Commit
•
67dd4e3
1
Parent(s):
f68ea82
Training in progress, step 6000, checkpoint
Browse files- checkpoint-6000/added_tokens.json +4 -0
- checkpoint-6000/config.json +92 -0
- checkpoint-6000/generation_config.json +9 -0
- checkpoint-6000/model.safetensors +3 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/preprocessor_config.json +19 -0
- checkpoint-6000/rng_state.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/special_tokens_map.json +13 -0
- checkpoint-6000/spm_char.model +3 -0
- checkpoint-6000/tokenizer_config.json +63 -0
- checkpoint-6000/trainer_state.json +969 -0
- checkpoint-6000/training_args.bin +3 -0
checkpoint-6000/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<ctc_blank>": 80,
|
| 3 |
+
"<mask>": 79
|
| 4 |
+
}
|
checkpoint-6000/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-6000/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-6000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3998eda95107425fccb16607b1e02d4ba5e50e6a5cfe55bba9d35a22c11c8e8
|
| 3 |
+
size 577789320
|
checkpoint-6000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e81dde7686f4cf9354c8283b5eee7c4b7e3b19b870046148a2a49df5671f894b
|
| 3 |
+
size 1155772233
|
checkpoint-6000/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-6000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5175ad1511aee236ce350aa93c5df8e157cf5eb171371962b0e2de11759fa1e
|
| 3 |
+
size 14244
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04ff002b31b6cc0a01a54d1e3c6f626c5449fc0c5290b11a28578f7f1a9d96b1
|
| 3 |
+
size 1064
|
checkpoint-6000/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-6000/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-6000/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-6000/trainer_state.json
ADDED
|
@@ -0,0 +1,969 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3196151554584503,
|
| 3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s12000/checkpoint-6000",
|
| 4 |
+
"epoch": 10.052356020942408,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6000,
|
| 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": 2.469545841217041,
|
| 14 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 15 |
+
"loss": 1.0402,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16753926701570682,
|
| 20 |
+
"grad_norm": 3.3642780780792236,
|
| 21 |
+
"learning_rate": 4.950000000000001e-06,
|
| 22 |
+
"loss": 0.8472,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2513089005235602,
|
| 27 |
+
"grad_norm": 1.8375087976455688,
|
| 28 |
+
"learning_rate": 7.45e-06,
|
| 29 |
+
"loss": 0.7331,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33507853403141363,
|
| 34 |
+
"grad_norm": 3.700824737548828,
|
| 35 |
+
"learning_rate": 9.950000000000001e-06,
|
| 36 |
+
"loss": 0.6472,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.418848167539267,
|
| 41 |
+
"grad_norm": 1.7632888555526733,
|
| 42 |
+
"learning_rate": 1.2450000000000001e-05,
|
| 43 |
+
"loss": 0.6112,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5026178010471204,
|
| 48 |
+
"grad_norm": 3.1861908435821533,
|
| 49 |
+
"learning_rate": 1.4950000000000001e-05,
|
| 50 |
+
"loss": 0.5865,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5863874345549738,
|
| 55 |
+
"grad_norm": 2.2845046520233154,
|
| 56 |
+
"learning_rate": 1.745e-05,
|
| 57 |
+
"loss": 0.5682,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6701570680628273,
|
| 62 |
+
"grad_norm": 2.079210042953491,
|
| 63 |
+
"learning_rate": 1.995e-05,
|
| 64 |
+
"loss": 0.5465,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7539267015706806,
|
| 69 |
+
"grad_norm": 3.669891119003296,
|
| 70 |
+
"learning_rate": 2.245e-05,
|
| 71 |
+
"loss": 0.5302,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.837696335078534,
|
| 76 |
+
"grad_norm": 2.4679417610168457,
|
| 77 |
+
"learning_rate": 2.495e-05,
|
| 78 |
+
