Commit
•
d71a2da
1
Parent(s):
b165a12
Training in progress, step 5000, checkpoint
Browse files- checkpoint-5000/added_tokens.json +4 -0
- checkpoint-5000/config.json +92 -0
- checkpoint-5000/generation_config.json +9 -0
- checkpoint-5000/model.safetensors +3 -0
- checkpoint-5000/optimizer.pt +3 -0
- checkpoint-5000/preprocessor_config.json +19 -0
- checkpoint-5000/rng_state.pth +3 -0
- checkpoint-5000/scheduler.pt +3 -0
- checkpoint-5000/special_tokens_map.json +37 -0
- checkpoint-5000/spm_char.model +3 -0
- checkpoint-5000/tokenizer_config.json +63 -0
- checkpoint-5000/trainer_state.json +813 -0
- checkpoint-5000/training_args.bin +3 -0
checkpoint-5000/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<ctc_blank>": 80,
|
| 3 |
+
"<mask>": 79
|
| 4 |
+
}
|
checkpoint-5000/config.json
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mikhail-panzo/zlm_b64_le4_s12000",
|
| 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-5000/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-5000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4c49be80531e0db46583e0bfd73e8621b6d0f67a12fb164b948121a142819c0
|
| 3 |
+
size 577789320
|
checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2748728bddea2bdff4539ee26fd3056796315691654c6288410684e26bba52ef
|
| 3 |
+
size 1155772233
|
checkpoint-5000/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-5000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a769a29ee893a15364c187dbd6820fd927858435a68ef677af08ff8f0dc5a57
|
| 3 |
+
size 14244
|
checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1f399f45159aaef0aa148c9c877935f6e452e84ec281c50697ba784fbd8b088
|
| 3 |
+
size 1064
|
checkpoint-5000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "<mask>",
|
| 18 |
+
"lstrip": true,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "<unk>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-5000/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-5000/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-5000/trainer_state.json
ADDED
|
@@ -0,0 +1,813 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.41181260347366333,
|
| 3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm-fil_b64_le5_s8000/checkpoint-5000",
|
| 4 |
+
"epoch": 222.22222222222223,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 2.2222222222222223,
|
| 13 |
+
"grad_norm": 4.803515434265137,
|
| 14 |
+
"learning_rate": 2.5000000000000004e-07,
|
| 15 |
+
"loss": 0.8968,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 4.444444444444445,
|
| 20 |
+
"grad_norm": 2.6444506645202637,
|
| 21 |
+
"learning_rate": 5.000000000000001e-07,
|
| 22 |
+
"loss": 0.8539,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 6.666666666666667,
|
| 27 |
+
"grad_norm": 1.9820537567138672,
|
| 28 |
+
"learning_rate": 7.5e-07,
|
| 29 |
+
"loss": 0.7856,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 8.88888888888889,
|
| 34 |
+
"grad_norm": 1.2031773328781128,
|
| 35 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 36 |
+
"loss": 0.7306,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 11.11111111111111,
|
| 41 |
+
"grad_norm": 1.728398084640503,
|
| 42 |
+
"learning_rate": 1.25e-06,
|
| 43 |
+
"loss": 0.6821,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 13.333333333333334,
|
| 48 |
+
"grad_norm": 1.232366681098938,
|
| 49 |
+
