mikhail-panzo commited on
Commit
870d5b3
1 Parent(s): 9cfb552

Training in progress, step 10000, checkpoint

Browse files
checkpoint-10000/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79
4
+ }
checkpoint-10000/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-10000/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-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d614dbc951f31ab1c1c7cb2d51ee381c875d4088cfce5461bad44c151ea7fe
3
+ size 577789320
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4794d0c35db11e4e6eab8dd632e2ac1840f780fcf14d2a7375054efd12a853
3
+ size 1155772233
checkpoint-10000/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-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65692b5e7ceb8b526903112dc578c08294dea38375f83722222b82a5ddfd72c6
3
+ size 14244
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9f7c891ead3460857869b782e8b1721461b0f2093b1455b002b8d67dda363b
3
+ size 1064
checkpoint-10000/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-10000/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-10000/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-10000/trainer_state.json ADDED
@@ -0,0 +1,1593 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.35580456256866455,
3
+ "best_model_checkpoint": "mikhail_panzo/zlm_b128_le5_s12000/checkpoint-10000",
4
+ "epoch": 16.756858638743456,
5
+ "eval_steps": 500,
6
+ "global_step": 10000,
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
+ "epoch": 7.625968586387435,
715
+ "grad_norm": 1.5206329822540283,
716
+ "learning_rate": 7.4530000000000005e-06,
717
+ "loss": 0.418,
718
+ "step": 4550
719
+ },
720
+ {
721
+ "epoch": 7.7097382198952875,
722
+ "grad_norm": 1.5614436864852905,
723
+ "learning_rate": 7.403e-06,
724
+ "loss": 0.4206,
725
+ "step": 4600
726
+ },
727
+ {
728
+ "epoch": 7.793507853403141,
729
+ "grad_norm": 1.9834551811218262,
730
+ "learning_rate": 7.353e-06,
731
+ "loss": 0.421,
732
+ "step": 4650
733
+ },
734
+ {
735
+ "epoch": 7.8772774869109945,
736
+ "grad_norm": 2.0368449687957764,
737
+ "learning_rate": 7.303e-06,
738
+ "loss": 0.4206,
739
+ "step": 4700
740
+ },
741
+ {
742
+ "epoch": 7.961047120418848,
743
+ "grad_norm": 1.4374061822891235,
744
+ "learning_rate": 7.253e-06,
745
+ "loss": 0.4127,
746
+ "step": 4750
747
+ },
748
+ {
749
+ "epoch": 8.044816753926701,
750
+ "grad_norm": 1.9674043655395508,
751
+ "learning_rate": 7.203000000000001e-06,
752
+ "loss": 0.4111,
753
+ "step": 4800
754
+ },
755
+ {
756
+ "epoch": 8.128586387434556,
757
+ "grad_norm": 1.4639081954956055,
758
+ "learning_rate": 7.153000000000001e-06,
759
+ "loss": 0.4153,
760
+ "step": 4850
761
+ },
762
+ {
763
+ "epoch": 8.212356020942408,
764
+ "grad_norm": 1.189695954322815,
765
+ "learning_rate": 7.103000000000001e-06,
766
+ "loss": 0.4257,
767
+ "step": 4900
768
+ },
769
+ {
770
+ "epoch": 8.296125654450261,
771
+ "grad_norm": 1.5426299571990967,
772
+ "learning_rate": 7.053000000000001e-06,
773
+ "loss": 0.4119,
774
+ "step": 4950
775
+ },
776
+ {
777
+ "epoch": 8.379895287958115,
778
+ "grad_norm": 1.526410460472107,
