mikhail-panzo
commited on
Commit
•
2a36387
1
Parent(s):
11228f3
Training in progress, step 2500, checkpoint
Browse files- checkpoint-2500/added_tokens.json +4 -0
- checkpoint-2500/config.json +92 -0
- checkpoint-2500/generation_config.json +9 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/preprocessor_config.json +19 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +13 -0
- checkpoint-2500/spm_char.model +3 -0
- checkpoint-2500/tokenizer_config.json +63 -0
- checkpoint-2500/trainer_state.json +423 -0
- checkpoint-2500/training_args.bin +3 -0
checkpoint-2500/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<ctc_blank>": 80,
|
3 |
+
"<mask>": 79
|
4 |
+
}
|
checkpoint-2500/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-2500/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-2500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c025c9639c8cc87bcf25b376e56de2418787608e9c0c0763871f627038f243d
|
3 |
+
size 577789320
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:570a3a5a8428761a17815d10e887f782926237f33463d551a2524938a8099180
|
3 |
+
size 1155772233
|
checkpoint-2500/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-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6897fa3d8d9743513473619f7423066e927c20bf6f50c5777bff0318ac4e29ec
|
3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:698bd4a10f83d4486fe8dacc1d1634da5e03772e893869455de6195d2dcba016
|
3 |
+
size 1064
|
checkpoint-2500/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-2500/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-2500/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-2500/trainer_state.json
ADDED
@@ -0,0 +1,423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3966299593448639,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/ceb_b128_le4_s8000/checkpoint-2000",
|
4 |
+
"epoch": 198.01980198019803,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 3.9603960396039604,
|
13 |
+
"grad_norm": 2.95651912689209,
|
14 |
+
"learning_rate": 2.5e-06,
|
15 |
+
"loss": 0.7707,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 7.920792079207921,
|
20 |
+
"grad_norm": 1.1273679733276367,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 0.6934,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 11.881188118811881,
|
27 |
+
"grad_norm": 2.1830034255981445,
|
28 |
+
"learning_rate": 7.5e-06,
|
29 |
+
"loss": 0.5983,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 15.841584158415841,
|
34 |
+
"grad_norm": 1.0733364820480347,
|
35 |
+
"learning_rate": 1e-05,
|
36 |
+
"loss": 0.5094,
|
37 |
+
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 19.801980198019802,
|
41 |
+
"grad_norm": 1.2824387550354004,
|
42 |
+
"learning_rate": 1.25e-05,
|
43 |
+
"loss": 0.4913,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 23.762376237623762,
|
48 |
+
"grad_norm": 0.9164418578147888,
|
49 |
+
"learning_rate": 1.5e-05,
|
50 |
+
"loss": 0.4764,
|
51 |
+
"step": 300
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 27.722772277227723,
|
55 |
+
"grad_norm": 0.8938279747962952,
|
56 |
+
"learning_rate": 1.75e-05,
|
57 |
+
"loss": 0.4648,
|
58 |
+
"step": 350
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 31.683168316831683,
|
62 |
+
"grad_norm": 0.7855221033096313,
|
63 |
+
"learning_rate": 2e-05,
|
64 |
+
"loss": 0.459,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 35.64356435643565,
|
69 |
+
"grad_norm": 0.9247761964797974,
|
70 |
+
"learning_rate": 2.25e-05,
|
71 |
+
"loss": 0.4519,
|
72 |
+
"step": 450
