Commit
•
fc67bc2
1
Parent(s):
3004449
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 sha256:16301888410924288f2425968ae3e447e2447c7342bc21c8bdd0c369b24cbc69
|
| 3 |
+
size 577789320
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:072e1c34e8b0c9732bbefe31cfdf90b9c12d9495c858abe3481975bc55cdad02
|
| 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:b0bd26a66f18a63513b4644dff9bbce4420bc172da7cc36bbc9e2bbc11796d8c
|
| 3 |
+
size 14244
|
checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd328cc1d8a8044893283284374db9b5e70b75fff40160eb779c4d2193057c2
|
| 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": 0.34259819984436035,
|
| 3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le4_s4000/checkpoint-3000",
|
| 4 |
+
"epoch": 5.026178010471204,
|
| 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": 0.08376963350785341,
|
| 13 |
+
"grad_norm": 2.9717624187469482,
|
| 14 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 15 |
+
"loss": 1.0424,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16753926701570682,
|
| 20 |
+
"grad_norm": 2.9720630645751953,
|
| 21 |
+
"learning_rate": 4.950000000000001e-06,
|
| 22 |
+
"loss": 0.8474,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2513089005235602,
|
| 27 |
+
"grad_norm": 2.445929765701294,
|
| 28 |
+
"learning_rate": 7.45e-06,
|
| 29 |
+
"loss": 0.7336,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33507853403141363,
|
| 34 |
+
"grad_norm": 5.502955913543701,
|
| 35 |
+
"learning_rate": 9.950000000000001e-06,
|
| 36 |
+
"loss": 0.6492,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.418848167539267,
|
| 41 |
+
"grad_norm": 2.3356130123138428,
|
| 42 |
+
"learning_rate": 1.2450000000000001e-05,
|
| 43 |
+
"loss": 0.6133,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5026178010471204,
|
| 48 |
+
"grad_norm": 1.937270164489746,
|
| 49 |
+
"learning_rate": 1.4950000000000001e-05,
|
| 50 |
+
"loss": 0.5889,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5863874345549738,
|
| 55 |
+
"grad_norm": 2.392244338989258,
|
| 56 |
+
"learning_rate": 1.745e-05,
|
| 57 |
+
"loss": 0.5694,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6701570680628273,
|
| 62 |
+
"grad_norm": 7.3209919929504395,
|
| 63 |
+
"learning_rate": 1.995e-05,
|
| 64 |
+
"loss": 0.5477,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7539267015706806,
|
| 69 |
+
"grad_norm": 3.415917158126831,
|
| 70 |
+
"learning_rate": 2.245e-05,
|
| 71 |
+
"loss": 0.5329,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.837696335078534,
|
| 76 |
+
"grad_norm": 3.0256705284118652,
|
| 77 |
+
"learning_rate": 2.495e-05,
|
| 78 |
+
"loss": 0.5173,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.837696335078534,
|
| 83 |
+
"eval_loss": 0.4566049873828888,
|
| 84 |
+
"eval_runtime": 261.3511,
|
| 85 |
+
"eval_samples_per_second": 32.481,
|
| 86 |
+
"eval_steps_per_second": 4.063,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.9214659685863874,
|
| 91 |
+
"grad_norm": 1.9436837434768677,
|
| 92 |
+
"learning_rate": 2.7450000000000003e-05,
|
| 93 |
+
"loss": 0.5079,
|
| 94 |
+
"step": 550
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.0052356020942408,
|
| 98 |
+
"grad_norm": 1.819956660270691,
|
| 99 |
+
"learning_rate": 2.995e-05,
|
| 100 |
+
"loss": 0.4969,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.0890052356020943,
|
| 105 |
+
"grad_norm": 5.457251071929932,
|
| 106 |
+
"learning_rate": 3.245e-05,
|
| 107 |
+
"loss": 0.4977,
|
| 108 |
+
"step": 650
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.1727748691099475,
|
| 112 |
+
"grad_norm": 3.183980703353882,
|
| 113 |
+
"learning_rate": 3.495e-05,
|
| 114 |
+