779
+ "learning_rate": 7.0030000000000005e-06,
780
+ "loss": 0.4185,
781
+ "step": 5000
782
+ },
783
+ {
784
+ "epoch": 8.379895287958115,
785
+ "eval_loss": 0.3761734962463379,
786
+ "eval_runtime": 274.1558,
787
+ "eval_samples_per_second": 30.964,
788
+ "eval_steps_per_second": 3.874,
789
+ "step": 5000
790
+ },
791
+ {
792
+ "epoch": 8.463664921465968,
793
+ "grad_norm": 1.3419328927993774,
794
+ "learning_rate": 6.953000000000001e-06,
795
+ "loss": 0.412,
796
+ "step": 5050
797
+ },
798
+ {
799
+ "epoch": 8.547434554973822,
800
+ "grad_norm": 2.1306657791137695,
801
+ "learning_rate": 6.903000000000001e-06,
802
+ "loss": 0.4108,
803
+ "step": 5100
804
+ },
805
+ {
806
+ "epoch": 8.631204188481675,
807
+ "grad_norm": 2.0914053916931152,
808
+ "learning_rate": 6.853000000000001e-06,
809
+ "loss": 0.4177,
810
+ "step": 5150
811
+ },
812
+ {
813
+ "epoch": 8.71497382198953,
814
+ "grad_norm": 1.6214958429336548,
815
+ "learning_rate": 6.803000000000001e-06,
816
+ "loss": 0.4083,
817
+ "step": 5200
818
+ },
819
+ {
820
+ "epoch": 8.798743455497382,
821
+ "grad_norm": 1.5650039911270142,
822
+ "learning_rate": 6.753e-06,
823
+ "loss": 0.4118,
824
+ "step": 5250
825
+ },
826
+ {
827
+ "epoch": 8.882513089005236,
828
+ "grad_norm": 1.564424991607666,
829
+ "learning_rate": 6.703000000000001e-06,
830
+ "loss": 0.4093,
831
+ "step": 5300
832
+ },
833
+ {
834
+ "epoch": 8.966282722513089,
835
+ "grad_norm": 1.623558759689331,
836
+ "learning_rate": 6.6530000000000005e-06,
837
+ "loss": 0.412,
838
+ "step": 5350
839
+ },
840
+ {
841
+ "epoch": 9.050052356020942,
842
+ "grad_norm": 1.5212219953536987,
843
+ "learning_rate": 6.603e-06,
844
+ "loss": 0.4125,
845
+ "step": 5400
846
+ },
847
+ {
848
+ "epoch": 9.133821989528796,
849
+ "grad_norm": 2.202746629714966,
850
+ "learning_rate": 6.553000000000001e-06,
851
+ "loss": 0.4049,
852
+ "step": 5450
853
+ },
854
+ {
855
+ "epoch": 9.217591623036649,
856
+ "grad_norm": 1.6582872867584229,
857
+ "learning_rate": 6.503e-06,
858
+ "loss": 0.4093,
859
+ "step": 5500
860
+ },
861
+ {
862
+ "epoch": 9.217591623036649,
863
+ "eval_loss": 0.373293936252594,
864
+ "eval_runtime": 279.0862,
865
+ "eval_samples_per_second": 30.417,
866
+ "eval_steps_per_second": 3.805,
867
+ "step": 5500
868
+ },
869
+ {
870
+ "epoch": 9.301361256544503,
871
+ "grad_norm": 2.3431801795959473,
872
+ "learning_rate": 6.453000000000001e-06,
873
+ "loss": 0.4099,
874
+ "step": 5550
875
+ },
876
+ {
877
+ "epoch": 9.385130890052356,
878
+ "grad_norm": 1.7502645254135132,
879
+ "learning_rate": 6.403e-06,
880
+ "loss": 0.4097,
881
+ "step": 5600
882
+ },
883
+ {
884
+ "epoch": 9.46890052356021,
885
+ "grad_norm": 1.638600468635559,
886
+ "learning_rate": 6.353e-06,
887
+ "loss": 0.4068,
888
+ "step": 5650
889
+ },
890
+ {
891
+ "epoch": 9.552670157068063,
892
+ "grad_norm": 1.3677990436553955,
893
+ "learning_rate": 6.3030000000000005e-06,
894
+ "loss": 0.4086,
895
+ "step": 5700
896
+ },
897
+ {
898
+ "epoch": 9.636439790575917,
899
+ "grad_norm": 1.4438238143920898,
900
+ "learning_rate": 6.253e-06,