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 39.603960396039604,
|
76 |
+
"grad_norm": 1.1086606979370117,
|
77 |
+
"learning_rate": 2.5e-05,
|
78 |
+
"loss": 0.4432,
|
79 |
+
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 39.603960396039604,
|
83 |
+
"eval_loss": 0.4058004915714264,
|
84 |
+
"eval_runtime": 7.6054,
|
85 |
+
"eval_samples_per_second": 23.667,
|
86 |
+
"eval_steps_per_second": 3.024,
|
87 |
+
"step": 500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 43.56435643564357,
|
91 |
+
"grad_norm": 1.3994853496551514,
|
92 |
+
"learning_rate": 2.7500000000000004e-05,
|
93 |
+
"loss": 0.4438,
|
94 |
+
"step": 550
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 47.524752475247524,
|
98 |
+
"grad_norm": 1.1104933023452759,
|
99 |
+
"learning_rate": 3e-05,
|
100 |
+
"loss": 0.4367,
|
101 |
+
"step": 600
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 51.48514851485149,
|
105 |
+
"grad_norm": 0.7456745505332947,
|
106 |
+
"learning_rate": 3.2500000000000004e-05,
|
107 |
+
"loss": 0.4315,
|
108 |
+
"step": 650
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 55.445544554455445,
|
112 |
+
"grad_norm": 1.0349308252334595,
|
113 |
+
"learning_rate": 3.5e-05,
|
114 |
+
"loss": 0.4294,
|
115 |
+
"step": 700
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 59.40594059405941,
|
119 |
+
"grad_norm": 0.5290626287460327,
|
120 |
+
"learning_rate": 3.7500000000000003e-05,
|
121 |
+
"loss": 0.4234,
|
122 |
+
"step": 750
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 63.366336633663366,
|
126 |
+
"grad_norm": 1.054995059967041,
|
127 |
+
"learning_rate": 4e-05,
|
128 |
+
"loss": 0.4231,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 67.32673267326733,
|
133 |
+
"grad_norm": 1.1774096488952637,
|
134 |
+
"learning_rate": 4.25e-05,
|
135 |
+
"loss": 0.4198,
|
136 |
+
"step": 850
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 71.2871287128713,
|
140 |
+
"grad_norm": 0.7513113617897034,
|
141 |
+
"learning_rate": 4.5e-05,
|
142 |
+
"loss": 0.4182,
|
143 |
+
"step": 900
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 75.24752475247524,
|
147 |
+
"grad_norm": 0.8465940952301025,
|
148 |
+
"learning_rate": 4.75e-05,
|
149 |
+
"loss": 0.4179,
|
150 |
+
"step": 950
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 79.20792079207921,
|
154 |
+
"grad_norm": 1.601589322090149,
|
155 |
+
"learning_rate": 5e-05,
|
156 |
+
"loss": 0.4129,
|
157 |
+
"step": 1000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 79.20792079207921,
|
161 |
+
"eval_loss": 0.3995668292045593,
|
162 |
+
"eval_runtime": 8.0229,
|
163 |
+
"eval_samples_per_second": 22.436,
|
164 |
+
"eval_steps_per_second": 2.867,
|
165 |
+
"step": 1000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 83.16831683168317,
|
169 |
+
"grad_norm": 2.049264669418335,
|
170 |
+
"learning_rate": 5.25e-05,
|
171 |
+
"loss": 0.4129,
|
172 |
+
"step": 1050
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 87.12871287128714,
|
176 |
+
"grad_norm": 1.0590511560440063,
|
177 |
+
"learning_rate": 5.500000000000001e-05,
|
178 |
+
"loss": 0.4118,
|
179 |
+
"step": 1100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 91.08910891089108,
|
183 |
+
"grad_norm": 1.015751600265503,
|
184 |
+
"learning_rate": 5.7499999999999995e-05,
|
185 |
+
"loss": 0.4074,
|
186 |
+
"step": 1150
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 95.04950495049505,
|
190 |
+
"grad_norm": 1.295837640762329,
|
191 |
+
"learning_rate": 6e-05,
|
192 |
+
"loss": 0.4056,