"learning_rate": 1.5e-06,
|
| 50 |
+
"loss": 0.6348,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 15.555555555555555,
|
| 55 |
+
"grad_norm": 1.4039260149002075,
|
| 56 |
+
"learning_rate": 1.75e-06,
|
| 57 |
+
"loss": 0.5962,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 17.77777777777778,
|
| 62 |
+
"grad_norm": 1.1848849058151245,
|
| 63 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 64 |
+
"loss": 0.5758,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 20.0,
|
| 69 |
+
"grad_norm": 0.9365352392196655,
|
| 70 |
+
"learning_rate": 2.25e-06,
|
| 71 |
+
"loss": 0.5636,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 22.22222222222222,
|
| 76 |
+
"grad_norm": 0.9893051981925964,
|
| 77 |
+
"learning_rate": 2.5e-06,
|
| 78 |
+
"loss": 0.5529,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 22.22222222222222,
|
| 83 |
+
"eval_loss": 0.4999743402004242,
|
| 84 |
+
"eval_runtime": 6.8701,
|
| 85 |
+
"eval_samples_per_second": 23.144,
|
| 86 |
+
"eval_steps_per_second": 2.911,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 24.444444444444443,
|
| 91 |
+
"grad_norm": 0.7535696029663086,
|
| 92 |
+
"learning_rate": 2.7500000000000004e-06,
|
| 93 |
+
"loss": 0.5476,
|
| 94 |
+
"step": 550
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 26.666666666666668,
|
| 98 |
+
"grad_norm": 0.7487667202949524,
|
| 99 |
+
"learning_rate": 3e-06,
|
| 100 |
+
"loss": 0.536,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 28.88888888888889,
|
| 105 |
+
"grad_norm": 0.9480589628219604,
|
| 106 |
+
"learning_rate": 3.2500000000000002e-06,
|
| 107 |
+
"loss": 0.5271,
|
| 108 |
+
"step": 650
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 31.11111111111111,
|
| 112 |
+
"grad_norm": 1.0027987957000732,
|
| 113 |
+
"learning_rate": 3.5e-06,
|
| 114 |
+
"loss": 0.5202,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 33.333333333333336,
|
| 119 |
+
"grad_norm": 0.7353075742721558,
|
| 120 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 121 |
+
"loss": 0.5128,
|
| 122 |
+
"step": 750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 35.55555555555556,
|
| 126 |
+
"grad_norm": 1.2223567962646484,
|
| 127 |
+
"learning_rate": 4.000000000000001e-06,
|
| 128 |
+
"loss": 0.5159,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 37.77777777777778,
|
| 133 |
+
"grad_norm": 0.835096001625061,
|
| 134 |
+
"learning_rate": 4.25e-06,
|
| 135 |
+
"loss": 0.5051,
|
| 136 |
+
"step": 850
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 40.0,
|
| 140 |
+
"grad_norm": 0.8878389000892639,
|
| 141 |
+
"learning_rate": 4.5e-06,
|
| 142 |
+
"loss": 0.5044,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 42.22222222222222,
|
| 147 |
+
"grad_norm": 0.8464574813842773,
|
| 148 |
+
"learning_rate": 4.75e-06,
|
| 149 |
+
"loss": 0.4984,
|
| 150 |
+
"step": 950
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 44.44444444444444,
|
| 154 |
+
"grad_norm": 0.8119956254959106,
|
| 155 |
+
"learning_rate": 5e-06,
|
| 156 |
+
"loss": 0.4974,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 44.44444444444444,
|
| 161 |
+
"eval_loss": 0.4557439386844635,
|
| 162 |
+
"eval_runtime": 6.6345,
|
| 163 |
+
"eval_samples_per_second": 23.965,
|
| 164 |
+
"eval_steps_per_second": 3.015,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 46.666666666666664,
