Commit
•
c28d10d
1
Parent(s):
3c87e71
Training in progress, step 4500, checkpoint
Browse files- checkpoint-4500/added_tokens.json +4 -0
- checkpoint-4500/config.json +92 -0
- checkpoint-4500/generation_config.json +9 -0
- checkpoint-4500/model.safetensors +3 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/preprocessor_config.json +19 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/special_tokens_map.json +13 -0
- checkpoint-4500/spm_char.model +3 -0
- checkpoint-4500/tokenizer_config.json +63 -0
- checkpoint-4500/trainer_state.json +735 -0
- checkpoint-4500/training_args.bin +3 -0
checkpoint-4500/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<ctc_blank>": 80,
|
| 3 |
+
"<mask>": 79
|
| 4 |
+
}
|
checkpoint-4500/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-4500/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-4500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f946bd01422a42efa5194ed8f68e76e3494e4e197a87c8b935b83c6d3b2051d
|
| 3 |
+
size 577789320
|
checkpoint-4500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1a76ffb03498e73833b63cd7a84d953f2d788ad7547eba5f48aec4505f9bd4
|
| 3 |
+
size 1155772233
|
checkpoint-4500/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-4500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb05267d439977ba7e4a053d0733c84510f12022320fa616f6071f86a71e5d3d
|
| 3 |
+
size 14244
|
checkpoint-4500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55e761ace71e708231c882aafdc2ffced90c8c4f8a4366b7878a4977f8e03ec8
|
| 3 |
+
size 1064
|
checkpoint-4500/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-4500/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-4500/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-4500/trainer_state.json
ADDED
|
@@ -0,0 +1,735 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3783535957336426,
|
| 3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le5_s12000/checkpoint-4500",
|
| 4 |
+
"epoch": 7.542198952879581,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4500,
|
| 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": 6.650441646575928,
|
| 14 |
+
"learning_rate": 2.4500000000000004e-07,
|
| 15 |
+
"loss": 1.1088,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16753926701570682,
|
| 20 |
+
"grad_norm": 13.608625411987305,
|
| 21 |
+
"learning_rate": 4.95e-07,
|
| 22 |
+
"loss": 1.1077,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2513089005235602,
|
| 27 |
+
"grad_norm": 2.7265217304229736,
|
| 28 |
+
"learning_rate": 7.450000000000001e-07,
|
| 29 |
+
"loss": 0.9759,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33507853403141363,
|
| 34 |
+
"grad_norm": 5.083759307861328,
|
| 35 |
+
"learning_rate": 9.950000000000002e-07,
|
| 36 |
+
"loss": 0.8705,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.418848167539267,
|
| 41 |
+
"grad_norm": 1.8121678829193115,
|
| 42 |
+
"learning_rate": 1.2450000000000002e-06,
|
| 43 |
+
"loss": 0.8185,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5026178010471204,
|
| 48 |
+
"grad_norm": 2.275899648666382,
|
| 49 |
+
"learning_rate": 1.495e-06,
|
| 50 |
+
"loss": 0.784,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5863874345549738,
|
| 55 |
+
"grad_norm": 2.2861170768737793,
|
| 56 |
+
"learning_rate": 1.745e-06,
|
| 57 |
+
"loss": 0.7545,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6701570680628273,
|
| 62 |
+