"loss": 0.5137,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.837696335078534,
|
| 83 |
+
"eval_loss": 0.4513999819755554,
|
| 84 |
+
"eval_runtime": 277.1074,
|
| 85 |
+
"eval_samples_per_second": 30.634,
|
| 86 |
+
"eval_steps_per_second": 3.832,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.9214659685863874,
|
| 91 |
+
"grad_norm": 2.703871726989746,
|
| 92 |
+
"learning_rate": 2.7450000000000003e-05,
|
| 93 |
+
"loss": 0.5071,
|
| 94 |
+
"step": 550
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.0052356020942408,
|
| 98 |
+
"grad_norm": 3.8184635639190674,
|
| 99 |
+
"learning_rate": 2.995e-05,
|
| 100 |
+
"loss": 0.4971,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.0890052356020943,
|
| 105 |
+
"grad_norm": 2.2857866287231445,
|
| 106 |
+
"learning_rate": 3.245e-05,
|
| 107 |
+
"loss": 0.4955,
|
| 108 |
+
"step": 650
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.1727748691099475,
|
| 112 |
+
"grad_norm": 3.5974085330963135,
|
| 113 |
+
"learning_rate": 3.495e-05,
|
| 114 |
+
"loss": 0.4935,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.256544502617801,
|
| 119 |
+
"grad_norm": 1.720818281173706,
|
| 120 |
+
"learning_rate": 3.745e-05,
|
| 121 |
+
"loss": 0.4763,
|
| 122 |
+
"step": 750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.3403141361256545,
|
| 126 |
+
"grad_norm": 3.080139636993408,
|
| 127 |
+
"learning_rate": 3.995e-05,
|
| 128 |
+
"loss": 0.4735,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.4240837696335078,
|
| 133 |
+
"grad_norm": 4.877579212188721,
|
| 134 |
+
"learning_rate": 4.245e-05,
|
| 135 |
+
"loss": 0.4654,
|
| 136 |
+
"step": 850
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.5078534031413613,
|
| 140 |
+
"grad_norm": 3.383965253829956,
|
| 141 |
+
"learning_rate": 4.495e-05,
|
| 142 |
+
"loss": 0.4628,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.5916230366492146,
|
| 147 |
+
"grad_norm": 3.3636982440948486,
|
| 148 |
+
"learning_rate": 4.745e-05,
|
| 149 |
+
"loss": 0.4541,
|
| 150 |
+
"step": 950
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.675392670157068,
|
| 154 |
+
"grad_norm": 1.666568398475647,
|
| 155 |
+
"learning_rate": 4.995e-05,
|
| 156 |
+
"loss": 0.4565,
|
| 157 |
+
"step": 1000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.675392670157068,
|
| 161 |
+
"eval_loss": 0.4093586802482605,
|
| 162 |
+
"eval_runtime": 269.4005,
|
| 163 |
+
"eval_samples_per_second": 31.511,
|
| 164 |
+
"eval_steps_per_second": 3.942,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.7591623036649215,
|
| 169 |
+
"grad_norm": 1.6522510051727295,
|
| 170 |
+
"learning_rate": 5.245e-05,
|
| 171 |
+
"loss": 0.4541,
|
| 172 |
+
"step": 1050
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.8429319371727748,
|
| 176 |
+
"grad_norm": 1.6531606912612915,
|
| 177 |
+
"learning_rate": 5.495e-05,
|
| 178 |
+
"loss": 0.4448,
|
| 179 |
+
"step": 1100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.9267015706806283,
|
| 183 |
+
"grad_norm": 3.3253750801086426,
|
| 184 |
+
"learning_rate": 5.745e-05,
|
| 185 |
+
"loss": 0.4346,
|
| 186 |
+
"step": 1150
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0104712041884816,
|
| 190 |
+
"grad_norm": 2.0393073558807373,
|
| 191 |
+
"learning_rate": 5.995000000000001e-05,
|
| 192 |
+
"loss": 0.4314,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.094240837696335,
|
| 197 |
+
"grad_norm": 1.906546950340271,
|
| 198 |
+
"learning_rate": 6.245000000000001e-05,
|
| 199 |
+
"loss": 0.4327,
|
| 200 |
+
"step": 1250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.1780104712041886,
|
| 204 |
+
"grad_norm": 1.7925021648406982,
|
| 205 |
+
"learning_rate": 6.494999999999999e-05,
|
| 206 |
+
"loss": 0.4285,
|
| 207 |
+
"step": 1300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.261780104712042,
|
| 211 |
+
"grad_norm": 2.5238988399505615,
|
| 212 |
+
"learning_rate": 6.745e-05,
|
| 213 |