|
| 169 |
+
"grad_norm": 1.2427846193313599,
|
| 170 |
+
"learning_rate": 5.2500000000000006e-06,
|
| 171 |
+
"loss": 0.4943,
|
| 172 |
+
"step": 1050
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 48.888888888888886,
|
| 176 |
+
"grad_norm": 0.9691639542579651,
|
| 177 |
+
"learning_rate": 5.500000000000001e-06,
|
| 178 |
+
"loss": 0.4879,
|
| 179 |
+
"step": 1100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 51.111111111111114,
|
| 183 |
+
"grad_norm": 0.815934419631958,
|
| 184 |
+
"learning_rate": 5.75e-06,
|
| 185 |
+
"loss": 0.4825,
|
| 186 |
+
"step": 1150
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 53.333333333333336,
|
| 190 |
+
"grad_norm": 1.090553641319275,
|
| 191 |
+
"learning_rate": 6e-06,
|
| 192 |
+
"loss": 0.4875,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 55.55555555555556,
|
| 197 |
+
"grad_norm": 1.090770959854126,
|
| 198 |
+
"learning_rate": 6.25e-06,
|
| 199 |
+
"loss": 0.4821,
|
| 200 |
+
"step": 1250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 57.77777777777778,
|
| 204 |
+
"grad_norm": 1.2514219284057617,
|
| 205 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 206 |
+
"loss": 0.4752,
|
| 207 |
+
"step": 1300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 60.0,
|
| 211 |
+
"grad_norm": 1.0580047369003296,
|
| 212 |
+
"learning_rate": 6.750000000000001e-06,
|
| 213 |
+
"loss": 0.4749,
|
| 214 |
+
"step": 1350
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 62.22222222222222,
|
| 218 |
+
"grad_norm": 1.2864220142364502,
|
| 219 |
+
"learning_rate": 7e-06,
|
| 220 |
+
"loss": 0.4727,
|
| 221 |
+
"step": 1400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 64.44444444444444,
|
| 225 |
+
"grad_norm": 1.0031774044036865,
|
| 226 |
+
"learning_rate": 7.25e-06,
|
| 227 |
+
"loss": 0.4706,
|
| 228 |
+
"step": 1450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 66.66666666666667,
|
| 232 |
+
"grad_norm": 0.7133861184120178,
|
| 233 |
+
"learning_rate": 7.500000000000001e-06,
|
| 234 |
+
"loss": 0.4716,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 66.66666666666667,
|
| 239 |
+
"eval_loss": 0.43592509627342224,
|
| 240 |
+
"eval_runtime": 6.6514,
|
| 241 |
+
"eval_samples_per_second": 23.905,
|
| 242 |
+
"eval_steps_per_second": 3.007,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 68.88888888888889,
|
| 247 |
+
"grad_norm": 0.8695252537727356,
|
| 248 |
+
"learning_rate": 7.75e-06,
|
| 249 |
+
"loss": 0.464,
|
| 250 |
+
"step": 1550
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 71.11111111111111,
|
| 254 |
+
"grad_norm": 2.2705039978027344,
|
| 255 |
+
"learning_rate": 8.000000000000001e-06,
|
| 256 |
+
"loss": 0.4677,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 73.33333333333333,
|
| 261 |
+
"grad_norm": 0.8814280033111572,
|
| 262 |
+
"learning_rate": 8.25e-06,
|
| 263 |
+
"loss": 0.4628,
|
| 264 |
+
"step": 1650
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 75.55555555555556,
|
| 268 |
+
"grad_norm": 0.6686401963233948,
|
| 269 |
+
"learning_rate": 8.5e-06,
|
| 270 |
+
"loss": 0.4642,
|
| 271 |
+
"step": 1700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 77.77777777777777,
|
| 275 |
+
"grad_norm": 1.1037653684616089,
|
| 276 |
+
"learning_rate": 8.750000000000001e-06,
|
| 277 |
+
"loss": 0.4582,
|
| 278 |
+
"step": 1750