"grad_norm": 3.1991238594055176,
|
| 63 |
+
"learning_rate": 1.9950000000000004e-06,
|
| 64 |
+
"loss": 0.7227,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7539267015706806,
|
| 69 |
+
"grad_norm": 1.843092679977417,
|
| 70 |
+
"learning_rate": 2.245e-06,
|
| 71 |
+
"loss": 0.6829,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.837696335078534,
|
| 76 |
+
"grad_norm": 1.4700403213500977,
|
| 77 |
+
"learning_rate": 2.4950000000000003e-06,
|
| 78 |
+
"loss": 0.6644,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.837696335078534,
|
| 83 |
+
"eval_loss": 0.5727962851524353,
|
| 84 |
+
"eval_runtime": 293.5061,
|
| 85 |
+
"eval_samples_per_second": 28.923,
|
| 86 |
+
"eval_steps_per_second": 3.618,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.9214659685863874,
|
| 91 |
+
"grad_norm": 1.4362367391586304,
|
| 92 |
+
"learning_rate": 2.7450000000000004e-06,
|
| 93 |
+
"loss": 0.6487,
|
| 94 |
+
"step": 550
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.0052356020942408,
|
| 98 |
+
"grad_norm": 1.8555901050567627,
|
| 99 |
+
"learning_rate": 2.995e-06,
|
| 100 |
+
"loss": 0.6301,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.0890052356020943,
|
| 105 |
+
"grad_norm": 1.9496757984161377,
|
| 106 |
+
"learning_rate": 3.2450000000000003e-06,
|
| 107 |
+
"loss": 0.6237,
|
| 108 |
+
"step": 650
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.1727748691099475,
|
| 112 |
+
"grad_norm": 3.0705084800720215,
|
| 113 |
+
"learning_rate": 3.495e-06,
|
| 114 |
+
"loss": 0.6156,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.256544502617801,
|
| 119 |
+
"grad_norm": 2.2215688228607178,
|
| 120 |
+
"learning_rate": 3.745e-06,
|
| 121 |
+
"loss": 0.5945,
|
| 122 |
+
"step": 750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.3403141361256545,
|
| 126 |
+
"grad_norm": 2.021375894546509,
|
| 127 |
+
"learning_rate": 3.995000000000001e-06,
|
| 128 |
+
"loss": 0.5891,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.4240837696335078,
|
| 133 |
+
"grad_norm": 2.0354769229888916,
|
| 134 |
+
"learning_rate": 4.245e-06,
|
| 135 |
+
"loss": 0.5781,
|
| 136 |
+
"step": 850
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.5078534031413613,
|
| 140 |
+
"grad_norm": 1.8674426078796387,
|
| 141 |
+
"learning_rate": 4.495e-06,
|
| 142 |
+
"loss": 0.5677,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.5916230366492146,
|
| 147 |
+
"grad_norm": 2.9264817237854004,
|
| 148 |
+
"learning_rate": 4.745e-06,
|
| 149 |
+
"loss": 0.5576,
|
| 150 |
+
"step": 950
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.675392670157068,
|
| 154 |
+
"grad_norm": 1.9513416290283203,
|
| 155 |
+
"learning_rate": 4.9950000000000005e-06,
|
| 156 |
+
"loss": 0.5594,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.675392670157068,
|
| 161 |
+
"eval_loss": 0.48248979449272156,
|
| 162 |
+
"eval_runtime": 294.2627,
|
| 163 |
+
"eval_samples_per_second": 28.848,
|
| 164 |
+
"eval_steps_per_second": 3.609,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.7591623036649215,
|
| 169 |
+
"grad_norm": 1.934941291809082,
|
| 170 |
+
"learning_rate": 5.245e-06,
|
| 171 |
+
"loss": 0.5571,
|
| 172 |
+
"step": 1050
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.8429319371727748,
|
| 176 |
+
"grad_norm": 1.7669196128845215,
|
| 177 |
+
"learning_rate": 5.495000000000001e-06,
|
| 178 |
+
"loss": 0.5477,
|
| 179 |
+