+
"loss": 0.4251,
|
| 214 |
+
"step": 1350
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.345549738219895,
|
| 218 |
+
"grad_norm": 2.53450345993042,
|
| 219 |
+
"learning_rate": 6.995e-05,
|
| 220 |
+
"loss": 0.4284,
|
| 221 |
+
"step": 1400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.4293193717277486,
|
| 225 |
+
"grad_norm": 1.9077616930007935,
|
| 226 |
+
"learning_rate": 7.245000000000001e-05,
|
| 227 |
+
"loss": 0.4244,
|
| 228 |
+
"step": 1450
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.513089005235602,
|
| 232 |
+
"grad_norm": 1.5720113515853882,
|
| 233 |
+
"learning_rate": 7.495e-05,
|
| 234 |
+
"loss": 0.4171,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.513089005235602,
|
| 239 |
+
"eval_loss": 0.384281188249588,
|
| 240 |
+
"eval_runtime": 274.8763,
|
| 241 |
+
"eval_samples_per_second": 30.883,
|
| 242 |
+
"eval_steps_per_second": 3.864,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.5968586387434556,
|
| 247 |
+
"grad_norm": 2.272549867630005,
|
| 248 |
+
"learning_rate": 7.745e-05,
|
| 249 |
+
"loss": 0.4175,
|
| 250 |
+
"step": 1550
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.680628272251309,
|
| 254 |
+
"grad_norm": 1.3440821170806885,
|
| 255 |
+
"learning_rate": 7.995e-05,
|
| 256 |
+
"loss": 0.4134,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.7643979057591626,
|
| 261 |
+
"grad_norm": 1.99045729637146,
|
| 262 |
+
"learning_rate": 8.245e-05,
|
| 263 |
+
"loss": 0.4117,
|
| 264 |
+
"step": 1650
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.8481675392670156,
|
| 268 |
+
"grad_norm": 1.3599165678024292,
|
| 269 |
+
"learning_rate": 8.495e-05,
|
| 270 |
+
"loss": 0.4101,
|
| 271 |
+
"step": 1700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.931937172774869,
|
| 275 |
+
"grad_norm": 2.3722105026245117,
|
| 276 |
+
"learning_rate": 8.745000000000001e-05,
|
| 277 |
+
"loss": 0.413,
|
| 278 |
+
"step": 1750
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.0157068062827226,
|
| 282 |
+
"grad_norm": 1.5704238414764404,
|
| 283 |
+
"learning_rate": 8.995e-05,
|
| 284 |
+
"loss": 0.4086,
|
| 285 |
+
"step": 1800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.099476439790576,
|
| 289 |
+
"grad_norm": 3.272968053817749,
|
| 290 |
+
"learning_rate": 9.245e-05,
|
| 291 |
+
"loss": 0.4057,
|
| 292 |
+
"step": 1850
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 3.183246073298429,
|
| 296 |
+
"grad_norm": 2.658064126968384,
|
| 297 |
+
"learning_rate": 9.495e-05,
|
| 298 |
+
"loss": 0.4071,
|
| 299 |
+
"step": 1900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.2670157068062826,
|
| 303 |
+
"grad_norm": 1.688971757888794,
|
| 304 |
+
"learning_rate": 9.745000000000001e-05,
|
| 305 |
+
"loss": 0.3984,
|
| 306 |
+
"step": 1950
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.350785340314136,
|
| 310 |
+
"grad_norm": 1.4563082456588745,
|
| 311 |
+
"learning_rate": 9.995e-05,
|
| 312 |
+
"loss": 0.404,
|
| 313 |
+
"step": 2000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.350785340314136,
|
| 317 |
+
"eval_loss": 0.36596959829330444,
|
| 318 |
+
"eval_runtime": 268.3638,
|
| 319 |
+
"eval_samples_per_second": 31.632,
|
| 320 |
+
"eval_steps_per_second": 3.957,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.4345549738219896,
|
| 325 |
+
"grad_norm": 1.6672757863998413,
|
| 326 |
+
"learning_rate": 9.951e-05,
|
| 327 |
+
"loss": 0.4032,
|
| 328 |
+
"step": 2050
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.518324607329843,
|
| 332 |
+
"grad_norm": 2.0084328651428223,
|
| 333 |
+
"learning_rate": 9.901e-05,
|
| 334 |
+
"loss": 0.4003,
|
| 335 |
+
"step": 2100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.6020942408376966,
|
| 339 |
+
"grad_norm": 1.8289756774902344,
|
| 340 |
+
"learning_rate": 9.851e-05,
|
| 341 |
+
"loss": 0.3986,
|
| 342 |
+