"loss": 0.4923,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.256544502617801,
|
| 119 |
+
"grad_norm": 7.1660051345825195,
|
| 120 |
+
"learning_rate": 3.745e-05,
|
| 121 |
+
"loss": 0.4802,
|
| 122 |
+
"step": 750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.3403141361256545,
|
| 126 |
+
"grad_norm": 5.499026775360107,
|
| 127 |
+
"learning_rate": 3.995e-05,
|
| 128 |
+
"loss": 0.4754,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.4240837696335078,
|
| 133 |
+
"grad_norm": 2.8053908348083496,
|
| 134 |
+
"learning_rate": 4.245e-05,
|
| 135 |
+
"loss": 0.4669,
|
| 136 |
+
"step": 850
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.5078534031413613,
|
| 140 |
+
"grad_norm": 3.017005443572998,
|
| 141 |
+
"learning_rate": 4.495e-05,
|
| 142 |
+
"loss": 0.4604,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.5916230366492146,
|
| 147 |
+
"grad_norm": 2.7971177101135254,
|
| 148 |
+
"learning_rate": 4.745e-05,
|
| 149 |
+
"loss": 0.4565,
|
| 150 |
+
"step": 950
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.675392670157068,
|
| 154 |
+
"grad_norm": 3.1588356494903564,
|
| 155 |
+
"learning_rate": 4.995e-05,
|
| 156 |
+
"loss": 0.455,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.675392670157068,
|
| 161 |
+
"eval_loss": 0.40312233567237854,
|
| 162 |
+
"eval_runtime": 256.4334,
|
| 163 |
+
"eval_samples_per_second": 33.104,
|
| 164 |
+
"eval_steps_per_second": 4.141,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.7591623036649215,
|
| 169 |
+
"grad_norm": 2.2053232192993164,
|
| 170 |
+
"learning_rate": 5.245e-05,
|
| 171 |
+
"loss": 0.4543,
|
| 172 |
+
"step": 1050
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.8429319371727748,
|
| 176 |
+
"grad_norm": 2.0562164783477783,
|
| 177 |
+
"learning_rate": 5.495e-05,
|
| 178 |
+
"loss": 0.4456,
|
| 179 |
+
"step": 1100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.9267015706806283,
|
| 183 |
+
"grad_norm": 2.730119466781616,
|
| 184 |
+
"learning_rate": 5.745e-05,
|
| 185 |
+
"loss": 0.4355,
|
| 186 |
+
"step": 1150
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0104712041884816,
|
| 190 |
+
"grad_norm": 1.7484283447265625,
|
| 191 |
+
"learning_rate": 5.995000000000001e-05,
|
| 192 |
+
"loss": 0.4299,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.094240837696335,
|
| 197 |
+
"grad_norm": 1.1786061525344849,
|
| 198 |
+
"learning_rate": 6.245000000000001e-05,
|
| 199 |
+
"loss": 0.4305,
|
| 200 |
+
"step": 1250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.1780104712041886,
|
| 204 |
+
"grad_norm": 1.98978590965271,
|
| 205 |
+
"learning_rate": 6.494999999999999e-05,
|
| 206 |
+
"loss": 0.4295,
|
| 207 |
+
"step": 1300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.261780104712042,
|
| 211 |
+
"grad_norm": 2.818659782409668,
|
| 212 |
+
"learning_rate": 6.745e-05,
|
| 213 |
+
"loss": 0.4235,
|
| 214 |
+
"step": 1350
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.345549738219895,
|
| 218 |
+
"grad_norm": 2.3864262104034424,
|
| 219 |
+
"learning_rate": 6.995e-05,
|
| 220 |
+
"loss": 0.4271,
|
| 221 |
+
"step": 1400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.4293193717277486,
|
| 225 |
+
"grad_norm": 1.3647903203964233,
|
| 226 |
+
"learning_rate": 7.245000000000001e-05,
|
| 227 |
+
"loss": 0.4208,
|
| 228 |
+
"step": 1450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.513089005235602,
|
| 232 |
+
"grad_norm": 2.2144172191619873,
|
| 233 |
+
"learning_rate": 7.495e-05,
|
| 234 |
+
"loss": 0.4175,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.513089005235602,
|
| 239 |
+
"eval_loss": 0.3777858018875122,
|
| 240 |
+
"eval_runtime": 260.5025,
|
| 241 |
