Upload 11 files
Browse files- added_tokens.json +4 -0
- config.json +92 -0
- generation_config.json +9 -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 +63 -0
- trainer_state.json +213 -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 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/speecht5_tts",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"SpeechT5ForTextToSpeech"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"conv_bias": false,
|
| 11 |
+
"conv_dim": [
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512
|
| 19 |
+
],
|
| 20 |
+
"conv_kernel": [
|
| 21 |
+
10,
|
| 22 |
+
3,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
2,
|
| 27 |
+
2
|
| 28 |
+
],
|
| 29 |
+
"conv_stride": [
|
| 30 |
+
5,
|
| 31 |
+
2,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2
|
| 37 |
+
],
|
| 38 |
+
"decoder_attention_heads": 12,
|
| 39 |
+
"decoder_ffn_dim": 3072,
|
| 40 |
+
"decoder_layerdrop": 0.1,
|
| 41 |
+
"decoder_layers": 6,
|
| 42 |
+
"decoder_start_token_id": 2,
|
| 43 |
+
"encoder_attention_heads": 12,
|
| 44 |
+
"encoder_ffn_dim": 3072,
|
| 45 |
+
"encoder_layerdrop": 0.1,
|
| 46 |
+
"encoder_layers": 12,
|
| 47 |
+
"encoder_max_relative_position": 160,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_norm": "group",
|
| 51 |
+
"feat_proj_dropout": 0.0,
|
| 52 |
+
"guided_attention_loss_num_heads": 2,
|
| 53 |
+
"guided_attention_loss_scale": 10.0,
|
| 54 |
+
"guided_attention_loss_sigma": 0.4,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.1,
|
| 57 |
+
"hidden_size": 768,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"is_encoder_decoder": true,
|
| 60 |
+
"layer_norm_eps": 1e-05,
|
| 61 |
+
"mask_feature_length": 10,
|
| 62 |
+
"mask_feature_min_masks": 0,
|
| 63 |
+
"mask_feature_prob": 0.0,
|
| 64 |
+
"mask_time_length": 10,
|
| 65 |
+
"mask_time_min_masks": 2,
|
| 66 |
+
"mask_time_prob": 0.05,
|
| 67 |
+
"max_length": 1876,
|
| 68 |
+
"max_speech_positions": 1876,
|
| 69 |
+
"max_text_positions": 600,
|
| 70 |
+
"model_type": "speecht5",
|
| 71 |
+
"num_conv_pos_embedding_groups": 16,
|
| 72 |
+
"num_conv_pos_embeddings": 128,
|
| 73 |
+
"num_feat_extract_layers": 7,
|
| 74 |
+
"num_mel_bins": 80,
|
| 75 |
+
"pad_token_id": 1,
|
| 76 |
+
"positional_dropout": 0.1,
|
| 77 |
+
"reduction_factor": 2,
|
| 78 |
+
"scale_embedding": false,
|
| 79 |
+
"speaker_embedding_dim": 512,
|
| 80 |
+
"speech_decoder_postnet_dropout": 0.5,
|
| 81 |
+
"speech_decoder_postnet_kernel": 5,
|
| 82 |
+
"speech_decoder_postnet_layers": 5,
|
| 83 |
+
"speech_decoder_postnet_units": 256,
|
| 84 |
+
"speech_decoder_prenet_dropout": 0.5,
|
| 85 |
+
"speech_decoder_prenet_layers": 2,
|
| 86 |
+
"speech_decoder_prenet_units": 256,
|
| 87 |
+
"torch_dtype": "float32",
|
| 88 |
+
"transformers_version": "4.44.0",
|
| 89 |
+
"use_cache": false,
|
| 90 |
+
"use_guided_attention_loss": true,
|
| 91 |
+
"vocab_size": 81
|
| 92 |
+
}
|
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": "4.44.0"
|
| 9 |
+
}
|
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 sha256:2b86118c963a3bbc56823a45a7ada9104806af5769817226735c3f15452bb87a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b80f6070f89085da65edc7f398e1f4ab0c587bb157756e4d3eaeed9f8366c0f2
|
| 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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 54 |
+
"eos_token": "</s>",
|