"step": 1100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.9267015706806283,
|
| 183 |
+
"grad_norm": 3.954806089401245,
|
| 184 |
+
"learning_rate": 5.745000000000001e-06,
|
| 185 |
+
"loss": 0.5294,
|
| 186 |
+
"step": 1150
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0104712041884816,
|
| 190 |
+
"grad_norm": 2.8323569297790527,
|
| 191 |
+
"learning_rate": 5.995000000000001e-06,
|
| 192 |
+
"loss": 0.5261,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.094240837696335,
|
| 197 |
+
"grad_norm": 2.193530797958374,
|
| 198 |
+
"learning_rate": 6.245000000000001e-06,
|
| 199 |
+
"loss": 0.5262,
|
| 200 |
+
"step": 1250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.1780104712041886,
|
| 204 |
+
"grad_norm": 1.5814998149871826,
|
| 205 |
+
"learning_rate": 6.4950000000000005e-06,
|
| 206 |
+
"loss": 0.5204,
|
| 207 |
+
"step": 1300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.261780104712042,
|
| 211 |
+
"grad_norm": 5.6610918045043945,
|
| 212 |
+
"learning_rate": 6.745000000000001e-06,
|
| 213 |
+
"loss": 0.5157,
|
| 214 |
+
"step": 1350
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.345549738219895,
|
| 218 |
+
"grad_norm": 9.156899452209473,
|
| 219 |
+
"learning_rate": 6.995000000000001e-06,
|
| 220 |
+
"loss": 0.5178,
|
| 221 |
+
"step": 1400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.4293193717277486,
|
| 225 |
+
"grad_norm": 2.3170149326324463,
|
| 226 |
+
"learning_rate": 7.245000000000001e-06,
|
| 227 |
+
"loss": 0.5163,
|
| 228 |
+
"step": 1450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.513089005235602,
|
| 232 |
+
"grad_norm": 2.1565325260162354,
|
| 233 |
+
"learning_rate": 7.495000000000001e-06,
|
| 234 |
+
"loss": 0.5042,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.513089005235602,
|
| 239 |
+
"eval_loss": 0.4464746415615082,
|
| 240 |
+
"eval_runtime": 293.8295,
|
| 241 |
+
"eval_samples_per_second": 28.891,
|
| 242 |
+
"eval_steps_per_second": 3.614,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.5997905759162303,
|
| 247 |
+
"grad_norm": 2.4758172035217285,
|
| 248 |
+
"learning_rate": 7.745e-06,
|
| 249 |
+
"loss": 0.5031,
|
| 250 |
+
"step": 1550
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.683560209424084,
|
| 254 |
+
"grad_norm": 2.1877381801605225,
|
| 255 |
+
"learning_rate": 7.990000000000001e-06,
|
| 256 |
+
"loss": 0.4994,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.7673298429319373,
|
| 261 |
+
"grad_norm": 2.4486210346221924,
|
| 262 |
+
"learning_rate": 8.24e-06,
|
| 263 |
+
"loss": 0.4965,
|
| 264 |
+
"step": 1650
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.8510994764397903,
|
| 268 |
+
"grad_norm": 2.596200704574585,
|
| 269 |
+
"learning_rate": 8.49e-06,
|
| 270 |
+
"loss": 0.4988,
|
| 271 |
+
"step": 1700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.934869109947644,
|
| 275 |
+
"grad_norm": 1.7787096500396729,
|
| 276 |
+
"learning_rate": 8.740000000000001e-06,
|
| 277 |
+
"loss": 0.4947,
|
| 278 |
+
"step": 1750
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.0186387434554973,
|
| 282 |
+
"grad_norm": 2.09403133392334,
|
| 283 |
+
"learning_rate": 8.99e-06,
|
| 284 |
+
"loss": 0.4845,
|
| 285 |
+
"step": 1800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.102408376963351,
|
| 289 |
+
"grad_norm": 2.0056636333465576,
|
| 290 |
+
"learning_rate": 9.240000000000001e-06,
|
| 291 |
