Training in progress, step 3000, checkpoint
Browse files- checkpoint-3000/added_tokens.json +4 -0
- checkpoint-3000/config.json +92 -0
- checkpoint-3000/generation_config.json +9 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/preprocessor_config.json +19 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +13 -0
- checkpoint-3000/spm_char.model +3 -0
- checkpoint-3000/tokenizer_config.json +63 -0
- checkpoint-3000/trainer_state.json +501 -0
- checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<ctc_blank>": 80,
|
| 3 |
+
"<mask>": 79
|
| 4 |
+
}
|
checkpoint-3000/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": "4.41.0.dev0",
|
| 89 |
+
"use_cache": false,
|
| 90 |
+
"use_guided_attention_loss": true,
|
| 91 |
+
"vocab_size": 81
|
| 92 |
+
}
|
checkpoint-3000/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": "4.41.0.dev0"
|
| 9 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f648c261fcdafea134afafe3703f0e5b62fdc231d63a5ada440d43436329e68
|
| 3 |
+
size 577789320
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9083a8b99f5c66757709e8775db4f29fa54ba8af2369dd96b426e5fc195f70f
|
| 3 |
+
size 1155772233
|
checkpoint-3000/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 |
+
}
|
checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d3fc7c17d487270f27e2c3733adda12b96d6505fca14729858402b855f37bf4
|
| 3 |
+
size 14244
|
checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7012ee3f099ad62840d6b9f1660082981c046dd45aa9867593fe5dd6be65399
|
| 3 |
+
size 1064
|
checkpoint-3000/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 |
+
}
|
checkpoint-3000/spm_char.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
|
| 3 |
+
size 238473
|
checkpoint-3000/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 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4159424901008606,
|
| 3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm_b32_le5_s4000/checkpoint-3000",
|
| 4 |
+
"epoch": 1.256544502617801,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020942408376963352,
|
| 13 |
+
"grad_norm": 5.243492126464844,
|
| 14 |
+
"learning_rate": 2.4000000000000003e-07,
|
| 15 |
+
"loss": 1.1863,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.041884816753926704,
|
| 20 |
+
"grad_norm": 16.012319564819336,
|
| 21 |
+
"learning_rate": 4.900000000000001e-07,
|
| 22 |
+
"loss": 1.01,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06282722513089005,
|
| 27 |
+
"grad_norm": 3.0757930278778076,
|
| 28 |
+
"learning_rate": 7.4e-07,
|
| 29 |
+
"loss": 0.9741,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08376963350785341,
|
| 34 |
+
"grad_norm": 3.897144079208374,
|
| 35 |
+
"learning_rate": 9.85e-07,
|
| 36 |
+
"loss": 0.9358,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10471204188481675,
|
| 41 |
+
"grad_norm": 3.6317360401153564,
|
| 42 |
+
"learning_rate": 1.235e-06,
|
| 43 |
+
"loss": 0.8767,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1256544502617801,
|
| 48 |
+
"grad_norm": 4.750243186950684,
|
| 49 |
+
"learning_rate": 1.485e-06,
|
| 50 |
+
"loss": 0.8576,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14659685863874344,
|
| 55 |
+
"grad_norm": 3.4898314476013184,
|
| 56 |
+
"learning_rate": 1.7350000000000001e-06,
|
| 57 |
+
"loss": 0.8472,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16753926701570682,
|
| 62 |
+
"grad_norm": 4.961293697357178,
|
| 63 |
+
"learning_rate": 1.985e-06,
|
| 64 |
+
"loss": 0.7591,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18848167539267016,
|
| 69 |
+
"grad_norm": 3.254897117614746,
|
| 70 |
+
"learning_rate": 2.235e-06,
|
| 71 |
+
"loss": 0.7548,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2094240837696335,
|
| 76 |
+
"grad_norm": 3.3995440006256104,
|
| 77 |
+
"learning_rate": 2.4850000000000003e-06,
|
| 78 |
+
"loss": 0.7211,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2094240837696335,
|
| 83 |
+
"eval_loss": 0.6148238182067871,
|
| 84 |
+
"eval_runtime": 267.7517,
|
| 85 |
+
"eval_samples_per_second": 31.705,
|
| 86 |
+
"eval_steps_per_second": 3.966,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23036649214659685,