"step": 2150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.6858638743455496,
|
| 346 |
+
"grad_norm": 1.791348934173584,
|
| 347 |
+
"learning_rate": 9.801e-05,
|
| 348 |
+
"loss": 0.3928,
|
| 349 |
+
"step": 2200
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.769633507853403,
|
| 353 |
+
"grad_norm": 1.9079582691192627,
|
| 354 |
+
"learning_rate": 9.751e-05,
|
| 355 |
+
"loss": 0.3899,
|
| 356 |
+
"step": 2250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.8534031413612566,
|
| 360 |
+
"grad_norm": 7.154463768005371,
|
| 361 |
+
"learning_rate": 9.701e-05,
|
| 362 |
+
"loss": 0.3894,
|
| 363 |
+
"step": 2300
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.93717277486911,
|
| 367 |
+
"grad_norm": 1.9638899564743042,
|
| 368 |
+
"learning_rate": 9.651e-05,
|
| 369 |
+
"loss": 0.399,
|
| 370 |
+
"step": 2350
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.020942408376963,
|
| 374 |
+
"grad_norm": 2.147676706314087,
|
| 375 |
+
"learning_rate": 9.601e-05,
|
| 376 |
+
"loss": 0.3902,
|
| 377 |
+
"step": 2400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 4.104712041884817,
|
| 381 |
+
"grad_norm": 2.282815456390381,
|
| 382 |
+
"learning_rate": 9.551e-05,
|
| 383 |
+
"loss": 0.3906,
|
| 384 |
+
"step": 2450
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 4.18848167539267,
|
| 388 |
+
"grad_norm": 1.2255228757858276,
|
| 389 |
+
"learning_rate": 9.501e-05,
|
| 390 |
+
"loss": 0.3851,
|
| 391 |
+
"step": 2500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 4.18848167539267,
|
| 395 |
+
"eval_loss": 0.354680597782135,
|
| 396 |
+
"eval_runtime": 269.5668,
|
| 397 |
+
"eval_samples_per_second": 31.491,
|
| 398 |
+
"eval_steps_per_second": 3.94,
|
| 399 |
+
"step": 2500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.272251308900524,
|
| 403 |
+
"grad_norm": 1.2088522911071777,
|
| 404 |
+
"learning_rate": 9.451000000000002e-05,
|
| 405 |
+
"loss": 0.3891,
|
| 406 |
+
"step": 2550
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 4.356020942408377,
|
| 410 |
+
"grad_norm": 1.3467260599136353,
|
| 411 |
+
"learning_rate": 9.402000000000001e-05,
|
| 412 |
+
"loss": 0.3854,
|
| 413 |
+
"step": 2600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.439790575916231,
|
| 417 |
+
"grad_norm": 1.2227791547775269,
|
| 418 |
+
"learning_rate": 9.352000000000001e-05,
|
| 419 |
+
"loss": 0.3818,
|
| 420 |
+
"step": 2650
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.523560209424084,
|
| 424 |
+
"grad_norm": 1.0672763586044312,
|
| 425 |
+
"learning_rate": 9.302e-05,
|
| 426 |
+
"loss": 0.389,
|
| 427 |
+
"step": 2700
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.607329842931938,
|
| 431 |
+
"grad_norm": 1.6198370456695557,
|
| 432 |
+
"learning_rate": 9.252e-05,
|
| 433 |
+
"loss": 0.3811,
|
| 434 |
+
"step": 2750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.69109947643979,
|
| 438 |
+
"grad_norm": 1.296200156211853,
|
| 439 |
+
"learning_rate": 9.202e-05,
|
| 440 |
+
"loss": 0.382,
|
| 441 |
+
"step": 2800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.774869109947644,
|
| 445 |
+
"grad_norm": 1.533375859260559,
|
| 446 |
+
"learning_rate": 9.152e-05,
|
| 447 |
+
"loss": 0.381,
|
| 448 |
+
"step": 2850
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.858638743455497,
|
| 452 |
+
"grad_norm": 2.161743640899658,
|
| 453 |
+
"learning_rate": 9.102e-05,
|
| 454 |
+
"loss": 0.3829,
|
| 455 |
+
"step": 2900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.942408376963351,
|
| 459 |
+
"grad_norm": 1.2308694124221802,
|
| 460 |
+
"learning_rate": 9.052000000000001e-05,
|
| 461 |
+
"loss": 0.3806,
|
| 462 |
+
"step": 2950
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.026178010471204,
|
| 466 |
+
"grad_norm": 1.2448184490203857,
|
| 467 |
+
"learning_rate": 9.002000000000001e-05,
|
| 468 |
+
"loss": 0.3808,
|
| 469 |
+
"step": 3000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 5.026178010471204,