|
193 |
+
"step": 1200
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 99.00990099009901,
|
197 |
+
"grad_norm": 1.49947988986969,
|
198 |
+
"learning_rate": 6.25e-05,
|
199 |
+
"loss": 0.4052,
|
200 |
+
"step": 1250
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 102.97029702970298,
|
204 |
+
"grad_norm": 1.3930383920669556,
|
205 |
+
"learning_rate": 6.500000000000001e-05,
|
206 |
+
"loss": 0.4072,
|
207 |
+
"step": 1300
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 106.93069306930693,
|
211 |
+
"grad_norm": 1.1130273342132568,
|
212 |
+
"learning_rate": 6.750000000000001e-05,
|
213 |
+
"loss": 0.4015,
|
214 |
+
"step": 1350
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 110.89108910891089,
|
218 |
+
"grad_norm": 2.1075382232666016,
|
219 |
+
"learning_rate": 7e-05,
|
220 |
+
"loss": 0.3994,
|
221 |
+
"step": 1400
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 114.85148514851485,
|
225 |
+
"grad_norm": 1.8470244407653809,
|
226 |
+
"learning_rate": 7.25e-05,
|
227 |
+
"loss": 0.397,
|
228 |
+
"step": 1450
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 118.81188118811882,
|
232 |
+
"grad_norm": 2.0715270042419434,
|
233 |
+
"learning_rate": 7.500000000000001e-05,
|
234 |
+
"loss": 0.3992,
|
235 |
+
"step": 1500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 118.81188118811882,
|
239 |
+
"eval_loss": 0.39855822920799255,
|
240 |
+
"eval_runtime": 7.8631,
|
241 |
+
"eval_samples_per_second": 22.892,
|
242 |
+
"eval_steps_per_second": 2.925,
|
243 |
+
"step": 1500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 122.77227722772277,
|
247 |
+
"grad_norm": 0.9546501636505127,
|
248 |
+
"learning_rate": 7.75e-05,
|
249 |
+
"loss": 0.3934,
|
250 |
+
"step": 1550
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 126.73267326732673,
|
254 |
+
"grad_norm": 1.1335992813110352,
|
255 |
+
"learning_rate": 8e-05,
|
256 |
+
"loss": 0.3927,
|
257 |
+
"step": 1600
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 130.69306930693068,
|
261 |
+
"grad_norm": 1.905771017074585,
|
262 |
+
"learning_rate": 8.25e-05,
|
263 |
+
"loss": 0.3895,
|
264 |
+
"step": 1650
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 134.65346534653466,
|
268 |
+
"grad_norm": 1.129404067993164,
|
269 |
+
"learning_rate": 8.5e-05,
|
270 |
+
"loss": 0.3897,
|
271 |
+
"step": 1700
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 138.6138613861386,
|
275 |
+
"grad_norm": 0.9640969038009644,
|
276 |
+
"learning_rate": 8.75e-05,
|
277 |
+
"loss": 0.3894,
|
278 |
+
"step": 1750
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 142.5742574257426,
|
282 |
+
"grad_norm": 0.9840293526649475,
|
283 |
+
"learning_rate": 9e-05,
|
284 |
+
"loss": 0.3862,
|
285 |
+
"step": 1800
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 146.53465346534654,
|
289 |
+
"grad_norm": 2.770336627960205,
|
290 |
+
"learning_rate": 9.250000000000001e-05,
|
291 |
+
"loss": 0.3861,
|
292 |
+
"step": 1850
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 150.4950495049505,
|
296 |
+
"grad_norm": 1.7189514636993408,
|
297 |
+
"learning_rate": 9.5e-05,
|
298 |
+
"loss": 0.3914,
|
299 |
+
"step": 1900
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 154.45544554455446,
|
303 |
+
"grad_norm": 2.454707622528076,
|
304 |
+
"learning_rate": 9.75e-05,
|
305 |
+
"loss": 0.3848,
|
306 |
+
"step": 1950
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 158.41584158415841,
|
310 |
+
"grad_norm": 2.1555542945861816,
|
311 |
+