901
+ "loss": 0.4067,
902
+ "step": 5750
903
+ },
904
+ {
905
+ "epoch": 9.72020942408377,
906
+ "grad_norm": 1.7439764738082886,
907
+ "learning_rate": 6.204e-06,
908
+ "loss": 0.4085,
909
+ "step": 5800
910
+ },
911
+ {
912
+ "epoch": 9.803979057591622,
913
+ "grad_norm": 1.257203459739685,
914
+ "learning_rate": 6.154e-06,
915
+ "loss": 0.4069,
916
+ "step": 5850
917
+ },
918
+ {
919
+ "epoch": 9.887748691099477,
920
+ "grad_norm": 1.2076969146728516,
921
+ "learning_rate": 6.104000000000001e-06,
922
+ "loss": 0.4,
923
+ "step": 5900
924
+ },
925
+ {
926
+ "epoch": 9.97151832460733,
927
+ "grad_norm": 1.1376831531524658,
928
+ "learning_rate": 6.054000000000001e-06,
929
+ "loss": 0.4088,
930
+ "step": 5950
931
+ },
932
+ {
933
+ "epoch": 10.055287958115183,
934
+ "grad_norm": 1.4293948411941528,
935
+ "learning_rate": 6.004000000000001e-06,
936
+ "loss": 0.4012,
937
+ "step": 6000
938
+ },
939
+ {
940
+ "epoch": 10.055287958115183,
941
+ "eval_loss": 0.3698088824748993,
942
+ "eval_runtime": 276.0941,
943
+ "eval_samples_per_second": 30.747,
944
+ "eval_steps_per_second": 3.847,
945
+ "step": 6000
946
+ },
947
+ {
948
+ "epoch": 10.139057591623036,
949
+ "grad_norm": 1.1719565391540527,
950
+ "learning_rate": 5.954000000000001e-06,
951
+ "loss": 0.4036,
952
+ "step": 6050
953
+ },
954
+ {
955
+ "epoch": 10.22282722513089,
956
+ "grad_norm": 1.0520621538162231,
957
+ "learning_rate": 5.9040000000000006e-06,
958
+ "loss": 0.4074,
959
+ "step": 6100
960
+ },
961
+ {
962
+ "epoch": 10.306596858638743,
963
+ "grad_norm": 1.9477139711380005,
964
+ "learning_rate": 5.854000000000001e-06,
965
+ "loss": 0.4049,
966
+ "step": 6150
967
+ },
968
+ {
969
+ "epoch": 10.390366492146597,
970
+ "grad_norm": 1.147050142288208,
971
+ "learning_rate": 5.804000000000001e-06,
972
+ "loss": 0.4009,
973
+ "step": 6200
974
+ },
975
+ {
976
+ "epoch": 10.47413612565445,
977
+ "grad_norm": 1.32716703414917,
978
+ "learning_rate": 5.754e-06,
979
+ "loss": 0.4037,
980
+ "step": 6250
981
+ },
982
+ {
983
+ "epoch": 10.557905759162304,
984
+ "grad_norm": 1.6168224811553955,
985
+ "learning_rate": 5.704000000000001e-06,
986
+ "loss": 0.401,
987
+ "step": 6300
988
+ },
989
+ {
990
+ "epoch": 10.641675392670157,
991
+ "grad_norm": 1.3314645290374756,
992
+ "learning_rate": 5.654e-06,
993
+ "loss": 0.4039,
994
+ "step": 6350
995
+ },
996
+ {
997
+ "epoch": 10.72544502617801,
998
+ "grad_norm": 1.0647807121276855,
999
+ "learning_rate": 5.604000000000001e-06,
1000
+ "loss": 0.4039,
1001
+ "step": 6400
1002
+ },
1003
+ {
1004
+ "epoch": 10.809214659685864,
1005
+ "grad_norm": 1.3919047117233276,
1006
+ "learning_rate": 5.5540000000000005e-06,
1007
+ "loss": 0.4014,
1008
+ "step": 6450
1009
+ },
1010
+ {
1011
+ "epoch": 10.892984293193717,
1012
+ "grad_norm": 1.3037397861480713,
1013
+ "learning_rate": 5.504e-06,
1014
+ "loss": 0.403,
1015
+ "step": 6500
1016
+ },
1017
+ {
1018
+ "epoch": 10.892984293193717,
1019
+ "eval_loss": 0.3670424520969391,
1020
+ "eval_runtime": 281.4305,
1021
+ "eval_samples_per_second": 30.164,
1022