|
| 473 |
+
"eval_loss": 0.3451012670993805,
|
| 474 |
+
"eval_runtime": 274.5252,
|
| 475 |
+
"eval_samples_per_second": 30.922,
|
| 476 |
+
"eval_steps_per_second": 3.868,
|
| 477 |
+
"step": 3000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 5.109947643979058,
|
| 481 |
+
"grad_norm": 1.4961705207824707,
|
| 482 |
+
"learning_rate": 8.952000000000001e-05,
|
| 483 |
+
"loss": 0.3755,
|
| 484 |
+
"step": 3050
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 5.193717277486911,
|
| 488 |
+
"grad_norm": 1.2276802062988281,
|
| 489 |
+
"learning_rate": 8.902e-05,
|
| 490 |
+
"loss": 0.3771,
|
| 491 |
+
"step": 3100
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 5.277486910994765,
|
| 495 |
+
"grad_norm": 1.3186664581298828,
|
| 496 |
+
"learning_rate": 8.852e-05,
|
| 497 |
+
"loss": 0.3766,
|
| 498 |
+
"step": 3150
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 5.361256544502618,
|
| 502 |
+
"grad_norm": 1.4056960344314575,
|
| 503 |
+
"learning_rate": 8.802e-05,
|
| 504 |
+
"loss": 0.3761,
|
| 505 |
+
"step": 3200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 5.445026178010472,
|
| 509 |
+
"grad_norm": 1.4609332084655762,
|
| 510 |
+
"learning_rate": 8.752e-05,
|
| 511 |
+
"loss": 0.377,
|
| 512 |
+
"step": 3250
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.528795811518324,
|
| 516 |
+
"grad_norm": 1.2348676919937134,
|
| 517 |
+
"learning_rate": 8.702e-05,
|
| 518 |
+
"loss": 0.3761,
|
| 519 |
+
"step": 3300
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.612565445026178,
|
| 523 |
+
"grad_norm": 1.2290446758270264,
|
| 524 |
+
"learning_rate": 8.652e-05,
|
| 525 |
+
"loss": 0.3735,
|
| 526 |
+
"step": 3350
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.696335078534031,
|
| 530 |
+
"grad_norm": 1.0205050706863403,
|
| 531 |
+
"learning_rate": 8.602e-05,
|
| 532 |
+
"loss": 0.3709,
|
| 533 |
+
"step": 3400
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.780104712041885,
|
| 537 |
+
"grad_norm": 1.83589768409729,
|
| 538 |
+
"learning_rate": 8.552e-05,
|
| 539 |
+
"loss": 0.3709,
|
| 540 |
+
"step": 3450
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 5.863874345549738,
|
| 544 |
+
"grad_norm": 1.8419536352157593,
|
| 545 |
+
"learning_rate": 8.502e-05,
|
| 546 |
+
"loss": 0.3704,
|
| 547 |
+
"step": 3500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.863874345549738,
|
| 551 |
+
"eval_loss": 0.33645617961883545,
|
| 552 |
+
"eval_runtime": 267.7957,
|
| 553 |
+
"eval_samples_per_second": 31.7,
|
| 554 |
+
"eval_steps_per_second": 3.966,
|
| 555 |
+
"step": 3500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 5.947643979057592,
|
| 559 |
+
"grad_norm": 0.9079850316047668,
|
| 560 |
+
"learning_rate": 8.452e-05,
|
| 561 |
+
"loss": 0.3674,
|
| 562 |
+
"step": 3550
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 6.031413612565445,
|
| 566 |
+
"grad_norm": 1.6563224792480469,
|
| 567 |
+
"learning_rate": 8.402e-05,
|
| 568 |
+
"loss": 0.368,
|
| 569 |
+
"step": 3600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 6.115183246073299,
|
| 573 |
+
"grad_norm": 0.9500299096107483,
|
| 574 |
+
"learning_rate": 8.352000000000001e-05,
|
| 575 |
+
"loss": 0.3692,
|
| 576 |
+
"step": 3650
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 6.198952879581152,
|
| 580 |
+
"grad_norm": 1.219301700592041,
|
| 581 |
+
"learning_rate": 8.302000000000001e-05,
|
| 582 |
+
"loss": 0.3664,
|
| 583 |
+
"step": 3700
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 6.282722513089006,
|
| 587 |
+
"grad_norm": 1.466737985610962,
|
| 588 |
+
"learning_rate": 8.252e-05,
|
| 589 |
+
"loss": 0.3697,
|
| 590 |
+
"step": 3750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.366492146596858,
|
| 594 |
+
"grad_norm": 1.329934000968933,
|
| 595 |
+
"learning_rate": 8.202e-05,
|
| 596 |
+
"loss": 0.3676,
|
| 597 |
+