| 55 |
+
"mask_token": "<mask>",
|
| 56 |
+
"model_max_length": 600,
|
| 57 |
+
"normalize": false,
|
| 58 |
+
"pad_token": "<pad>",
|
| 59 |
+
"processor_class": "SpeechT5Processor",
|
| 60 |
+
"sp_model_kwargs": {},
|
| 61 |
+
"tokenizer_class": "SpeechT5Tokenizer",
|
| 62 |
+
"unk_token": "<unk>"
|
| 63 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.42311346530914307,
|
| 3 |
+
"best_model_checkpoint": "speecht5_finetuned_bphc/checkpoint-500",
|
| 4 |
+
"epoch": 2.6595744680851063,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13297872340425532,
|
| 13 |
+
"grad_norm": 3.937445640563965,
|
| 14 |
+
"learning_rate": 2.4e-05,
|
| 15 |
+
"loss": 1.0732,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.26595744680851063,
|
| 20 |
+
"grad_norm": 3.3802008628845215,
|
| 21 |
+
"learning_rate": 4.9e-05,
|
| 22 |
+
"loss": 0.7567,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.39893617021276595,
|
| 27 |
+
"grad_norm": 7.172617435455322,
|
| 28 |
+
"learning_rate": 7.3e-05,
|
| 29 |
+
"loss": 0.6624,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5319148936170213,
|
| 34 |
+
"grad_norm": 5.82205867767334,
|
| 35 |
+
"learning_rate": 9.8e-05,
|
| 36 |
+
"loss": 0.6294,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5319148936170213,
|
| 41 |
+
"eval_loss": 0.5470437407493591,
|
| 42 |
+
"eval_runtime": 19.8146,
|
| 43 |
+
"eval_samples_per_second": 33.763,
|
| 44 |
+
"eval_steps_per_second": 16.907,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.6648936170212766,
|
| 49 |
+
"grad_norm": 3.176703929901123,
|
| 50 |
+
"learning_rate": 9.425e-05,
|
| 51 |
+
"loss": 0.6045,
|
| 52 |
+
"step": 125
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.7978723404255319,
|
| 56 |
+
"grad_norm": 2.801500082015991,
|
| 57 |
+
"learning_rate": 8.800000000000001e-05,
|
| 58 |
+
"loss": 0.5722,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.9308510638297872,
|
| 63 |
+
"grad_norm": 7.730113506317139,
|
| 64 |
+
"learning_rate": 8.175000000000001e-05,
|
| 65 |
+
"loss": 0.5563,
|
| 66 |
+
"step": 175
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.0638297872340425,
|
| 70 |
+
"grad_norm": 11.911551475524902,
|
| 71 |
+
"learning_rate": 7.55e-05,
|
| 72 |
+
"loss": 0.5486,
|
| 73 |
+
"step": 200
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.0638297872340425,
|
| 77 |
+
"eval_loss": 0.4846374988555908,
|
| 78 |
+
"eval_runtime": 18.6315,
|
| 79 |
+
"eval_samples_per_second": 35.907,
|
| 80 |
+
"eval_steps_per_second": 17.98,
|
| 81 |
+
"step": 200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.196808510638298,
|
| 85 |
+
"grad_norm": 4.457734107971191,
|
| 86 |
+
"learning_rate": 6.925e-05,
|
| 87 |
+
"loss": 0.5378,
|
| 88 |
+
"step": 225
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.3297872340425532,
|
| 92 |
+
"grad_norm": 2.7005956172943115,
|
| 93 |
+
"learning_rate": 6.3e-05,
|
| 94 |
+
"loss": 0.5355,
|
| 95 |
+
"step": 250
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.4627659574468086,
|
| 99 |
+
"grad_norm": 2.9917397499084473,
|
| 100 |
+
"learning_rate": 5.6750000000000004e-05,
|
| 101 |
+
"loss": 0.5138,
|
| 102 |
+
"step": 275
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5957446808510638,
|
| 106 |
+
"grad_norm": 3.650026321411133,
|
| 107 |
+
"learning_rate": 5.05e-05,
|
| 108 |
+
"loss": 0.5046,
|
| 109 |
+
