Commit
•
b84ab82
1
Parent(s):
6f2daec
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 sha256:1c8c64eb12c9b4e5bfeb1ac0c3a2b6e7080ec73102beb068800f3cb791fd237a
|
| 3 |
+
size 577789320
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75fee3606d631d10b98e7ceaab79718b1cc960b188b057303ee9a4dd0c9b07c5
|
| 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 sha256:0aa2e9b05d62fd84534d446714acc4c711b138dead93513400fa55984d4962f0
|
| 3 |
+
size 14244
|
checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffa04f318dac7e524e25447b54d3f41fa2eaef690d4b697dd0fccadbc3fd98bc
|
| 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": 0.40509888529777527,
|
| 3 |
+
"best_model_checkpoint": "mikhail_panzo/ceb_b128_le3_s4000/checkpoint-500",
|
| 4 |
+
"epoch": 237.62376237623764,
|
| 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": 3.9603960396039604,
|
| 13 |
+
"grad_norm": 1.6000345945358276,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 0.7102,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 7.920792079207921,
|
| 20 |
+
"grad_norm": 1.240767478942871,
|
| 21 |
+
"learning_rate": 5e-05,
|
| 22 |
+
"loss": 0.5129,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 11.881188118811881,
|
| 27 |
+
"grad_norm": 2.545292377471924,
|
| 28 |
+
"learning_rate": 7.5e-05,
|
| 29 |
+
"loss": 0.4701,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 15.841584158415841,
|
| 34 |
+
"grad_norm": 3.054067611694336,
|
| 35 |
+
"learning_rate": 0.0001,
|
| 36 |
+
"loss": 0.4502,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 19.801980198019802,
|
| 41 |
+
"grad_norm": 3.884960889816284,
|
| 42 |
+
"learning_rate": 0.000125,
|
| 43 |
+
"loss": 0.4433,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 23.762376237623762,
|
| 48 |
+
"grad_norm": 2.102992296218872,
|
| 49 |
+
"learning_rate": 0.00015,
|
| 50 |
+
"loss": 0.4361,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 27.722772277227723,
|
| 55 |
+
"grad_norm": 3.1947975158691406,
|
| 56 |
+
"learning_rate": 0.000175,
|
| 57 |
+
"loss": 0.4335,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 31.683168316831683,
|
| 62 |
+
"grad_norm": 4.315099716186523,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.4322,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 35.64356435643565,
|
| 69 |
+
"grad_norm": 6.909496784210205,
|
| 70 |
+
"learning_rate": 0.00022500000000000002,
|
| 71 |
+
"loss": 0.4346,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 39.603960396039604,
|
| 76 |
+
"grad_norm": 2.0800621509552,
|
| 77 |
+
"learning_rate": 0.00025,
|
| 78 |
+
"loss": 0.42,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 39.603960396039604,
|
| 83 |
+
"eval_loss": 0.40509888529777527,
|
| 84 |
+
"eval_runtime": 8.3422,
|
| 85 |
+
"eval_samples_per_second": 21.577,
|
| 86 |
+
"eval_steps_per_second": 2.757,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 43.56435643564357,
|
| 91 |
+
"grad_norm": 5.034981727600098,
|
| 92 |
+
"learning_rate": 0.000275,
|
| 93 |
+
"loss": 0.4336,
|
| 94 |
+
"step": 550
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 47.524752475247524,
|
| 98 |
+
"grad_norm": 6.329326152801514,
|
| 99 |
+
"learning_rate": 0.0003,
|
| 100 |
+
"loss": 0.4265,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 51.48514851485149,
|
| 105 |
+
"grad_norm": 2.624539852142334,
|
| 106 |
+
"learning_rate": 0.00032500000000000004,
|
| 107 |
+
"loss": 0.4249,
|
| 108 |
+
"step": 650
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 55.445544554455445,
|
| 112 |
+
"grad_norm": 1.945346474647522,
|
| 113 |
+
"learning_rate": 0.00035,
|
| 114 |
+