"learning_rate": 0.0001,
|
312 |
+
"loss": 0.3814,
|
313 |
+
"step": 2000
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 158.41584158415841,
|
317 |
+
"eval_loss": 0.3966299593448639,
|
318 |
+
"eval_runtime": 7.7159,
|
319 |
+
"eval_samples_per_second": 23.329,
|
320 |
+
"eval_steps_per_second": 2.981,
|
321 |
+
"step": 2000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 162.37623762376236,
|
325 |
+
"grad_norm": 1.1228975057601929,
|
326 |
+
"learning_rate": 9.916666666666667e-05,
|
327 |
+
"loss": 0.3817,
|
328 |
+
"step": 2050
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 166.33663366336634,
|
332 |
+
"grad_norm": 1.629294991493225,
|
333 |
+
"learning_rate": 9.833333333333333e-05,
|
334 |
+
"loss": 0.3813,
|
335 |
+
"step": 2100
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 170.2970297029703,
|
339 |
+
"grad_norm": 0.9008976221084595,
|
340 |
+
"learning_rate": 9.75e-05,
|
341 |
+
"loss": 0.377,
|
342 |
+
"step": 2150
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 174.25742574257427,
|
346 |
+
"grad_norm": 2.174643039703369,
|
347 |
+
"learning_rate": 9.666666666666667e-05,
|
348 |
+
"loss": 0.3737,
|
349 |
+
"step": 2200
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 178.21782178217822,
|
353 |
+
"grad_norm": 1.617219090461731,
|
354 |
+
"learning_rate": 9.583333333333334e-05,
|
355 |
+
"loss": 0.3736,
|
356 |
+
"step": 2250
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 182.17821782178217,
|
360 |
+
"grad_norm": 1.292871117591858,
|
361 |
+
"learning_rate": 9.5e-05,
|
362 |
+
"loss": 0.3786,
|
363 |
+
"step": 2300
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 186.13861386138615,
|
367 |
+
"grad_norm": 1.5530415773391724,
|
368 |
+
"learning_rate": 9.416666666666667e-05,
|
369 |
+
"loss": 0.3726,
|
370 |
+
"step": 2350
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 190.0990099009901,
|
374 |
+
"grad_norm": 0.9837754964828491,
|
375 |
+
"learning_rate": 9.333333333333334e-05,
|
376 |
+
"loss": 0.3713,
|
377 |
+
"step": 2400
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 194.05940594059405,
|
381 |
+
"grad_norm": 0.8343392610549927,
|
382 |
+
"learning_rate": 9.250000000000001e-05,
|
383 |
+
"loss": 0.3727,
|
384 |
+
"step": 2450
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 198.01980198019803,
|
388 |
+
"grad_norm": 2.9330906867980957,
|
389 |
+
"learning_rate": 9.166666666666667e-05,
|
390 |
+
"loss": 0.3688,
|
391 |
+
"step": 2500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 198.01980198019803,
|
395 |
+
"eval_loss": 0.40214845538139343,
|
396 |
+
"eval_runtime": 7.9273,
|
397 |
+
"eval_samples_per_second": 22.706,
|
398 |
+
"eval_steps_per_second": 2.901,
|
399 |
+
"step": 2500
|
400 |
+
}
|
401 |
+
],
|
402 |
+
"logging_steps": 50,
|
403 |
+
"max_steps": 8000,
|
404 |
+
"num_input_tokens_seen": 0,
|
405 |
+
"num_train_epochs": 667,
|
406 |
+
"save_steps": 500,
|
407 |
+
"stateful_callbacks": {
|
408 |
+
"TrainerControl": {
|
409 |
+
"args": {
|
410 |
+
"should_epoch_stop": false,
|
411 |
+
"should_evaluate": false,
|
412 |
+
"should_log": false,
|
413 |
+
"should_save": true,
|
414 |
+
"should_training_stop": false
|
415 |
+
},
|
416 |
+
"attributes": {}
|
417 |
+
}
|
418 |
+
},
|
419 |
+
"total_flos": 5.40291039934441e+16,
|
420 |
+
"train_batch_size": 16,
|
421 |
+
"trial_name": null,
|
422 |
+
"trial_params": null
|
423 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85df14de5cd709ebb874ec61066a56bc489b0cf6ac7193ea95d4fbf830394508
|
3 |
+
size 5304
|