 1875
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 21.11142061281337,
|
| 835 |
+
"grad_norm": 1.610386610031128,
|
| 836 |
+
"learning_rate": 5.315789473684211e-06,
|
| 837 |
+
"loss": 0.358,
|
| 838 |
+
"step": 1900
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 21.11142061281337,
|
| 842 |
+
"eval_loss": 0.36805444955825806,
|
| 843 |
+
"eval_runtime": 13.4893,
|
| 844 |
+
"eval_samples_per_second": 23.723,
|
| 845 |
+
"eval_steps_per_second": 23.723,
|
| 846 |
+
"step": 1900
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 21.389972144846798,
|
| 850 |
+
"grad_norm": 1.5456234216690063,
|
| 851 |
+
"learning_rate": 4.000000000000001e-06,
|
| 852 |
+
"loss": 0.357,
|
| 853 |
+
"step": 1925
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 21.668523676880223,
|
| 857 |
+
"grad_norm": 1.233559489250183,
|
| 858 |
+
"learning_rate": 2.68421052631579e-06,
|
| 859 |
+
"loss": 0.3566,
|
| 860 |
+
"step": 1950
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 21.668523676880223,
|
| 864 |
+
"eval_loss": 0.37138742208480835,
|
| 865 |
+
"eval_runtime": 13.4793,
|
| 866 |
+
"eval_samples_per_second": 23.74,
|
| 867 |
+
"eval_steps_per_second": 23.74,
|
| 868 |
+
"step": 1950
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 21.94707520891365,
|
| 872 |
+
"grad_norm": 1.3927557468414307,
|
| 873 |
+
"learning_rate": 1.3684210526315791e-06,
|
| 874 |
+
"loss": 0.3578,
|
| 875 |
+
"step": 1975
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 22.22284122562674,
|
| 879 |
+
"grad_norm": 1.2782479524612427,
|
| 880 |
+
"learning_rate": 5.263157894736842e-08,
|
| 881 |
+
"loss": 0.3539,
|
| 882 |
+
"step": 2000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 22.22284122562674,
|
| 886 |
+
"eval_loss": 0.3719028830528259,
|
| 887 |
+
"eval_runtime": 13.4208,
|
| 888 |
+
"eval_samples_per_second": 23.844,
|
| 889 |
+
"eval_steps_per_second": 23.844,
|
| 890 |
+
"step": 2000
|
| 891 |
+
}
|
| 892 |
+
],
|
| 893 |
+
"logging_steps": 25,
|
| 894 |
+
"max_steps": 2000,
|
| 895 |
+
"num_input_tokens_seen": 0,
|
| 896 |
+
"num_train_epochs": 23,
|
| 897 |
+
"save_steps": 100,
|
| 898 |
+
"stateful_callbacks": {
|
| 899 |
+
"TrainerControl": {
|
| 900 |
+
"args": {
|
| 901 |
+
"should_epoch_stop": false,
|
| 902 |
+
"should_evaluate": false,
|
| 903 |
+
"should_log": false,
|
| 904 |
+
"should_save": true,
|
| 905 |
+
"should_training_stop": true
|
| 906 |
+
},
|
| 907 |
+
"attributes": {}
|
| 908 |
+
}
|
| 909 |
+
},
|
| 910 |
+
"total_flos": 5863317642483840.0,
|
| 911 |
+
"train_batch_size": 4,
|
| 912 |
+
"trial_name": null,
|
| 913 |
+
"trial_params": null
|
| 914 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be9e776f34f67b0ce79831e4e54c3792782a1ed1a0ce25e8325d66402335a8dc
|
| 3 |
+
size 5496
|