"step": 3800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.450261780104712,
|
| 601 |
+
"grad_norm": 1.0545940399169922,
|
| 602 |
+
"learning_rate": 8.152e-05,
|
| 603 |
+
"loss": 0.3673,
|
| 604 |
+
"step": 3850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 6.534031413612565,
|
| 608 |
+
"grad_norm": 1.7130441665649414,
|
| 609 |
+
"learning_rate": 8.102000000000001e-05,
|
| 610 |
+
"loss": 0.3658,
|
| 611 |
+
"step": 3900
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.617801047120419,
|
| 615 |
+
"grad_norm": 2.0463407039642334,
|
| 616 |
+
"learning_rate": 8.052000000000001e-05,
|
| 617 |
+
"loss": 0.3681,
|
| 618 |
+
"step": 3950
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 6.701570680628272,
|
| 622 |
+
"grad_norm": 1.0734078884124756,
|
| 623 |
+
"learning_rate": 8.002000000000001e-05,
|
| 624 |
+
"loss": 0.3664,
|
| 625 |
+
"step": 4000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.701570680628272,
|
| 629 |
+
"eval_loss": 0.3334435820579529,
|
| 630 |
+
"eval_runtime": 269.2566,
|
| 631 |
+
"eval_samples_per_second": 31.528,
|
| 632 |
+
"eval_steps_per_second": 3.944,
|
| 633 |
+
"step": 4000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 6.785340314136126,
|
| 637 |
+
"grad_norm": 0.9216086864471436,
|
| 638 |
+
"learning_rate": 7.952000000000001e-05,
|
| 639 |
+
"loss": 0.3619,
|
| 640 |
+
"step": 4050
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 6.869109947643979,
|
| 644 |
+
"grad_norm": 1.802753210067749,
|
| 645 |
+
"learning_rate": 7.902e-05,
|
| 646 |
+
"loss": 0.3628,
|
| 647 |
+
"step": 4100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 6.952879581151833,
|
| 651 |
+
"grad_norm": 1.3391004800796509,
|
| 652 |
+
"learning_rate": 7.852e-05,
|
| 653 |
+
"loss": 0.3626,
|
| 654 |
+
"step": 4150
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 7.036649214659686,
|
| 658 |
+
"grad_norm": 0.9989505410194397,
|
| 659 |
+
"learning_rate": 7.802e-05,
|
| 660 |
+
"loss": 0.3641,
|
| 661 |
+
"step": 4200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 7.12041884816754,
|
| 665 |
+
"grad_norm": 1.318490743637085,
|
| 666 |
+
"learning_rate": 7.752e-05,
|
| 667 |
+
"loss": 0.3661,
|
| 668 |
+
"step": 4250
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.204188481675392,
|
| 672 |
+
"grad_norm": 1.4725680351257324,
|
| 673 |
+
"learning_rate": 7.702e-05,
|
| 674 |
+
"loss": 0.359,
|
| 675 |
+
"step": 4300
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 7.287958115183246,
|
| 679 |
+
"grad_norm": 1.3948692083358765,
|
| 680 |
+
"learning_rate": 7.652e-05,
|
| 681 |
+
"loss": 0.3622,
|
| 682 |
+
"step": 4350
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 7.371727748691099,
|
| 686 |
+
"grad_norm": 1.4226194620132446,
|
| 687 |
+
"learning_rate": 7.602000000000001e-05,
|
| 688 |
+
"loss": 0.3641,
|
| 689 |
+
"step": 4400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 7.455497382198953,
|
| 693 |
+
"grad_norm": 1.008616328239441,
|
| 694 |
+
"learning_rate": 7.552e-05,
|
| 695 |
+
"loss": 0.3643,
|
| 696 |
+
"step": 4450
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 7.539267015706806,
|
| 700 |
+
"grad_norm": 1.3399937152862549,
|
| 701 |
+
"learning_rate": 7.502e-05,
|
| 702 |
+
"loss": 0.3598,
|
| 703 |
+
"step": 4500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 7.539267015706806,
|
| 707 |
+
"eval_loss": 0.32835692167282104,
|
| 708 |
+
"eval_runtime": 275.5633,
|
| 709 |
+
"eval_samples_per_second": 30.806,
|
| 710 |
+
"eval_steps_per_second": 3.854,
|
| 711 |
+
"step": 4500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 7.62303664921466,
|
| 715 |
+
"grad_norm": 1.2946890592575073,
|
| 716 |
+
"learning_rate": 7.452e-05,
|
| 717 |
+
"loss": 0.3595,
|
| 718 |
+
"step": 4550
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 7.706806282722513,
|
| 722 |
+
"grad_norm": 1.672792911529541,
|
| 723 |