+
"eval_samples_per_second": 32.587,
|
| 242 |
+
"eval_steps_per_second": 4.077,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.5968586387434556,
|
| 247 |
+
"grad_norm": 1.6483193635940552,
|
| 248 |
+
"learning_rate": 7.745e-05,
|
| 249 |
+
"loss": 0.414,
|
| 250 |
+
"step": 1550
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.680628272251309,
|
| 254 |
+
"grad_norm": 1.7688554525375366,
|
| 255 |
+
"learning_rate": 7.995e-05,
|
| 256 |
+
"loss": 0.4153,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.7643979057591626,
|
| 261 |
+
"grad_norm": 1.2314317226409912,
|
| 262 |
+
"learning_rate": 8.245e-05,
|
| 263 |
+
"loss": 0.4089,
|
| 264 |
+
"step": 1650
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.8481675392670156,
|
| 268 |
+
"grad_norm": 1.6623793840408325,
|
| 269 |
+
"learning_rate": 8.495e-05,
|
| 270 |
+
"loss": 0.4124,
|
| 271 |
+
"step": 1700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.931937172774869,
|
| 275 |
+
"grad_norm": 3.812507390975952,
|
| 276 |
+
"learning_rate": 8.745000000000001e-05,
|
| 277 |
+
"loss": 0.4112,
|
| 278 |
+
"step": 1750
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.0157068062827226,
|
| 282 |
+
"grad_norm": 2.141019821166992,
|
| 283 |
+
"learning_rate": 8.995e-05,
|
| 284 |
+
"loss": 0.4081,
|
| 285 |
+
"step": 1800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.099476439790576,
|
| 289 |
+
"grad_norm": 1.8928133249282837,
|
| 290 |
+
"learning_rate": 9.245e-05,
|
| 291 |
+
"loss": 0.4067,
|
| 292 |
+
"step": 1850
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.183246073298429,
|
| 296 |
+
"grad_norm": 2.322817087173462,
|
| 297 |
+
"learning_rate": 9.495e-05,
|
| 298 |
+
"loss": 0.4088,
|
| 299 |
+
"step": 1900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.2670157068062826,
|
| 303 |
+
"grad_norm": 2.1984918117523193,
|
| 304 |
+
"learning_rate": 9.745000000000001e-05,
|
| 305 |
+
"loss": 0.3976,
|
| 306 |
+
"step": 1950
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.350785340314136,
|
| 310 |
+
"grad_norm": 2.0455121994018555,
|
| 311 |
+
"learning_rate": 9.995e-05,
|
| 312 |
+
"loss": 0.4022,
|
| 313 |
+
"step": 2000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.350785340314136,
|
| 317 |
+
"eval_loss": 0.3677983582019806,
|
| 318 |
+
"eval_runtime": 257.3111,
|
| 319 |
+
"eval_samples_per_second": 32.991,
|
| 320 |
+
"eval_steps_per_second": 4.127,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.4345549738219896,
|
| 325 |
+
"grad_norm": 2.0729174613952637,
|
| 326 |
+
"learning_rate": 9.755000000000001e-05,
|
| 327 |
+
"loss": 0.4017,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.518324607329843,
|
| 332 |
+
"grad_norm": 1.4496002197265625,
|
| 333 |
+
"learning_rate": 9.505e-05,
|
| 334 |
+
"loss": 0.3999,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.6020942408376966,
|
| 339 |
+
"grad_norm": 1.313783884048462,
|
| 340 |
+
"learning_rate": 9.255e-05,
|
| 341 |
+
"loss": 0.3971,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.6858638743455496,
|
| 346 |
+
"grad_norm": 2.4938676357269287,
|
| 347 |
+
"learning_rate": 9.005000000000001e-05,
|
| 348 |
+
"loss": 0.3958,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.769633507853403,
|
| 353 |
+
"grad_norm": 1.6081351041793823,
|
| 354 |
+
"learning_rate": 8.755e-05,
|
| 355 |
+
"loss": 0.389,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.8534031413612566,
|
| 360 |
+
"grad_norm": 1.5322096347808838,
|
| 361 |
+
"learning_rate": 8.505000000000001e-05,
|
| 362 |
+
"loss": 0.3887,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.93717277486911,
|
| 367 |
+
"grad_norm": 2.3951408863067627,
|
| 368 |
+