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 80.0,
|
| 282 |
+
"grad_norm": 1.0339733362197876,
|
| 283 |
+
"learning_rate": 9e-06,
|
| 284 |
+
"loss": 0.4595,
|
| 285 |
+
"step": 1800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 82.22222222222223,
|
| 289 |
+
"grad_norm": 0.715323269367218,
|
| 290 |
+
"learning_rate": 9.250000000000001e-06,
|
| 291 |
+
"loss": 0.4621,
|
| 292 |
+
"step": 1850
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 84.44444444444444,
|
| 296 |
+
"grad_norm": 0.872926652431488,
|
| 297 |
+
"learning_rate": 9.5e-06,
|
| 298 |
+
"loss": 0.4553,
|
| 299 |
+
"step": 1900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 86.66666666666667,
|
| 303 |
+
"grad_norm": 0.8996181488037109,
|
| 304 |
+
"learning_rate": 9.75e-06,
|
| 305 |
+
"loss": 0.4528,
|
| 306 |
+
"step": 1950
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 88.88888888888889,
|
| 310 |
+
"grad_norm": 1.3289371728897095,
|
| 311 |
+
"learning_rate": 1e-05,
|
| 312 |
+
"loss": 0.453,
|
| 313 |
+
"step": 2000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 88.88888888888889,
|
| 317 |
+
"eval_loss": 0.4245700240135193,
|
| 318 |
+
"eval_runtime": 6.6886,
|
| 319 |
+
"eval_samples_per_second": 23.772,
|
| 320 |
+
"eval_steps_per_second": 2.99,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 91.11111111111111,
|
| 325 |
+
"grad_norm": 0.9035242795944214,
|
| 326 |
+
"learning_rate": 9.916666666666668e-06,
|
| 327 |
+
"loss": 0.4504,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 93.33333333333333,
|
| 332 |
+
"grad_norm": 1.091410756111145,
|
| 333 |
+
"learning_rate": 9.833333333333333e-06,
|
| 334 |
+
"loss": 0.4528,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 95.55555555555556,
|
| 339 |
+
"grad_norm": 0.7232839465141296,
|
| 340 |
+
"learning_rate": 9.75e-06,
|
| 341 |
+
"loss": 0.4481,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 97.77777777777777,
|
| 346 |
+
"grad_norm": 0.9006613492965698,
|
| 347 |
+
"learning_rate": 9.666666666666667e-06,
|
| 348 |
+
"loss": 0.444,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 100.0,
|
| 353 |
+
"grad_norm": 0.9088640809059143,
|
| 354 |
+
"learning_rate": 9.583333333333335e-06,
|
| 355 |
+
"loss": 0.4445,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 102.22222222222223,
|
| 360 |
+
"grad_norm": 1.2409088611602783,
|
| 361 |
+
"learning_rate": 9.5e-06,
|
| 362 |
+
"loss": 0.4457,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 104.44444444444444,
|
| 367 |
+
"grad_norm": 0.749260663986206,
|
| 368 |
+
"learning_rate": 9.416666666666667e-06,
|
| 369 |
+
"loss": 0.4453,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 106.66666666666667,
|
| 374 |
+
"grad_norm": 0.7552911639213562,
|
| 375 |
+
"learning_rate": 9.333333333333334e-06,
|
| 376 |
+
"loss": 0.4402,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 108.88888888888889,
|
| 381 |
+
"grad_norm": 1.0751075744628906,
|
| 382 |
+
"learning_rate": 9.250000000000001e-06,
|
| 383 |
+
"loss": 0.4417,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 111.11111111111111,
|
| 388 |
+
"grad_norm": 0.8774231672286987,
|
| 389 |
+
"learning_rate": 9.166666666666666e-06,
|
| 390 |
+
"loss": 0.4428,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 111.11111111111111,
|
| 395 |
+
"eval_loss": 0.41958874464035034,
|