|
| 91 |
+
"grad_norm": 3.2476744651794434,
|
| 92 |
+
"learning_rate": 2.7350000000000005e-06,
|
| 93 |
+
"loss": 0.6859,
|
| 94 |
+
"step": 550
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2513089005235602,
|
| 98 |
+
"grad_norm": 4.222187042236328,
|
| 99 |
+
"learning_rate": 2.9850000000000002e-06,
|
| 100 |
+
"loss": 0.6653,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.27225130890052357,
|
| 105 |
+
"grad_norm": 3.4279122352600098,
|
| 106 |
+
"learning_rate": 3.2350000000000004e-06,
|
| 107 |
+
"loss": 0.6612,
|
| 108 |
+
"step": 650
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2931937172774869,
|
| 112 |
+
"grad_norm": 2.7588794231414795,
|
| 113 |
+
"learning_rate": 3.485e-06,
|
| 114 |
+
"loss": 0.6404,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.31413612565445026,
|
| 119 |
+
"grad_norm": 3.481127977371216,
|
| 120 |
+
"learning_rate": 3.7350000000000002e-06,
|
| 121 |
+
"loss": 0.647,
|
| 122 |
+
"step": 750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.33507853403141363,
|
| 126 |
+
"grad_norm": 4.153278827667236,
|
| 127 |
+
"learning_rate": 3.985000000000001e-06,
|
| 128 |
+
"loss": 0.6374,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.35602094240837695,
|
| 133 |
+
"grad_norm": 5.10654354095459,
|
| 134 |
+
"learning_rate": 4.235e-06,
|
| 135 |
+
"loss": 0.6225,
|
| 136 |
+
"step": 850
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3769633507853403,
|
| 140 |
+
"grad_norm": 2.7014458179473877,
|
| 141 |
+
"learning_rate": 4.485e-06,
|
| 142 |
+
"loss": 0.6026,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.39790575916230364,
|
| 147 |
+
"grad_norm": 2.965581178665161,
|
| 148 |
+
"learning_rate": 4.735e-06,
|
| 149 |
+
"loss": 0.5963,
|
| 150 |
+
"step": 950
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.418848167539267,
|
| 154 |
+
"grad_norm": 2.671508312225342,
|
| 155 |
+
"learning_rate": 4.9850000000000006e-06,
|
| 156 |
+
"loss": 0.6059,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.418848167539267,
|
| 161 |
+
"eval_loss": 0.514046847820282,
|
| 162 |
+
"eval_runtime": 268.9563,
|
| 163 |
+
"eval_samples_per_second": 31.563,
|
| 164 |
+
"eval_steps_per_second": 3.949,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.4397905759162304,
|
| 169 |
+
"grad_norm": 2.840752363204956,
|
| 170 |
+
"learning_rate": 5.235e-06,
|
| 171 |
+
"loss": 0.5759,
|
| 172 |
+
"step": 1050
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.4607329842931937,
|
| 176 |
+
"grad_norm": 4.1088714599609375,
|
| 177 |
+
"learning_rate": 5.485e-06,
|
| 178 |
+
"loss": 0.5678,
|
| 179 |
+
"step": 1100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.4816753926701571,
|
| 183 |
+
"grad_norm": 2.7752063274383545,
|
| 184 |
+
"learning_rate": 5.735e-06,
|
| 185 |
+
"loss": 0.5759,
|
| 186 |
+
"step": 1150
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.5026178010471204,
|
| 190 |
+
"grad_norm": 5.213489055633545,
|
| 191 |
+
"learning_rate": 5.985000000000001e-06,
|
| 192 |
+
"loss": 0.5476,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.5235602094240838,
|
| 197 |
+
"grad_norm": 2.6381824016571045,
|
| 198 |
+
"learning_rate": 6.235000000000001e-06,
|
| 199 |
+
"loss": 0.5632,
|
| 200 |
+
"step": 1250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5445026178010471,
|
| 204 |
+
"grad_norm": 3.088671922683716,
|
| 205 |
+
"learning_rate": 6.485000000000001e-06,
|
| 206 |
+
"loss": 0.5625,
|
| 207 |
+
"step": 1300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5654450261780105,
|
| 211 |
+
"grad_norm": 3.4818124771118164,
|
| 212 |
+
"learning_rate": 6.735000000000001e-06,
|
| 213 |
+
"loss": 0.5608,
|
| 214 |
+
"step": 1350
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.5863874345549738,
|
| 218 |
+
"grad_norm": 3.6994926929473877,
|
| 219 |
+
"learning_rate": 6.985000000000001e-06,
|
| 220 |
+
"loss": 0.5351,
|
| 221 |
+
"step": 1400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.6073298429319371,
|
| 225 |
+
"grad_norm": 4.822711944580078,
|
| 226 |
+
"learning_rate": 7.235000000000001e-06,
|
| 227 |
+