"learning_rate": 8.26e-05,
|
| 369 |
+
"loss": 0.392,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.020942408376963,
|
| 374 |
+
"grad_norm": 1.0958179235458374,
|
| 375 |
+
"learning_rate": 8.010000000000001e-05,
|
| 376 |
+
"loss": 0.3846,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 4.104712041884817,
|
| 381 |
+
"grad_norm": 1.2315720319747925,
|
| 382 |
+
"learning_rate": 7.76e-05,
|
| 383 |
+
"loss": 0.3867,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.18848167539267,
|
| 388 |
+
"grad_norm": 1.3186556100845337,
|
| 389 |
+
"learning_rate": 7.510000000000001e-05,
|
| 390 |
+
"loss": 0.3848,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 4.18848167539267,
|
| 395 |
+
"eval_loss": 0.3522670865058899,
|
| 396 |
+
"eval_runtime": 269.3867,
|
| 397 |
+
"eval_samples_per_second": 31.512,
|
| 398 |
+
"eval_steps_per_second": 3.942,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.272251308900524,
|
| 403 |
+
"grad_norm": 1.6223663091659546,
|
| 404 |
+
"learning_rate": 7.26e-05,
|
| 405 |
+
"loss": 0.3868,
|
| 406 |
+
"step": 2550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 4.356020942408377,
|
| 410 |
+
"grad_norm": 1.2300375699996948,
|
| 411 |
+
"learning_rate": 7.01e-05,
|
| 412 |
+
"loss": 0.3834,
|
| 413 |
+
"step": 2600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.439790575916231,
|
| 417 |
+
"grad_norm": 1.930428147315979,
|
| 418 |
+
"learning_rate": 6.76e-05,
|
| 419 |
+
"loss": 0.3789,
|
| 420 |
+
"step": 2650
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.523560209424084,
|
| 424 |
+
"grad_norm": 1.2785884141921997,
|
| 425 |
+
"learning_rate": 6.510000000000001e-05,
|
| 426 |
+
"loss": 0.3821,
|
| 427 |
+
"step": 2700
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.607329842931938,
|
| 431 |
+
"grad_norm": 2.007714033126831,
|
| 432 |
+
"learning_rate": 6.26e-05,
|
| 433 |
+
"loss": 0.3777,
|
| 434 |
+
"step": 2750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.69109947643979,
|
| 438 |
+
"grad_norm": 1.490657925605774,
|
| 439 |
+
"learning_rate": 6.0100000000000004e-05,
|
| 440 |
+
"loss": 0.3817,
|
| 441 |
+
"step": 2800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.774869109947644,
|
| 445 |
+
"grad_norm": 1.7175956964492798,
|
| 446 |
+
"learning_rate": 5.76e-05,
|
| 447 |
+
"loss": 0.3778,
|
| 448 |
+
"step": 2850
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.858638743455497,
|
| 452 |
+
"grad_norm": 1.9603019952774048,
|
| 453 |
+
"learning_rate": 5.5100000000000004e-05,
|
| 454 |
+
"loss": 0.3787,
|
| 455 |
+
"step": 2900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.942408376963351,
|
| 459 |
+
"grad_norm": 0.9075130224227905,
|
| 460 |
+
"learning_rate": 5.2600000000000005e-05,
|
| 461 |
+
"loss": 0.3775,
|
| 462 |
+
"step": 2950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.026178010471204,
|
| 466 |
+
"grad_norm": 1.1054623126983643,
|
| 467 |
+
"learning_rate": 5.0100000000000005e-05,
|
| 468 |
+
"loss": 0.3763,
|
| 469 |
+
"step": 3000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 5.026178010471204,
|
| 473 |
+
"eval_loss": 0.34259819984436035,
|
| 474 |
+
"eval_runtime": 256.7226,
|
| 475 |
+
"eval_samples_per_second": 33.067,
|
| 476 |
+
"eval_steps_per_second": 4.137,
|
| 477 |
+
"step": 3000
|
| 478 |
+
}
|
| 479 |
+
],
|
| 480 |
+
"logging_steps": 50,
|
| 481 |
+
"max_steps": 4000,
|
| 482 |
+
"num_input_tokens_seen": 0,
|
| 483 |
+
"num_train_epochs": 7,
|
| 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": 5.37491824204009e+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 sha256:5484e04f6ef3fa6c1a7fb861e2b263b28356830486ed692cff98e0b32f9f8b6f
|
| 3 |
+
size 5304
|