| 396 |
+
"eval_runtime": 6.7008,
|
| 397 |
+
"eval_samples_per_second": 23.728,
|
| 398 |
+
"eval_steps_per_second": 2.985,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 113.33333333333333,
|
| 403 |
+
"grad_norm": 1.3239281177520752,
|
| 404 |
+
"learning_rate": 9.083333333333333e-06,
|
| 405 |
+
"loss": 0.4399,
|
| 406 |
+
"step": 2550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 115.55555555555556,
|
| 410 |
+
"grad_norm": 0.9855658411979675,
|
| 411 |
+
"learning_rate": 9e-06,
|
| 412 |
+
"loss": 0.4376,
|
| 413 |
+
"step": 2600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 117.77777777777777,
|
| 417 |
+
"grad_norm": 0.9498355984687805,
|
| 418 |
+
"learning_rate": 8.916666666666667e-06,
|
| 419 |
+
"loss": 0.4427,
|
| 420 |
+
"step": 2650
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 120.0,
|
| 424 |
+
"grad_norm": 1.3080662488937378,
|
| 425 |
+
"learning_rate": 8.833333333333334e-06,
|
| 426 |
+
"loss": 0.437,
|
| 427 |
+
"step": 2700
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 122.22222222222223,
|
| 431 |
+
"grad_norm": 0.6745712757110596,
|
| 432 |
+
"learning_rate": 8.750000000000001e-06,
|
| 433 |
+
"loss": 0.4405,
|
| 434 |
+
"step": 2750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 124.44444444444444,
|
| 438 |
+
"grad_norm": 1.136643409729004,
|
| 439 |
+
"learning_rate": 8.666666666666668e-06,
|
| 440 |
+
"loss": 0.4329,
|
| 441 |
+
"step": 2800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 126.66666666666667,
|
| 445 |
+
"grad_norm": 0.8538027405738831,
|
| 446 |
+
"learning_rate": 8.583333333333333e-06,
|
| 447 |
+
"loss": 0.4313,
|
| 448 |
+
"step": 2850
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 128.88888888888889,
|
| 452 |
+
"grad_norm": 0.8776795268058777,
|
| 453 |
+
"learning_rate": 8.5e-06,
|
| 454 |
+
"loss": 0.43,
|
| 455 |
+
"step": 2900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 131.11111111111111,
|
| 459 |
+
"grad_norm": 0.987410306930542,
|
| 460 |
+
"learning_rate": 8.416666666666667e-06,
|
| 461 |
+
"loss": 0.4346,
|
| 462 |
+
"step": 2950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 133.33333333333334,
|
| 466 |
+
"grad_norm": 1.061345100402832,
|
| 467 |
+
"learning_rate": 8.333333333333334e-06,
|
| 468 |
+
"loss": 0.4332,
|
| 469 |
+
"step": 3000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 133.33333333333334,
|
| 473 |
+
"eval_loss": 0.4170692563056946,
|
| 474 |
+
"eval_runtime": 6.8806,
|
| 475 |
+
"eval_samples_per_second": 23.108,
|
| 476 |
+
"eval_steps_per_second": 2.907,
|
| 477 |
+
"step": 3000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 135.55555555555554,
|
| 481 |
+
"grad_norm": 0.9580554962158203,
|
| 482 |
+
"learning_rate": 8.25e-06,
|
| 483 |
+
"loss": 0.4344,
|
| 484 |
+
"step": 3050
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 137.77777777777777,
|
| 488 |
+
"grad_norm": 0.8951635956764221,
|
| 489 |
+
"learning_rate": 8.166666666666668e-06,
|
| 490 |
+
"loss": 0.4303,
|
| 491 |
+
"step": 3100
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 140.0,
|
| 495 |
+
"grad_norm": 1.0797936916351318,
|
| 496 |
+
"learning_rate": 8.083333333333334e-06,
|
| 497 |
+
"loss": 0.4331,
|
| 498 |
+
"step": 3150
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 142.22222222222223,
|
| 502 |
+
"grad_norm": 1.1288533210754395,