+
"learning_rate": 7.402e-05,
|
| 724 |
+
"loss": 0.3651,
|
| 725 |
+
"step": 4600
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 7.790575916230367,
|
| 729 |
+
"grad_norm": 1.3620250225067139,
|
| 730 |
+
"learning_rate": 7.352e-05,
|
| 731 |
+
"loss": 0.3666,
|
| 732 |
+
"step": 4650
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 7.87434554973822,
|
| 736 |
+
"grad_norm": 2.236588954925537,
|
| 737 |
+
"learning_rate": 7.302e-05,
|
| 738 |
+
"loss": 0.365,
|
| 739 |
+
"step": 4700
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 7.958115183246074,
|
| 743 |
+
"grad_norm": 2.052438259124756,
|
| 744 |
+
"learning_rate": 7.252e-05,
|
| 745 |
+
"loss": 0.3557,
|
| 746 |
+
"step": 4750
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.041884816753926,
|
| 750 |
+
"grad_norm": 1.1328259706497192,
|
| 751 |
+
"learning_rate": 7.202e-05,
|
| 752 |
+
"loss": 0.3573,
|
| 753 |
+
"step": 4800
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.12565445026178,
|
| 757 |
+
"grad_norm": 1.4987516403198242,
|
| 758 |
+
"learning_rate": 7.151999999999999e-05,
|
| 759 |
+
"loss": 0.3547,
|
| 760 |
+
"step": 4850
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.209424083769633,
|
| 764 |
+
"grad_norm": 1.502505898475647,
|
| 765 |
+
"learning_rate": 7.102000000000001e-05,
|
| 766 |
+
"loss": 0.3668,
|
| 767 |
+
"step": 4900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 8.293193717277488,
|
| 771 |
+
"grad_norm": 1.4446626901626587,
|
| 772 |
+
"learning_rate": 7.052000000000001e-05,
|
| 773 |
+
"loss": 0.3566,
|
| 774 |
+
"step": 4950
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 8.37696335078534,
|
| 778 |
+
"grad_norm": 0.9949765205383301,
|
| 779 |
+
"learning_rate": 7.002000000000001e-05,
|
| 780 |
+
"loss": 0.3612,
|
| 781 |
+
"step": 5000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 8.37696335078534,
|
| 785 |
+
"eval_loss": 0.3273167312145233,
|
| 786 |
+
"eval_runtime": 277.1246,
|
| 787 |
+
"eval_samples_per_second": 30.632,
|
| 788 |
+
"eval_steps_per_second": 3.832,
|
| 789 |
+
"step": 5000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 8.460732984293193,
|
| 793 |
+
"grad_norm": 1.5191736221313477,
|
| 794 |
+
"learning_rate": 6.952000000000001e-05,
|
| 795 |
+
"loss": 0.355,
|
| 796 |
+
"step": 5050
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 8.544502617801047,
|
| 800 |
+
"grad_norm": 2.3525736331939697,
|
| 801 |
+
"learning_rate": 6.902000000000001e-05,
|
| 802 |
+
"loss": 0.3554,
|
| 803 |
+
"step": 5100
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 8.6282722513089,
|
| 807 |
+
"grad_norm": 1.3651047945022583,
|
| 808 |
+
"learning_rate": 6.852e-05,
|
| 809 |
+
"loss": 0.36,
|
| 810 |
+
"step": 5150
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 8.712041884816754,
|
| 814 |
+
"grad_norm": 1.8448572158813477,
|
| 815 |
+
"learning_rate": 6.802e-05,
|
| 816 |
+
"loss": 0.3535,
|
| 817 |
+
"step": 5200
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 8.795811518324607,
|
| 821 |
+
"grad_norm": 1.2485219240188599,
|
| 822 |
+
"learning_rate": 6.752e-05,
|
| 823 |
+
"loss": 0.3564,
|
| 824 |
+
"step": 5250
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 8.879581151832461,
|
| 828 |
+
"grad_norm": 1.3560365438461304,
|
| 829 |
+
"learning_rate": 6.702e-05,
|
| 830 |
+
"loss": 0.3536,
|
| 831 |
+
"step": 5300
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 8.963350785340314,
|
| 835 |
+
"grad_norm": 1.9484964609146118,
|
| 836 |
+
"learning_rate": 6.652000000000001e-05,
|
| 837 |
+
"loss": 0.3554,
|
| 838 |
+
"step": 5350
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 9.047120418848168,
|
| 842 |
+
"grad_norm": 1.1570740938186646,
|
| 843 |
+
"learning_rate": 6.602000000000001e-05,
|
| 844 |
+
"loss": 0.3608,
|
| 845 |
+
"step": 5400
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 9.13089005235602,
|