"loss": 0.4155,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 59.40594059405941,
|
| 119 |
+
"grad_norm": 3.682614326477051,
|
| 120 |
+
"learning_rate": 0.000375,
|
| 121 |
+
"loss": 0.4117,
|
| 122 |
+
"step": 750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 63.366336633663366,
|
| 126 |
+
"grad_norm": 1.726725459098816,
|
| 127 |
+
"learning_rate": 0.0004,
|
| 128 |
+
"loss": 0.4139,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 67.32673267326733,
|
| 133 |
+
"grad_norm": 1.665935754776001,
|
| 134 |
+
"learning_rate": 0.000425,
|
| 135 |
+
"loss": 0.4138,
|
| 136 |
+
"step": 850
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 71.2871287128713,
|
| 140 |
+
"grad_norm": 2.6523916721343994,
|
| 141 |
+
"learning_rate": 0.00045000000000000004,
|
| 142 |
+
"loss": 0.4098,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 75.24752475247524,
|
| 147 |
+
"grad_norm": 4.059382915496826,
|
| 148 |
+
"learning_rate": 0.000475,
|
| 149 |
+
"loss": 0.4075,
|
| 150 |
+
"step": 950
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 79.20792079207921,
|
| 154 |
+
"grad_norm": 4.141351222991943,
|
| 155 |
+
"learning_rate": 0.0005,
|
| 156 |
+
"loss": 0.4187,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 79.20792079207921,
|
| 161 |
+
"eval_loss": 0.44087010622024536,
|
| 162 |
+
"eval_runtime": 7.9097,
|
| 163 |
+
"eval_samples_per_second": 22.757,
|
| 164 |
+
"eval_steps_per_second": 2.908,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 83.16831683168317,
|
| 169 |
+
"grad_norm": 4.268443584442139,
|
| 170 |
+
"learning_rate": 0.0005250000000000001,
|
| 171 |
+
"loss": 0.4233,
|
| 172 |
+
"step": 1050
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 87.12871287128714,
|
| 176 |
+
"grad_norm": 2.5200088024139404,
|
| 177 |
+
"learning_rate": 0.00055,
|
| 178 |
+
"loss": 0.4165,
|
| 179 |
+
"step": 1100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 91.08910891089108,
|
| 183 |
+
"grad_norm": 1.1965175867080688,
|
| 184 |
+
"learning_rate": 0.000575,
|
| 185 |
+
"loss": 0.4131,
|
| 186 |
+
"step": 1150
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 95.04950495049505,
|
| 190 |
+
"grad_norm": 5.397756099700928,
|
| 191 |
+
"learning_rate": 0.0006,
|
| 192 |
+
"loss": 0.4209,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 99.00990099009901,
|
| 197 |
+
"grad_norm": 4.361856460571289,
|
| 198 |
+
"learning_rate": 0.000625,
|
| 199 |
+
"loss": 0.4289,
|
| 200 |
+
"step": 1250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 102.97029702970298,
|
| 204 |
+
"grad_norm": 8.962231636047363,
|
| 205 |
+
"learning_rate": 0.0006500000000000001,
|
| 206 |
+
"loss": 0.4418,
|
| 207 |
+
"step": 1300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 106.93069306930693,
|
| 211 |
+
"grad_norm": 5.27103328704834,
|
| 212 |
+
"learning_rate": 0.000675,
|
| 213 |
+
"loss": 0.4297,
|
| 214 |
+
"step": 1350
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 110.89108910891089,
|
| 218 |
+
"grad_norm": 5.550845623016357,
|
| 219 |
+
"learning_rate": 0.0007,
|
| 220 |
+
"loss": 0.4394,
|
| 221 |
+
"step": 1400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 114.85148514851485,
|
| 225 |
+
"grad_norm": 1.9186675548553467,
|
| 226 |
+
"learning_rate": 0.000725,
|
| 227 |
+
"loss": 0.436,
|
| 228 |
+
"step": 1450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 118.81188118811882,
|
| 232 |
+
"grad_norm": 2.9912400245666504,
|
| 233 |
+
"learning_rate": 0.00075,
|
| 234 |
+
"loss": 0.4401,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 118.81188118811882,
|
| 239 |
+
"eval_loss": 0.4779699444770813,
|
| 240 |
+
"eval_runtime": 7.8042,
|
| 241 |
+