|
| 503 |
+
"learning_rate": 8.000000000000001e-06,
|
| 504 |
+
"loss": 0.425,
|
| 505 |
+
"step": 3200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 144.44444444444446,
|
| 509 |
+
"grad_norm": 0.9219405055046082,
|
| 510 |
+
"learning_rate": 7.916666666666667e-06,
|
| 511 |
+
"loss": 0.4335,
|
| 512 |
+
"step": 3250
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 146.66666666666666,
|
| 516 |
+
"grad_norm": 0.8145209550857544,
|
| 517 |
+
"learning_rate": 7.833333333333333e-06,
|
| 518 |
+
"loss": 0.4249,
|
| 519 |
+
"step": 3300
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 148.88888888888889,
|
| 523 |
+
"grad_norm": 0.7597942352294922,
|
| 524 |
+
"learning_rate": 7.75e-06,
|
| 525 |
+
"loss": 0.4284,
|
| 526 |
+
"step": 3350
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 151.11111111111111,
|
| 530 |
+
"grad_norm": 1.0502862930297852,
|
| 531 |
+
"learning_rate": 7.666666666666667e-06,
|
| 532 |
+
"loss": 0.4285,
|
| 533 |
+
"step": 3400
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 153.33333333333334,
|
| 537 |
+
"grad_norm": 0.9932737350463867,
|
| 538 |
+
"learning_rate": 7.583333333333333e-06,
|
| 539 |
+
"loss": 0.4263,
|
| 540 |
+
"step": 3450
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 155.55555555555554,
|
| 544 |
+
"grad_norm": 0.9701213836669922,
|
| 545 |
+
"learning_rate": 7.500000000000001e-06,
|
| 546 |
+
"loss": 0.4246,
|
| 547 |
+
"step": 3500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 155.55555555555554,
|
| 551 |
+
"eval_loss": 0.41539278626441956,
|
| 552 |
+
"eval_runtime": 6.9499,
|
| 553 |
+
"eval_samples_per_second": 22.878,
|
| 554 |
+
"eval_steps_per_second": 2.878,
|
| 555 |
+
"step": 3500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 157.77777777777777,
|
| 559 |
+
"grad_norm": 1.0768437385559082,
|
| 560 |
+
"learning_rate": 7.416666666666668e-06,
|
| 561 |
+
"loss": 0.4252,
|
| 562 |
+
"step": 3550
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 160.0,
|
| 566 |
+
"grad_norm": 0.7991815805435181,
|
| 567 |
+
"learning_rate": 7.333333333333333e-06,
|
| 568 |
+
"loss": 0.4219,
|
| 569 |
+
"step": 3600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 162.22222222222223,
|
| 573 |
+
"grad_norm": 1.1402180194854736,
|
| 574 |
+
"learning_rate": 7.25e-06,
|
| 575 |
+
"loss": 0.4247,
|
| 576 |
+
"step": 3650
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 164.44444444444446,
|
| 580 |
+
"grad_norm": 0.8970450758934021,
|
| 581 |
+
"learning_rate": 7.166666666666667e-06,
|
| 582 |
+
"loss": 0.4252,
|
| 583 |
+
"step": 3700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 166.66666666666666,
|
| 587 |
+
"grad_norm": 0.733568549156189,
|
| 588 |
+
"learning_rate": 7.083333333333335e-06,
|
| 589 |
+
"loss": 0.4238,
|
| 590 |
+
"step": 3750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 168.88888888888889,
|
| 594 |
+
"grad_norm": 1.1045589447021484,
|
| 595 |
+
"learning_rate": 7e-06,
|
| 596 |
+
"loss": 0.4275,
|
| 597 |
+
"step": 3800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 171.11111111111111,
|
| 601 |
+
"grad_norm": 1.0485199689865112,
|
| 602 |
+
"learning_rate": 6.916666666666667e-06,
|
| 603 |
+
"loss": 0.4295,
|
| 604 |
+
"step": 3850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 173.33333333333334,
|
| 608 |
+