+ "eval_steps_per_second": 3.774,
1023
+ "step": 6500
1024
+ },
1025
+ {
1026
+ "epoch": 10.976753926701571,
1027
+ "grad_norm": 0.9927046298980713,
1028
+ "learning_rate": 5.454000000000001e-06,
1029
+ "loss": 0.4002,
1030
+ "step": 6550
1031
+ },
1032
+ {
1033
+ "epoch": 11.060523560209424,
1034
+ "grad_norm": 2.82547926902771,
1035
+ "learning_rate": 5.404e-06,
1036
+ "loss": 0.4035,
1037
+ "step": 6600
1038
+ },
1039
+ {
1040
+ "epoch": 11.144293193717278,
1041
+ "grad_norm": 1.4662278890609741,
1042
+ "learning_rate": 5.354e-06,
1043
+ "loss": 0.4031,
1044
+ "step": 6650
1045
+ },
1046
+ {
1047
+ "epoch": 11.22806282722513,
1048
+ "grad_norm": 0.9803363084793091,
1049
+ "learning_rate": 5.304e-06,
1050
+ "loss": 0.3984,
1051
+ "step": 6700
1052
+ },
1053
+ {
1054
+ "epoch": 11.311832460732985,
1055
+ "grad_norm": 1.580372929573059,
1056
+ "learning_rate": 5.254e-06,
1057
+ "loss": 0.3987,
1058
+ "step": 6750
1059
+ },
1060
+ {
1061
+ "epoch": 11.395602094240838,
1062
+ "grad_norm": 1.5269379615783691,
1063
+ "learning_rate": 5.2040000000000005e-06,
1064
+ "loss": 0.3999,
1065
+ "step": 6800
1066
+ },
1067
+ {
1068
+ "epoch": 11.479371727748692,
1069
+ "grad_norm": 1.2878773212432861,
1070
+ "learning_rate": 5.154e-06,
1071
+ "loss": 0.3991,
1072
+ "step": 6850
1073
+ },
1074
+ {
1075
+ "epoch": 11.563141361256545,
1076
+ "grad_norm": 1.2725164890289307,
1077
+ "learning_rate": 5.104e-06,
1078
+ "loss": 0.3979,
1079
+ "step": 6900
1080
+ },
1081
+ {
1082
+ "epoch": 11.646910994764397,
1083
+ "grad_norm": 2.5339043140411377,
1084
+ "learning_rate": 5.054e-06,
1085
+ "loss": 0.3966,
1086
+ "step": 6950
1087
+ },
1088
+ {
1089
+ "epoch": 11.730680628272252,
1090
+ "grad_norm": 1.1876580715179443,
1091
+ "learning_rate": 5.004e-06,
1092
+ "loss": 0.4017,
1093
+ "step": 7000
1094
+ },
1095
+ {
1096
+ "epoch": 11.730680628272252,
1097
+ "eval_loss": 0.3627295196056366,
1098
+ "eval_runtime": 270.756,
1099
+ "eval_samples_per_second": 31.353,
1100
+ "eval_steps_per_second": 3.922,
1101
+ "step": 7000
1102
+ },
1103
+ {
1104
+ "epoch": 11.814450261780104,
1105
+ "grad_norm": 1.1595991849899292,
1106
+ "learning_rate": 4.954e-06,
1107
+ "loss": 0.4003,
1108
+ "step": 7050
1109
+ },
1110
+ {
1111
+ "epoch": 11.898219895287959,
1112
+ "grad_norm": 1.2361228466033936,
1113
+ "learning_rate": 4.904000000000001e-06,
1114
+ "loss": 0.4019,
1115
+ "step": 7100
1116
+ },
1117
+ {
1118
+ "epoch": 11.981989528795811,
1119
+ "grad_norm": 1.5332549810409546,
1120
+ "learning_rate": 4.8540000000000005e-06,
1121
+ "loss": 0.395,
1122
+ "step": 7150
1123
+ },
1124
+ {
1125
+ "epoch": 12.065759162303666,
1126
+ "grad_norm": 1.4963312149047852,
1127
+ "learning_rate": 4.804e-06,
1128
+ "loss": 0.406,
1129
+ "step": 7200
1130
+ },
1131
+ {
1132
+ "epoch": 12.149528795811518,
1133
+ "grad_norm": 1.5511187314987183,
1134
+ "learning_rate": 4.7540000000000006e-06,
1135
+ "loss": 0.3991,
1136
+ "step": 7250
1137
+ },
1138
+ {
1139
+ "epoch": 12.233298429319373,
1140
+ "grad_norm": 1.8427493572235107,
1141
+ "learning_rate": 4.704e-06,
1142