"eval_samples_per_second": 23.065,
|
| 242 |
+
"eval_steps_per_second": 2.947,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 122.77227722772277,
|
| 247 |
+
"grad_norm": 2.4975500106811523,
|
| 248 |
+
"learning_rate": 0.0007750000000000001,
|
| 249 |
+
"loss": 0.4325,
|
| 250 |
+
"step": 1550
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 126.73267326732673,
|
| 254 |
+
"grad_norm": 4.072780609130859,
|
| 255 |
+
"learning_rate": 0.0008,
|
| 256 |
+
"loss": 0.4258,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 130.69306930693068,
|
| 261 |
+
"grad_norm": 8.71650218963623,
|
| 262 |
+
"learning_rate": 0.000825,
|
| 263 |
+
"loss": 0.427,
|
| 264 |
+
"step": 1650
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 134.65346534653466,
|
| 268 |
+
"grad_norm": 3.707995653152466,
|
| 269 |
+
"learning_rate": 0.00085,
|
| 270 |
+
"loss": 0.4227,
|
| 271 |
+
"step": 1700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 138.6138613861386,
|
| 275 |
+
"grad_norm": 1.5397919416427612,
|
| 276 |
+
"learning_rate": 0.000875,
|
| 277 |
+
"loss": 0.4194,
|
| 278 |
+
"step": 1750
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 142.5742574257426,
|
| 282 |
+
"grad_norm": 3.601444959640503,
|
| 283 |
+
"learning_rate": 0.0009000000000000001,
|
| 284 |
+
"loss": 0.4234,
|
| 285 |
+
"step": 1800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 146.53465346534654,
|
| 289 |
+
"grad_norm": 4.232907772064209,
|
| 290 |
+
"learning_rate": 0.000925,
|
| 291 |
+
"loss": 0.4276,
|
| 292 |
+
"step": 1850
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 150.4950495049505,
|
| 296 |
+
"grad_norm": 8.078680038452148,
|
| 297 |
+
"learning_rate": 0.00095,
|
| 298 |
+
"loss": 0.4453,
|
| 299 |
+
"step": 1900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 154.45544554455446,
|
| 303 |
+
"grad_norm": 1.406493067741394,
|
| 304 |
+
"learning_rate": 0.000975,
|
| 305 |
+
"loss": 0.4428,
|
| 306 |
+
"step": 1950
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 158.41584158415841,
|
| 310 |
+
"grad_norm": 3.9557948112487793,
|
| 311 |
+
"learning_rate": 0.001,
|
| 312 |
+
"loss": 0.4456,
|
| 313 |
+
"step": 2000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 158.41584158415841,
|
| 317 |
+
"eval_loss": 0.4567292630672455,
|
| 318 |
+
"eval_runtime": 8.3256,
|
| 319 |
+
"eval_samples_per_second": 21.62,
|
| 320 |
+
"eval_steps_per_second": 2.763,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 162.37623762376236,
|
| 325 |
+
"grad_norm": 1.2412426471710205,
|
| 326 |
+
"learning_rate": 0.000975,
|
| 327 |
+
"loss": 0.4309,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 166.33663366336634,
|
| 332 |
+
"grad_norm": 2.759005069732666,
|
| 333 |
+
"learning_rate": 0.00095,
|
| 334 |
+
"loss": 0.4229,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 170.2970297029703,
|
| 339 |
+
"grad_norm": 1.9666180610656738,
|
| 340 |
+
"learning_rate": 0.000925,
|
| 341 |
+
"loss": 0.4326,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 174.25742574257427,
|
| 346 |
+
"grad_norm": 2.397604465484619,
|
| 347 |
+
"learning_rate": 0.0009000000000000001,
|
| 348 |
+
"loss": 0.435,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 178.21782178217822,
|
| 353 |
+
"grad_norm": 0.8311312198638916,
|
| 354 |
+
"learning_rate": 0.000875,
|
| 355 |
+
"loss": 0.4514,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 182.17821782178217,
|
| 360 |
+
"grad_norm": 1.0605016946792603,
|
| 361 |
+
"learning_rate": 0.00085,
|
| 362 |
+
"loss": 0.4318,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 186.13861386138615,
|
| 367 |
+
"grad_norm": 4.460992813110352,
|