+
"loss": 0.4833,
|
| 292 |
+
"step": 1850
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.1861780104712043,
|
| 296 |
+
"grad_norm": 3.200199842453003,
|
| 297 |
+
"learning_rate": 9.49e-06,
|
| 298 |
+
"loss": 0.484,
|
| 299 |
+
"step": 1900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.269947643979058,
|
| 303 |
+
"grad_norm": 2.5462379455566406,
|
| 304 |
+
"learning_rate": 9.74e-06,
|
| 305 |
+
"loss": 0.4726,
|
| 306 |
+
"step": 1950
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.353717277486911,
|
| 310 |
+
"grad_norm": 1.3994622230529785,
|
| 311 |
+
"learning_rate": 9.990000000000001e-06,
|
| 312 |
+
"loss": 0.4795,
|
| 313 |
+
"step": 2000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.353717277486911,
|
| 317 |
+
"eval_loss": 0.42617055773735046,
|
| 318 |
+
"eval_runtime": 269.3627,
|
| 319 |
+
"eval_samples_per_second": 31.515,
|
| 320 |
+
"eval_steps_per_second": 3.943,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.4374869109947643,
|
| 325 |
+
"grad_norm": 1.8979076147079468,
|
| 326 |
+
"learning_rate": 9.952e-06,
|
| 327 |
+
"loss": 0.4792,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.521256544502618,
|
| 332 |
+
"grad_norm": 1.4493324756622314,
|
| 333 |
+
"learning_rate": 9.902000000000001e-06,
|
| 334 |
+
"loss": 0.4751,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.6050261780104713,
|
| 339 |
+
"grad_norm": 3.3374929428100586,
|
| 340 |
+
"learning_rate": 9.852e-06,
|
| 341 |
+
"loss": 0.4736,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.6887958115183244,
|
| 346 |
+
"grad_norm": 3.5062992572784424,
|
| 347 |
+
"learning_rate": 9.802e-06,
|
| 348 |
+
"loss": 0.4675,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.772565445026178,
|
| 353 |
+
"grad_norm": 2.250505208969116,
|
| 354 |
+
"learning_rate": 9.752e-06,
|
| 355 |
+
"loss": 0.4611,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.8563350785340313,
|
| 360 |
+
"grad_norm": 1.793270468711853,
|
| 361 |
+
"learning_rate": 9.702e-06,
|
| 362 |
+
"loss": 0.4605,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.940104712041885,
|
| 367 |
+
"grad_norm": 1.663677453994751,
|
| 368 |
+
"learning_rate": 9.652e-06,
|
| 369 |
+
"loss": 0.4693,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.023874345549738,
|
| 374 |
+
"grad_norm": 2.1321282386779785,
|
| 375 |
+
"learning_rate": 9.602e-06,
|
| 376 |
+
"loss": 0.4587,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 4.107643979057592,
|
| 381 |
+
"grad_norm": 1.7361410856246948,
|
| 382 |
+
"learning_rate": 9.552000000000001e-06,
|
| 383 |
+
"loss": 0.4611,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.191413612565445,
|
| 388 |
+
"grad_norm": 2.167386770248413,
|
| 389 |
+
"learning_rate": 9.502000000000002e-06,
|
| 390 |
+
"loss": 0.455,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 4.191413612565445,
|
| 395 |
+
"eval_loss": 0.40905508399009705,
|
| 396 |
+
"eval_runtime": 269.8231,
|
| 397 |
+
"eval_samples_per_second": 31.461,
|
| 398 |
+
"eval_steps_per_second": 3.936,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.275183246073299,
|
| 403 |
+
"grad_norm": 1.430746078491211,
|
| 404 |
+
"learning_rate": 9.452000000000002e-06,
|
| 405 |
+
"loss": 0.4581,
|
| 406 |
+
"step": 2550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 4.358952879581151,
|
| 410 |
+
"grad_norm": 2.1168527603149414,
|
| 411 |