+ "loss": 0.3982,
1143
+ "step": 7300
1144
+ },
1145
+ {
1146
+ "epoch": 12.317068062827225,
1147
+ "grad_norm": 1.3739436864852905,
1148
+ "learning_rate": 4.654e-06,
1149
+ "loss": 0.3966,
1150
+ "step": 7350
1151
+ },
1152
+ {
1153
+ "epoch": 12.400837696335078,
1154
+ "grad_norm": 1.659621238708496,
1155
+ "learning_rate": 4.604e-06,
1156
+ "loss": 0.4019,
1157
+ "step": 7400
1158
+ },
1159
+ {
1160
+ "epoch": 12.484607329842932,
1161
+ "grad_norm": 1.8510388135910034,
1162
+ "learning_rate": 4.554000000000001e-06,
1163
+ "loss": 0.4013,
1164
+ "step": 7450
1165
+ },
1166
+ {
1167
+ "epoch": 12.568376963350785,
1168
+ "grad_norm": 1.100199580192566,
1169
+ "learning_rate": 4.504e-06,
1170
+ "loss": 0.3961,
1171
+ "step": 7500
1172
+ },
1173
+ {
1174
+ "epoch": 12.568376963350785,
1175
+ "eval_loss": 0.36272022128105164,
1176
+ "eval_runtime": 264.6514,
1177
+ "eval_samples_per_second": 32.076,
1178
+ "eval_steps_per_second": 4.013,
1179
+ "step": 7500
1180
+ },
1181
+ {
1182
+ "epoch": 12.652146596858639,
1183
+ "grad_norm": 1.439460039138794,
1184
+ "learning_rate": 4.454000000000001e-06,
1185
+ "loss": 0.3937,
1186
+ "step": 7550
1187
+ },
1188
+ {
1189
+ "epoch": 12.735916230366492,
1190
+ "grad_norm": 1.253373622894287,
1191
+ "learning_rate": 4.4040000000000005e-06,
1192
+ "loss": 0.4011,
1193
+ "step": 7600
1194
+ },
1195
+ {
1196
+ "epoch": 12.819685863874346,
1197
+ "grad_norm": 1.6404370069503784,
1198
+ "learning_rate": 4.354e-06,
1199
+ "loss": 0.4016,
1200
+ "step": 7650
1201
+ },
1202
+ {
1203
+ "epoch": 12.903455497382199,
1204
+ "grad_norm": 1.3606590032577515,
1205
+ "learning_rate": 4.304000000000001e-06,
1206
+ "loss": 0.3964,
1207
+ "step": 7700
1208
+ },
1209
+ {
1210
+ "epoch": 12.987225130890053,
1211
+ "grad_norm": 1.249391794204712,
1212
+ "learning_rate": 4.254e-06,
1213
+ "loss": 0.4013,
1214
+ "step": 7750
1215
+ },
1216
+ {
1217
+ "epoch": 13.070994764397906,
1218
+ "grad_norm": 1.1404308080673218,
1219
+ "learning_rate": 4.205e-06,
1220
+ "loss": 0.3939,
1221
+ "step": 7800
1222
+ },
1223
+ {
1224
+ "epoch": 13.15476439790576,
1225
+ "grad_norm": 0.9418945908546448,
1226
+ "learning_rate": 4.155e-06,
1227
+ "loss": 0.3968,
1228
+ "step": 7850
1229
+ },
1230
+ {
1231
+ "epoch": 13.238534031413613,
1232
+ "grad_norm": 1.3190369606018066,
1233
+ "learning_rate": 4.1050000000000005e-06,
1234
+ "loss": 0.3977,
1235
+ "step": 7900
1236
+ },
1237
+ {
1238
+ "epoch": 13.322303664921465,
1239
+ "grad_norm": 1.2260388135910034,
1240
+ "learning_rate": 4.055000000000001e-06,
1241
+ "loss": 0.3973,
1242
+ "step": 7950
1243
+ },
1244
+ {
1245
+ "epoch": 13.40607329842932,
1246
+ "grad_norm": 1.035477638244629,
1247
+ "learning_rate": 4.005000000000001e-06,
1248
+ "loss": 0.3957,
1249
+ "step": 8000
1250
+ },
1251
+ {
1252
+ "epoch": 13.40607329842932,
1253
+ "eval_loss": 0.3603293001651764,
1254
+ "eval_runtime": 270.7314,
1255
+ "eval_samples_per_second": 31.356,
1256
+ "eval_steps_per_second": 3.923,
1257
+ "step": 8000
1258
+ },
1259
+ {
1260
+ "epoch": 13.489842931937172,
1261