"step": 300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.5957446808510638,
|
| 113 |
+
"eval_loss": 0.45161741971969604,
|
| 114 |
+
"eval_runtime": 18.3387,
|
| 115 |
+
"eval_samples_per_second": 36.48,
|
| 116 |
+
"eval_steps_per_second": 18.267,
|
| 117 |
+
"step": 300
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.728723404255319,
|
| 121 |
+
"grad_norm": 3.8126158714294434,
|
| 122 |
+
"learning_rate": 4.4250000000000005e-05,
|
| 123 |
+
"loss": 0.4897,
|
| 124 |
+
"step": 325
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.8617021276595744,
|
| 128 |
+
"grad_norm": 4.279622554779053,
|
| 129 |
+
"learning_rate": 3.8e-05,
|
| 130 |
+
"loss": 0.4865,
|
| 131 |
+
"step": 350
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.9946808510638299,
|
| 135 |
+
"grad_norm": 4.044638633728027,
|
| 136 |
+
"learning_rate": 3.175e-05,
|
| 137 |
+
"loss": 0.4823,
|
| 138 |
+
"step": 375
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.127659574468085,
|
| 142 |
+
"grad_norm": 4.797245979309082,
|
| 143 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 144 |
+
"loss": 0.4732,
|
| 145 |
+
"step": 400
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.127659574468085,
|
| 149 |
+
"eval_loss": 0.43503323197364807,
|
| 150 |
+
"eval_runtime": 18.8477,
|
| 151 |
+
"eval_samples_per_second": 35.495,
|
| 152 |
+
"eval_steps_per_second": 17.774,
|
| 153 |
+
"step": 400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.2606382978723403,
|
| 157 |
+
"grad_norm": 2.5267035961151123,
|
| 158 |
+
"learning_rate": 1.925e-05,
|
| 159 |
+
"loss": 0.4774,
|
| 160 |
+
"step": 425
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.393617021276596,
|
| 164 |
+
"grad_norm": 3.2455756664276123,
|
| 165 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 166 |
+
"loss": 0.4646,
|
| 167 |
+
"step": 450
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.526595744680851,
|
| 171 |
+
"grad_norm": 3.491698980331421,
|
| 172 |
+
"learning_rate": 6.750000000000001e-06,
|
| 173 |
+
"loss": 0.4601,
|
| 174 |
+
"step": 475
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.6595744680851063,
|
| 178 |
+
"grad_norm": 3.7166852951049805,
|
| 179 |
+
"learning_rate": 5.000000000000001e-07,
|
| 180 |
+
"loss": 0.4601,
|
| 181 |
+
"step": 500
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.6595744680851063,
|
| 185 |
+
"eval_loss": 0.42311346530914307,
|
| 186 |
+
"eval_runtime": 18.8917,
|
| 187 |
+
"eval_samples_per_second": 35.412,
|
| 188 |
+
"eval_steps_per_second": 17.733,
|
| 189 |
+
"step": 500
|
| 190 |
+
}
|
| 191 |
+
],
|
| 192 |
+
"logging_steps": 25,
|
| 193 |
+
"max_steps": 500,
|
| 194 |
+
"num_input_tokens_seen": 0,
|
| 195 |
+
"num_train_epochs": 3,
|
| 196 |
+
"save_steps": 100,
|
| 197 |
+
"stateful_callbacks": {
|
| 198 |
+
"TrainerControl": {
|
| 199 |
+
"args": {
|
| 200 |
+
"should_epoch_stop": false,
|
| 201 |
+
"should_evaluate": false,
|
| 202 |
+
"should_log": false,
|
| 203 |
+
"should_save": true,
|
| 204 |
+
"should_training_stop": true
|
| 205 |
+
},
|
| 206 |
+
"attributes": {}
|
| 207 |
+
}
|
| 208 |
+
},
|
| 209 |
+
"total_flos": 1481834827297440.0,
|
| 210 |
+
"train_batch_size": 4,
|
| 211 |
+
"trial_name": null,
|
| 212 |
+
"trial_params": null
|
| 213 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0642a3ac3185f2030fc6dc592188d12be47f2dbb0ae03986a455aa8d77a2f381
|
| 3 |
+
size 5368
|