+
"learning_rate": 9.402e-06,
|
| 412 |
+
"loss": 0.4516,
|
| 413 |
+
"step": 2600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.442722513089005,
|
| 417 |
+
"grad_norm": 2.1330721378326416,
|
| 418 |
+
"learning_rate": 9.353000000000002e-06,
|
| 419 |
+
"loss": 0.4505,
|
| 420 |
+
"step": 2650
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.526492146596858,
|
| 424 |
+
"grad_norm": 1.274557113647461,
|
| 425 |
+
"learning_rate": 9.303e-06,
|
| 426 |
+
"loss": 0.4575,
|
| 427 |
+
"step": 2700
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.610261780104712,
|
| 431 |
+
"grad_norm": 1.835204839706421,
|
| 432 |
+
"learning_rate": 9.253000000000001e-06,
|
| 433 |
+
"loss": 0.4491,
|
| 434 |
+
"step": 2750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.694031413612565,
|
| 438 |
+
"grad_norm": 2.0255746841430664,
|
| 439 |
+
"learning_rate": 9.203000000000002e-06,
|
| 440 |
+
"loss": 0.4484,
|
| 441 |
+
"step": 2800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.777801047120419,
|
| 445 |
+
"grad_norm": 2.4793522357940674,
|
| 446 |
+
"learning_rate": 9.153e-06,
|
| 447 |
+
"loss": 0.4489,
|
| 448 |
+
"step": 2850
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.861570680628272,
|
| 452 |
+
"grad_norm": 1.7192201614379883,
|
| 453 |
+
"learning_rate": 9.103e-06,
|
| 454 |
+
"loss": 0.4502,
|
| 455 |
+
"step": 2900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.945340314136126,
|
| 459 |
+
"grad_norm": 1.9378846883773804,
|
| 460 |
+
"learning_rate": 9.053000000000001e-06,
|
| 461 |
+
"loss": 0.4483,
|
| 462 |
+
"step": 2950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.029109947643979,
|
| 466 |
+
"grad_norm": 2.4576103687286377,
|
| 467 |
+
"learning_rate": 9.003e-06,
|
| 468 |
+
"loss": 0.4474,
|
| 469 |
+
"step": 3000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 5.029109947643979,
|
| 473 |
+
"eval_loss": 0.39903518557548523,
|
| 474 |
+
"eval_runtime": 269.2955,
|
| 475 |
+
"eval_samples_per_second": 31.523,
|
| 476 |
+
"eval_steps_per_second": 3.944,
|
| 477 |
+
"step": 3000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 5.112879581151833,
|
| 481 |
+
"grad_norm": 1.4718371629714966,
|
| 482 |
+
"learning_rate": 8.953e-06,
|
| 483 |
+
"loss": 0.4428,
|
| 484 |
+
"step": 3050
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 5.196649214659685,
|
| 488 |
+
"grad_norm": 2.4222004413604736,
|
| 489 |
+
"learning_rate": 8.903000000000001e-06,
|
| 490 |
+
"loss": 0.4417,
|
| 491 |
+
"step": 3100
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 5.280418848167539,
|
| 495 |
+
"grad_norm": 1.5284855365753174,
|
| 496 |
+
"learning_rate": 8.853e-06,
|
| 497 |
+
"loss": 0.4395,
|
| 498 |
+
"step": 3150
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 5.364188481675392,
|
| 502 |
+
"grad_norm": 1.7470890283584595,
|
| 503 |
+
"learning_rate": 8.803e-06,
|
| 504 |
+
"loss": 0.4359,
|
| 505 |
+
"step": 3200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 5.447958115183246,
|
| 509 |
+
"grad_norm": 2.1919684410095215,
|
| 510 |
+
"learning_rate": 8.753e-06,
|
| 511 |
+
"loss": 0.4389,
|
| 512 |
+
"step": 3250
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.531727748691099,
|
| 516 |
+
"grad_norm": 1.6179628372192383,
|
| 517 |
+
"learning_rate": 8.703e-06,
|
| 518 |
+
"loss": 0.4423,
|
| 519 |
+
"step": 3300
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.615497382198953,