| 368 |
+
"learning_rate": 0.000825,
|
| 369 |
+
"loss": 0.4175,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 190.0990099009901,
|
| 374 |
+
"grad_norm": 1.9337185621261597,
|
| 375 |
+
"learning_rate": 0.0008,
|
| 376 |
+
"loss": 0.4119,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 194.05940594059405,
|
| 381 |
+
"grad_norm": 3.334519624710083,
|
| 382 |
+
"learning_rate": 0.0007750000000000001,
|
| 383 |
+
"loss": 0.4074,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 198.01980198019803,
|
| 388 |
+
"grad_norm": 1.8377976417541504,
|
| 389 |
+
"learning_rate": 0.00075,
|
| 390 |
+
"loss": 0.4221,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 198.01980198019803,
|
| 395 |
+
"eval_loss": 0.4531227648258209,
|
| 396 |
+
"eval_runtime": 8.0586,
|
| 397 |
+
"eval_samples_per_second": 22.336,
|
| 398 |
+
"eval_steps_per_second": 2.854,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 201.98019801980197,
|
| 403 |
+
"grad_norm": 4.119373798370361,
|
| 404 |
+
"learning_rate": 0.000725,
|
| 405 |
+
"loss": 0.3957,
|
| 406 |
+
"step": 2550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 205.94059405940595,
|
| 410 |
+
"grad_norm": 1.5359861850738525,
|
| 411 |
+
"learning_rate": 0.0007,
|
| 412 |
+
"loss": 0.3932,
|
| 413 |
+
"step": 2600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 209.9009900990099,
|
| 417 |
+
"grad_norm": 1.9072787761688232,
|
| 418 |
+
"learning_rate": 0.000675,
|
| 419 |
+
"loss": 0.3771,
|
| 420 |
+
"step": 2650
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 213.86138613861385,
|
| 424 |
+
"grad_norm": 1.0733487606048584,
|
| 425 |
+
"learning_rate": 0.0006500000000000001,
|
| 426 |
+
"loss": 0.382,
|
| 427 |
+
"step": 2700
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 217.82178217821783,
|
| 431 |
+
"grad_norm": 2.296584367752075,
|
| 432 |
+
"learning_rate": 0.000625,
|
| 433 |
+
"loss": 0.3757,
|
| 434 |
+
"step": 2750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 221.78217821782178,
|
| 438 |
+
"grad_norm": 2.115774631500244,
|
| 439 |
+
"learning_rate": 0.0006,
|
| 440 |
+
"loss": 0.3688,
|
| 441 |
+
"step": 2800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 225.74257425742573,
|
| 445 |
+
"grad_norm": 0.9828720092773438,
|
| 446 |
+
"learning_rate": 0.000575,
|
| 447 |
+
"loss": 0.3722,
|
| 448 |
+
"step": 2850
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 229.7029702970297,
|
| 452 |
+
"grad_norm": 0.9079552292823792,
|
| 453 |
+
"learning_rate": 0.00055,
|
| 454 |
+
"loss": 0.3634,
|
| 455 |
+
"step": 2900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 233.66336633663366,
|
| 459 |
+
"grad_norm": 1.3151072263717651,
|
| 460 |
+
"learning_rate": 0.0005250000000000001,
|
| 461 |
+
"loss": 0.3629,
|
| 462 |
+
"step": 2950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 237.62376237623764,
|
| 466 |
+
"grad_norm": 2.782442569732666,
|
| 467 |
+
"learning_rate": 0.0005,
|
| 468 |
+
"loss": 0.3571,
|
| 469 |
+
"step": 3000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 237.62376237623764,
|
| 473 |
+
"eval_loss": 0.45037713646888733,
|
| 474 |
+
"eval_runtime": 7.9501,
|
| 475 |
+
"eval_samples_per_second": 22.641,
|
| 476 |
+
"eval_steps_per_second": 2.893,
|
| 477 |
+
"step": 3000
|
| 478 |
+
}
|
| 479 |
+
],
|
| 480 |
+
"logging_steps": 50,
|
| 481 |
+
"max_steps": 4000,
|
| 482 |
+
"num_input_tokens_seen": 0,
|
| 483 |
+
"num_train_epochs": 334,
|
| 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": 6.483773509386624e+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:cbaa345de0ab4f13d7bd425d09bcae2ff7f99ef402d8f7a65319c9cd541130dc
|
| 3 |
+
size 5304
|