"grad_norm": 0.9441601634025574,
|
| 609 |
+
"learning_rate": 6.833333333333334e-06,
|
| 610 |
+
"loss": 0.4206,
|
| 611 |
+
"step": 3900
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 175.55555555555554,
|
| 615 |
+
"grad_norm": 0.7985955476760864,
|
| 616 |
+
"learning_rate": 6.750000000000001e-06,
|
| 617 |
+
"loss": 0.4263,
|
| 618 |
+
"step": 3950
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 177.77777777777777,
|
| 622 |
+
"grad_norm": 0.6838188171386719,
|
| 623 |
+
"learning_rate": 6.666666666666667e-06,
|
| 624 |
+
"loss": 0.4202,
|
| 625 |
+
"step": 4000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 177.77777777777777,
|
| 629 |
+
"eval_loss": 0.41334837675094604,
|
| 630 |
+
"eval_runtime": 6.7658,
|
| 631 |
+
"eval_samples_per_second": 23.5,
|
| 632 |
+
"eval_steps_per_second": 2.956,
|
| 633 |
+
"step": 4000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 180.0,
|
| 637 |
+
"grad_norm": 1.0729726552963257,
|
| 638 |
+
"learning_rate": 6.5833333333333335e-06,
|
| 639 |
+
"loss": 0.4218,
|
| 640 |
+
"step": 4050
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 182.22222222222223,
|
| 644 |
+
"grad_norm": 0.8395955562591553,
|
| 645 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 646 |
+
"loss": 0.4172,
|
| 647 |
+
"step": 4100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 184.44444444444446,
|
| 651 |
+
"grad_norm": 0.7987414002418518,
|
| 652 |
+
"learning_rate": 6.416666666666667e-06,
|
| 653 |
+
"loss": 0.4222,
|
| 654 |
+
"step": 4150
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 186.66666666666666,
|
| 658 |
+
"grad_norm": 0.7480828762054443,
|
| 659 |
+
"learning_rate": 6.333333333333333e-06,
|
| 660 |
+
"loss": 0.4178,
|
| 661 |
+
"step": 4200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 188.88888888888889,
|
| 665 |
+
"grad_norm": 1.003481149673462,
|
| 666 |
+
"learning_rate": 6.25e-06,
|
| 667 |
+
"loss": 0.4183,
|
| 668 |
+
"step": 4250
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 191.11111111111111,
|
| 672 |
+
"grad_norm": 1.080949306488037,
|
| 673 |
+
"learning_rate": 6.168333333333334e-06,
|
| 674 |
+
"loss": 0.4207,
|
| 675 |
+
"step": 4300
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 193.33333333333334,
|
| 679 |
+
"grad_norm": 1.0521224737167358,
|
| 680 |
+
"learning_rate": 6.085000000000001e-06,
|
| 681 |
+
"loss": 0.4186,
|
| 682 |
+
"step": 4350
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 195.55555555555554,
|
| 686 |
+
"grad_norm": 0.9048583507537842,
|
| 687 |
+
"learning_rate": 6.001666666666667e-06,
|
| 688 |
+
"loss": 0.418,
|
| 689 |
+
"step": 4400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 197.77777777777777,
|
| 693 |
+
"grad_norm": 1.4653879404067993,
|
| 694 |
+
"learning_rate": 5.918333333333334e-06,
|
| 695 |
+
"loss": 0.414,
|
| 696 |
+
"step": 4450
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 200.0,
|
| 700 |
+
"grad_norm": 1.5214589834213257,
|
| 701 |
+
"learning_rate": 5.835000000000001e-06,
|
| 702 |
+
"loss": 0.4223,
|
| 703 |
+
"step": 4500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 200.0,
|
| 707 |
+
"eval_loss": 0.41453027725219727,
|
| 708 |
+
"eval_runtime": 6.6498,
|
| 709 |
+
"eval_samples_per_second": 23.91,
|
| 710 |
+
"eval_steps_per_second": 3.008,
|
| 711 |
+