|
| 523 |
+
"grad_norm": 1.420087218284607,
|
| 524 |
+
"learning_rate": 8.653e-06,
|
| 525 |
+
"loss": 0.4324,
|
| 526 |
+
"step": 3350
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.699267015706806,
|
| 530 |
+
"grad_norm": 1.6972101926803589,
|
| 531 |
+
"learning_rate": 8.603e-06,
|
| 532 |
+
"loss": 0.4327,
|
| 533 |
+
"step": 3400
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.78303664921466,
|
| 537 |
+
"grad_norm": 8.797286033630371,
|
| 538 |
+
"learning_rate": 8.553000000000001e-06,
|
| 539 |
+
"loss": 0.4347,
|
| 540 |
+
"step": 3450
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 5.866806282722513,
|
| 544 |
+
"grad_norm": 1.5441597700119019,
|
| 545 |
+
"learning_rate": 8.503e-06,
|
| 546 |
+
"loss": 0.4342,
|
| 547 |
+
"step": 3500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.866806282722513,
|
| 551 |
+
"eval_loss": 0.39290204644203186,
|
| 552 |
+
"eval_runtime": 272.1215,
|
| 553 |
+
"eval_samples_per_second": 31.196,
|
| 554 |
+
"eval_steps_per_second": 3.903,
|
| 555 |
+
"step": 3500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 5.950575916230367,
|
| 559 |
+
"grad_norm": 1.957065224647522,
|
| 560 |
+
"learning_rate": 8.453000000000002e-06,
|
| 561 |
+
"loss": 0.4288,
|
| 562 |
+
"step": 3550
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 6.0343455497382195,
|
| 566 |
+
"grad_norm": 1.3891559839248657,
|
| 567 |
+
"learning_rate": 8.403e-06,
|
| 568 |
+
"loss": 0.429,
|
| 569 |
+
"step": 3600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 6.118115183246073,
|
| 573 |
+
"grad_norm": 1.6092897653579712,
|
| 574 |
+
"learning_rate": 8.353000000000001e-06,
|
| 575 |
+
"loss": 0.431,
|
| 576 |
+
"step": 3650
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 6.201884816753926,
|
| 580 |
+
"grad_norm": 1.5566798448562622,
|
| 581 |
+
"learning_rate": 8.303000000000002e-06,
|
| 582 |
+
"loss": 0.428,
|
| 583 |
+
"step": 3700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 6.28565445026178,
|
| 587 |
+
"grad_norm": 2.70001220703125,
|
| 588 |
+
"learning_rate": 8.253e-06,
|
| 589 |
+
"loss": 0.433,
|
| 590 |
+
"step": 3750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.369424083769633,
|
| 594 |
+
"grad_norm": 2.6352884769439697,
|
| 595 |
+
"learning_rate": 8.203000000000001e-06,
|
| 596 |
+
"loss": 0.431,
|
| 597 |
+
"step": 3800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.453193717277487,
|
| 601 |
+
"grad_norm": 2.049609422683716,
|
| 602 |
+
"learning_rate": 8.153000000000001e-06,
|
| 603 |
+
"loss": 0.4279,
|
| 604 |
+
"step": 3850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 6.53696335078534,
|
| 608 |
+
"grad_norm": 1.422606110572815,
|
| 609 |
+
"learning_rate": 8.103e-06,
|
| 610 |
+
"loss": 0.4266,
|
| 611 |
+
"step": 3900
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.620732984293194,
|
| 615 |
+
"grad_norm": 1.659340739250183,
|
| 616 |
+
"learning_rate": 8.053e-06,
|
| 617 |
+
"loss": 0.4293,
|
| 618 |
+
"step": 3950
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 6.704502617801047,
|
| 622 |
+
"grad_norm": 1.6214194297790527,
|
| 623 |
+
"learning_rate": 8.003000000000001e-06,
|
| 624 |
+
"loss": 0.4258,
|
| 625 |
+
"step": 4000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.704502617801047,
|
| 629 |
+
"eval_loss": 0.385530561208725,
|
| 630 |
+
"eval_runtime": 270.5177,