"loss": 0.5407,
|
| 228 |
+
"step": 1450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.6282722513089005,
|
| 232 |
+
"grad_norm": 3.7619833946228027,
|
| 233 |
+
"learning_rate": 7.485000000000001e-06,
|
| 234 |
+
"loss": 0.5347,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.6282722513089005,
|
| 239 |
+
"eval_loss": 0.4724981188774109,
|
| 240 |
+
"eval_runtime": 271.4755,
|
| 241 |
+
"eval_samples_per_second": 31.27,
|
| 242 |
+
"eval_steps_per_second": 3.912,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.6492146596858639,
|
| 247 |
+
"grad_norm": 2.4959261417388916,
|
| 248 |
+
"learning_rate": 7.735e-06,
|
| 249 |
+
"loss": 0.5247,
|
| 250 |
+
"step": 1550
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6701570680628273,
|
| 254 |
+
"grad_norm": 4.8328447341918945,
|
| 255 |
+
"learning_rate": 7.985e-06,
|
| 256 |
+
"loss": 0.5263,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.6910994764397905,
|
| 261 |
+
"grad_norm": 3.3857789039611816,
|
| 262 |
+
"learning_rate": 8.235e-06,
|
| 263 |
+
"loss": 0.5366,
|
| 264 |
+
"step": 1650
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.7120418848167539,
|
| 268 |
+
"grad_norm": 6.467920780181885,
|
| 269 |
+
"learning_rate": 8.485000000000001e-06,
|
| 270 |
+
"loss": 0.5233,
|
| 271 |
+
"step": 1700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.7329842931937173,
|
| 275 |
+
"grad_norm": 3.377429485321045,
|
| 276 |
+
"learning_rate": 8.735000000000002e-06,
|
| 277 |
+
"loss": 0.528,
|
| 278 |
+
"step": 1750
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7539267015706806,
|
| 282 |
+
"grad_norm": 2.8954410552978516,
|
| 283 |
+
"learning_rate": 8.985000000000001e-06,
|
| 284 |
+
"loss": 0.5072,
|
| 285 |
+
"step": 1800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.774869109947644,
|
| 289 |
+
"grad_norm": 5.599782943725586,
|
| 290 |
+
"learning_rate": 9.235e-06,
|
| 291 |
+
"loss": 0.5337,
|
| 292 |
+
"step": 1850
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.7958115183246073,
|
| 296 |
+
"grad_norm": 3.421278238296509,
|
| 297 |
+
"learning_rate": 9.485000000000002e-06,
|
| 298 |
+
"loss": 0.506,
|
| 299 |
+
"step": 1900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.8167539267015707,
|
| 303 |
+
"grad_norm": 2.43534517288208,
|
| 304 |
+
"learning_rate": 9.735e-06,
|
| 305 |
+
"loss": 0.503,
|
| 306 |
+
"step": 1950
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.837696335078534,
|
| 310 |
+
"grad_norm": 3.1177427768707275,
|
| 311 |
+
"learning_rate": 9.985000000000002e-06,
|
| 312 |
+
"loss": 0.4888,
|
| 313 |
+
"step": 2000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.837696335078534,
|
| 317 |
+
"eval_loss": 0.46118447184562683,
|
| 318 |
+
"eval_runtime": 279.0953,
|
| 319 |
+
"eval_samples_per_second": 30.416,
|
| 320 |
+
"eval_steps_per_second": 3.805,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8586387434554974,
|
| 325 |
+
"grad_norm": 3.640716075897217,
|
| 326 |
+
"learning_rate": 9.765e-06,
|
| 327 |
+
"loss": 0.5128,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8795811518324608,
|
| 332 |
+
"grad_norm": 6.894229412078857,
|
| 333 |
+
"learning_rate": 9.515000000000001e-06,
|
| 334 |
+
"loss": 0.4882,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.900523560209424,
|
| 339 |
+
"grad_norm": 3.4520230293273926,
|
| 340 |
+
"learning_rate": 9.265e-06,
|
| 341 |
+
"loss": 0.4932,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.9214659685863874,
|
| 346 |
+
"grad_norm": 3.128208875656128,
|
| 347 |
+
"learning_rate": 9.015000000000001e-06,
|
| 348 |
+
"loss": 0.4861,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9424083769633508,
|
| 353 |
+
"grad_norm": 3.2562131881713867,
|
| 354 |
+
"learning_rate": 8.765e-06,
|
| 355 |
+
"loss": 0.495,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9633507853403142,
|
| 360 |
+
"grad_norm": 4.8225603103637695,
|
| 361 |
+
"learning_rate": 8.515e-06,
|
| 362 |
+
"loss": 0.4968,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9842931937172775,
|
| 367 |
+
"grad_norm": 3.6048710346221924,
|
| 368 |
+
"learning_rate": 8.265000000000001e-06,