"step": 4500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 202.22222222222223,
|
| 715 |
+
"grad_norm": 1.1058125495910645,
|
| 716 |
+
"learning_rate": 5.751666666666668e-06,
|
| 717 |
+
"loss": 0.4164,
|
| 718 |
+
"step": 4550
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 204.44444444444446,
|
| 722 |
+
"grad_norm": 0.8250144124031067,
|
| 723 |
+
"learning_rate": 5.668333333333334e-06,
|
| 724 |
+
"loss": 0.418,
|
| 725 |
+
"step": 4600
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 206.66666666666666,
|
| 729 |
+
"grad_norm": 0.710696816444397,
|
| 730 |
+
"learning_rate": 5.585000000000001e-06,
|
| 731 |
+
"loss": 0.4195,
|
| 732 |
+
"step": 4650
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 208.88888888888889,
|
| 736 |
+
"grad_norm": 0.8722075819969177,
|
| 737 |
+
"learning_rate": 5.501666666666668e-06,
|
| 738 |
+
"loss": 0.4127,
|
| 739 |
+
"step": 4700
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 211.11111111111111,
|
| 743 |
+
"grad_norm": 1.548494815826416,
|
| 744 |
+
"learning_rate": 5.418333333333333e-06,
|
| 745 |
+
"loss": 0.4175,
|
| 746 |
+
"step": 4750
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 213.33333333333334,
|
| 750 |
+
"grad_norm": 1.0577216148376465,
|
| 751 |
+
"learning_rate": 5.335000000000001e-06,
|
| 752 |
+
"loss": 0.4142,
|
| 753 |
+
"step": 4800
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 215.55555555555554,
|
| 757 |
+
"grad_norm": 0.8775042295455933,
|
| 758 |
+
"learning_rate": 5.2516666666666675e-06,
|
| 759 |
+
"loss": 0.4185,
|
| 760 |
+
"step": 4850
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 217.77777777777777,
|
| 764 |
+
"grad_norm": 0.8470151424407959,
|
| 765 |
+
"learning_rate": 5.168333333333334e-06,
|
| 766 |
+
"loss": 0.4107,
|
| 767 |
+
"step": 4900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 220.0,
|
| 771 |
+
"grad_norm": 0.9309485554695129,
|
| 772 |
+
"learning_rate": 5.085e-06,
|
| 773 |
+
"loss": 0.4138,
|
| 774 |
+
"step": 4950
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 222.22222222222223,
|
| 778 |
+
"grad_norm": 0.7797917127609253,
|
| 779 |
+
"learning_rate": 5.0016666666666665e-06,
|
| 780 |
+
"loss": 0.4127,
|
| 781 |
+
"step": 5000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 222.22222222222223,
|
| 785 |
+
"eval_loss": 0.41181260347366333,
|
| 786 |
+
"eval_runtime": 6.6484,
|
| 787 |
+
"eval_samples_per_second": 23.915,
|
| 788 |
+
"eval_steps_per_second": 3.008,
|
| 789 |
+
"step": 5000
|
| 790 |
+
}
|
| 791 |
+
],
|
| 792 |
+
"logging_steps": 50,
|
| 793 |
+
"max_steps": 8000,
|
| 794 |
+
"num_input_tokens_seen": 0,
|
| 795 |
+
"num_train_epochs": 364,
|
| 796 |
+
"save_steps": 500,
|
| 797 |
+
"stateful_callbacks": {
|
| 798 |
+
"TrainerControl": {
|
| 799 |
+
"args": {
|
| 800 |
+
"should_epoch_stop": false,
|
| 801 |
+
"should_evaluate": false,
|
| 802 |
+
"should_log": false,
|
| 803 |
+
"should_save": true,
|
| 804 |
+
"should_training_stop": false
|
| 805 |
+
},
|
| 806 |
+
"attributes": {}
|
| 807 |
+
}
|
| 808 |
+
},
|
| 809 |
+
"total_flos": 7.276831512578496e+16,
|
| 810 |
+
"train_batch_size": 32,
|
| 811 |
+
"trial_name": null,
|
| 812 |
+
"trial_params": null
|
| 813 |
+
}
|
checkpoint-5000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4496fb86a719121d50f59f5a3033b349102dc8db9bac2fc6b307af92943070
|
| 3 |
+
size 5304
|