| 849 |
+
"grad_norm": 2.5024497509002686,
|
| 850 |
+
"learning_rate": 6.552000000000001e-05,
|
| 851 |
+
"loss": 0.3519,
|
| 852 |
+
"step": 5450
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 9.214659685863875,
|
| 856 |
+
"grad_norm": 1.2458699941635132,
|
| 857 |
+
"learning_rate": 6.502e-05,
|
| 858 |
+
"loss": 0.3523,
|
| 859 |
+
"step": 5500
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 9.214659685863875,
|
| 863 |
+
"eval_loss": 0.32777872681617737,
|
| 864 |
+
"eval_runtime": 273.5101,
|
| 865 |
+
"eval_samples_per_second": 31.037,
|
| 866 |
+
"eval_steps_per_second": 3.883,
|
| 867 |
+
"step": 5500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 9.298429319371728,
|
| 871 |
+
"grad_norm": 1.3453543186187744,
|
| 872 |
+
"learning_rate": 6.452e-05,
|
| 873 |
+
"loss": 0.3534,
|
| 874 |
+
"step": 5550
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 9.38219895287958,
|
| 878 |
+
"grad_norm": 1.2104579210281372,
|
| 879 |
+
"learning_rate": 6.402e-05,
|
| 880 |
+
"loss": 0.3553,
|
| 881 |
+
"step": 5600
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 9.465968586387435,
|
| 885 |
+
"grad_norm": 1.1557406187057495,
|
| 886 |
+
"learning_rate": 6.352e-05,
|
| 887 |
+
"loss": 0.3514,
|
| 888 |
+
"step": 5650
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 9.549738219895287,
|
| 892 |
+
"grad_norm": 1.621117353439331,
|
| 893 |
+
"learning_rate": 6.302e-05,
|
| 894 |
+
"loss": 0.3542,
|
| 895 |
+
"step": 5700
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 9.633507853403142,
|
| 899 |
+
"grad_norm": 0.9746065139770508,
|
| 900 |
+
"learning_rate": 6.252e-05,
|
| 901 |
+
"loss": 0.3538,
|
| 902 |
+
"step": 5750
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 9.717277486910994,
|
| 906 |
+
"grad_norm": 1.445143222808838,
|
| 907 |
+
"learning_rate": 6.202e-05,
|
| 908 |
+
"loss": 0.3536,
|
| 909 |
+
"step": 5800
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 9.801047120418849,
|
| 913 |
+
"grad_norm": 1.8927617073059082,
|
| 914 |
+
"learning_rate": 6.152e-05,
|
| 915 |
+
"loss": 0.3532,
|
| 916 |
+
"step": 5850
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 9.884816753926701,
|
| 920 |
+
"grad_norm": 1.3752628564834595,
|
| 921 |
+
"learning_rate": 6.102e-05,
|
| 922 |
+
"loss": 0.3479,
|
| 923 |
+
"step": 5900
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 9.968586387434556,
|
| 927 |
+
"grad_norm": 1.8939998149871826,
|
| 928 |
+
"learning_rate": 6.0519999999999997e-05,
|
| 929 |
+
"loss": 0.3533,
|
| 930 |
+
"step": 5950
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 10.052356020942408,
|
| 934 |
+
"grad_norm": 1.564810037612915,
|
| 935 |
+
"learning_rate": 6.002e-05,
|
| 936 |
+
"loss": 0.3484,
|
| 937 |
+
"step": 6000
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 10.052356020942408,
|
| 941 |
+
"eval_loss": 0.3196151554584503,
|
| 942 |
+
"eval_runtime": 270.4466,
|
| 943 |
+
"eval_samples_per_second": 31.389,
|
| 944 |
+
"eval_steps_per_second": 3.927,
|
| 945 |
+
"step": 6000
|
| 946 |
+
}
|
| 947 |
+
],
|
| 948 |
+
"logging_steps": 50,
|
| 949 |
+
"max_steps": 12000,
|
| 950 |
+
"num_input_tokens_seen": 0,
|
| 951 |
+
"num_train_epochs": 21,
|
| 952 |
+
"save_steps": 500,
|
| 953 |
+
"stateful_callbacks": {
|
| 954 |
+
"TrainerControl": {
|
| 955 |
+
"args": {
|
| 956 |
+
"should_epoch_stop": false,
|
| 957 |
+
"should_evaluate": false,
|
| 958 |
+
"should_log": false,
|
| 959 |
+
"should_save": true,
|
| 960 |
+
"should_training_stop": false
|
| 961 |
+
},
|
| 962 |
+
"attributes": {}
|
| 963 |
+
}
|
| 964 |
+
},
|
| 965 |
+
"total_flos": 1.0787618967689203e+17,
|
| 966 |
+
"train_batch_size": 16,
|
| 967 |
+
"trial_name": null,
|
| 968 |
+
"trial_params": null
|
| 969 |
+
}
|
checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6304ea0933d70781edbe7cacf0314ac17c1883ad578c342a8882df2edd83e655
|
| 3 |
+
size 5304
|