|
| 369 |
+
"loss": 0.4975,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.0052356020942408,
|
| 374 |
+
"grad_norm": 5.707277774810791,
|
| 375 |
+
"learning_rate": 8.015e-06,
|
| 376 |
+
"loss": 0.4717,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.0261780104712042,
|
| 381 |
+
"grad_norm": 3.100660800933838,
|
| 382 |
+
"learning_rate": 7.765000000000001e-06,
|
| 383 |
+
"loss": 0.489,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.0471204188481675,
|
| 388 |
+
"grad_norm": 2.2402753829956055,
|
| 389 |
+
"learning_rate": 7.515e-06,
|
| 390 |
+
"loss": 0.4923,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.0471204188481675,
|
| 395 |
+
"eval_loss": 0.4335620403289795,
|
| 396 |
+
"eval_runtime": 275.5568,
|
| 397 |
+
"eval_samples_per_second": 30.807,
|
| 398 |
+
"eval_steps_per_second": 3.854,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.068062827225131,
|
| 403 |
+
"grad_norm": 4.66270112991333,
|
| 404 |
+
"learning_rate": 7.265000000000001e-06,
|
| 405 |
+
"loss": 0.4845,
|
| 406 |
+
"step": 2550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.0890052356020943,
|
| 410 |
+
"grad_norm": 2.6913790702819824,
|
| 411 |
+
"learning_rate": 7.015000000000001e-06,
|
| 412 |
+
"loss": 0.4614,
|
| 413 |
+
"step": 2600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.1099476439790577,
|
| 417 |
+
"grad_norm": 2.7639589309692383,
|
| 418 |
+
"learning_rate": 6.7650000000000005e-06,
|
| 419 |
+
"loss": 0.4844,
|
| 420 |
+
"step": 2650
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.130890052356021,
|
| 424 |
+
"grad_norm": 3.4958367347717285,
|
| 425 |
+
"learning_rate": 6.515e-06,
|
| 426 |
+
"loss": 0.485,
|
| 427 |
+
"step": 2700
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.1518324607329844,
|
| 431 |
+
"grad_norm": 1.9745889902114868,
|
| 432 |
+
"learning_rate": 6.265e-06,
|
| 433 |
+
"loss": 0.4875,
|
| 434 |
+
"step": 2750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1727748691099475,
|
| 438 |
+
"grad_norm": 2.011784553527832,
|
| 439 |
+
"learning_rate": 6.015000000000001e-06,
|
| 440 |
+
"loss": 0.4637,
|
| 441 |
+
"step": 2800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.193717277486911,
|
| 445 |
+
"grad_norm": 4.093133926391602,
|
| 446 |
+
"learning_rate": 5.765000000000001e-06,
|
| 447 |
+
"loss": 0.4665,
|
| 448 |
+
"step": 2850
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.2146596858638743,
|
| 452 |
+
"grad_norm": 3.1722769737243652,
|
| 453 |
+
"learning_rate": 5.5150000000000006e-06,
|
| 454 |
+
"loss": 0.4708,
|
| 455 |
+
"step": 2900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.2356020942408377,
|
| 459 |
+
"grad_norm": 3.777724504470825,
|
| 460 |
+
"learning_rate": 5.265e-06,
|
| 461 |
+
"loss": 0.4697,
|
| 462 |
+
"step": 2950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.256544502617801,
|
| 466 |
+
"grad_norm": 2.69818377494812,
|
| 467 |
+
"learning_rate": 5.015e-06,
|
| 468 |
+
"loss": 0.4686,
|
| 469 |
+
"step": 3000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.256544502617801,
|
| 473 |
+
"eval_loss": 0.4159424901008606,
|
| 474 |
+
"eval_runtime": 272.6799,
|
| 475 |
+
"eval_samples_per_second": 31.132,
|
| 476 |
+
"eval_steps_per_second": 3.895,
|
| 477 |
+
"step": 3000
|
| 478 |
+
}
|
| 479 |
+
],
|
| 480 |
+
"logging_steps": 50,
|
| 481 |
+
"max_steps": 4000,
|
| 482 |
+
"num_input_tokens_seen": 0,
|
| 483 |
+
"num_train_epochs": 2,
|
| 484 |
+
"save_steps": 500,
|
| 485 |
+
"stateful_callbacks": {
|
| 486 |
+
"TrainerControl": {
|
| 487 |
+
"args": {
|
| 488 |
+
"should_epoch_stop": false,
|
| 489 |
+
"should_evaluate": false,
|
| 490 |
+
"should_log": false,
|
| 491 |
+
"should_save": true,
|
| 492 |
+
"should_training_stop": false
|
| 493 |
+
},
|
| 494 |
+
"attributes": {}
|
| 495 |
+
}
|
| 496 |
+
},
|
| 497 |
+
"total_flos": 1.3431343807297152e+16,
|
| 498 |
+
"train_batch_size": 16,
|
| 499 |
+
"trial_name": null,
|
| 500 |
+
"trial_params": null
|
| 501 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e477b9339822c7d6cb2a90b0a25d94f526e1b3b97304135eb3949a17ebd18ba
|
| 3 |
+
size 5304
|