|
| 631 |
+
"eval_samples_per_second": 31.381,
|
| 632 |
+
"eval_steps_per_second": 3.926,
|
| 633 |
+
"step": 4000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 6.788272251308901,
|
| 637 |
+
"grad_norm": 2.0542335510253906,
|
| 638 |
+
"learning_rate": 7.953e-06,
|
| 639 |
+
"loss": 0.4232,
|
| 640 |
+
"step": 4050
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 6.872041884816754,
|
| 644 |
+
"grad_norm": 2.0001602172851562,
|
| 645 |
+
"learning_rate": 7.903e-06,
|
| 646 |
+
"loss": 0.4201,
|
| 647 |
+
"step": 4100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 6.955811518324607,
|
| 651 |
+
"grad_norm": 1.5019524097442627,
|
| 652 |
+
"learning_rate": 7.853000000000001e-06,
|
| 653 |
+
"loss": 0.4202,
|
| 654 |
+
"step": 4150
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 7.0395811518324605,
|
| 658 |
+
"grad_norm": 1.5901544094085693,
|
| 659 |
+
"learning_rate": 7.803000000000001e-06,
|
| 660 |
+
"loss": 0.4214,
|
| 661 |
+
"step": 4200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 7.123350785340314,
|
| 665 |
+
"grad_norm": 1.3859797716140747,
|
| 666 |
+
"learning_rate": 7.753e-06,
|
| 667 |
+
"loss": 0.4268,
|
| 668 |
+
"step": 4250
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.2071204188481675,
|
| 672 |
+
"grad_norm": 1.6223664283752441,
|
| 673 |
+
"learning_rate": 7.703e-06,
|
| 674 |
+
"loss": 0.4163,
|
| 675 |
+
"step": 4300
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 7.290890052356021,
|
| 679 |
+
"grad_norm": 1.9755197763442993,
|
| 680 |
+
"learning_rate": 7.653000000000001e-06,
|
| 681 |
+
"loss": 0.421,
|
| 682 |
+
"step": 4350
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 7.374659685863874,
|
| 686 |
+
"grad_norm": 1.9882097244262695,
|
| 687 |
+
"learning_rate": 7.603000000000001e-06,
|
| 688 |
+
"loss": 0.4215,
|
| 689 |
+
"step": 4400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 7.458429319371728,
|
| 693 |
+
"grad_norm": 1.4274579286575317,
|
| 694 |
+
"learning_rate": 7.553e-06,
|
| 695 |
+
"loss": 0.424,
|
| 696 |
+
"step": 4450
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 7.542198952879581,
|
| 700 |
+
"grad_norm": 1.5370174646377563,
|
| 701 |
+
"learning_rate": 7.503e-06,
|
| 702 |
+
"loss": 0.4175,
|
| 703 |
+
"step": 4500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 7.542198952879581,
|
| 707 |
+
"eval_loss": 0.3783535957336426,
|
| 708 |
+
"eval_runtime": 264.9436,
|
| 709 |
+
"eval_samples_per_second": 32.041,
|
| 710 |
+
"eval_steps_per_second": 4.008,
|
| 711 |
+
"step": 4500
|
| 712 |
+
}
|
| 713 |
+
],
|
| 714 |
+
"logging_steps": 50,
|
| 715 |
+
"max_steps": 12000,
|
| 716 |
+
"num_input_tokens_seen": 0,
|
| 717 |
+
"num_train_epochs": 21,
|
| 718 |
+
"save_steps": 500,
|
| 719 |
+
"stateful_callbacks": {
|
| 720 |
+
"TrainerControl": {
|
| 721 |
+
"args": {
|
| 722 |
+
"should_epoch_stop": false,
|
| 723 |
+
"should_evaluate": false,
|
| 724 |
+
"should_log": false,
|
| 725 |
+
"should_save": true,
|
| 726 |
+
"should_training_stop": false
|
| 727 |
+
},
|
| 728 |
+
"attributes": {}
|
| 729 |
+
}
|
| 730 |
+
},
|
| 731 |
+
"total_flos": 8.073028933214573e+16,
|
| 732 |
+
"train_batch_size": 16,
|
| 733 |
+
"trial_name": null,
|
| 734 |
+
"trial_params": null
|
| 735 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3271e94c7230c79ad74395a607b3d03fda68860c191e572f07beb52b230aeff7
|
| 3 |
+
size 5304
|