+ "grad_norm": 1.4767895936965942,
1262
+ "learning_rate": 3.955e-06,
1263
+ "loss": 0.3921,
1264
+ "step": 8050
1265
+ },
1266
+ {
1267
+ "epoch": 13.573612565445027,
1268
+ "grad_norm": 15.019492149353027,
1269
+ "learning_rate": 3.905000000000001e-06,
1270
+ "loss": 0.3947,
1271
+ "step": 8100
1272
+ },
1273
+ {
1274
+ "epoch": 13.65738219895288,
1275
+ "grad_norm": 1.3216609954833984,
1276
+ "learning_rate": 3.855e-06,
1277
+ "loss": 0.3969,
1278
+ "step": 8150
1279
+ },
1280
+ {
1281
+ "epoch": 13.741151832460734,
1282
+ "grad_norm": 1.0909982919692993,
1283
+ "learning_rate": 3.8050000000000004e-06,
1284
+ "loss": 0.3916,
1285
+ "step": 8200
1286
+ },
1287
+ {
1288
+ "epoch": 13.824921465968586,
1289
+ "grad_norm": 1.6264184713363647,
1290
+ "learning_rate": 3.7550000000000005e-06,
1291
+ "loss": 0.3951,
1292
+ "step": 8250
1293
+ },
1294
+ {
1295
+ "epoch": 13.90869109947644,
1296
+ "grad_norm": 1.1289631128311157,
1297
+ "learning_rate": 3.705e-06,
1298
+ "loss": 0.3926,
1299
+ "step": 8300
1300
+ },
1301
+ {
1302
+ "epoch": 13.992460732984293,
1303
+ "grad_norm": 1.1617991924285889,
1304
+ "learning_rate": 3.655e-06,
1305
+ "loss": 0.393,
1306
+ "step": 8350
1307
+ },
1308
+ {
1309
+ "epoch": 14.076230366492146,
1310
+ "grad_norm": 1.1278605461120605,
1311
+ "learning_rate": 3.6050000000000002e-06,
1312
+ "loss": 0.3969,
1313
+ "step": 8400
1314
+ },
1315
+ {
1316
+ "epoch": 14.16,
1317
+ "grad_norm": 0.9024301767349243,
1318
+ "learning_rate": 3.5550000000000003e-06,
1319
+ "loss": 0.3888,
1320
+ "step": 8450
1321
+ },
1322
+ {
1323
+ "epoch": 14.243769633507853,
1324
+ "grad_norm": 0.9253320097923279,
1325
+ "learning_rate": 3.505e-06,
1326
+ "loss": 0.3919,
1327
+ "step": 8500
1328
+ },
1329
+ {
1330
+ "epoch": 14.243769633507853,
1331
+ "eval_loss": 0.35886332392692566,
1332
+ "eval_runtime": 262.8233,
1333
+ "eval_samples_per_second": 32.299,
1334
+ "eval_steps_per_second": 4.041,
1335
+ "step": 8500
1336
+ },
1337
+ {
1338
+ "epoch": 14.327539267015707,
1339
+ "grad_norm": 1.3649754524230957,
1340
+ "learning_rate": 3.455e-06,
1341
+ "loss": 0.3961,
1342
+ "step": 8550
1343
+ },
1344
+ {
1345
+ "epoch": 14.41130890052356,
1346
+ "grad_norm": 1.2764108180999756,
1347
+ "learning_rate": 3.4050000000000004e-06,
1348
+ "loss": 0.3946,
1349
+ "step": 8600
1350
+ },
1351
+ {
1352
+ "epoch": 14.495078534031414,
1353
+ "grad_norm": 1.174688458442688,
1354
+ "learning_rate": 3.3550000000000005e-06,
1355
+ "loss": 0.3955,
1356
+ "step": 8650
1357
+ },
1358
+ {
1359
+ "epoch": 14.578848167539267,
1360
+ "grad_norm": 1.0795891284942627,
1361
+ "learning_rate": 3.3050000000000005e-06,
1362
+ "loss": 0.3933,
1363
+ "step": 8700
1364
+ },
1365
+ {
1366
+ "epoch": 14.662617801047121,
1367
+ "grad_norm": 0.9259040355682373,
1368
+ "learning_rate": 3.255e-06,
1369
+ "loss": 0.3913,
1370
+ "step": 8750
1371
+ },
1372
+ {
1373
+ "epoch": 14.746387434554974,
1374
+ "grad_norm": 1.1176104545593262,
1375
+ "learning_rate": 3.2050000000000002e-06,
1376
+ "loss": 0.3942,
1377
+ "step": 8800
1378
+ },
1379
+ {
1380
+ "epoch": 14.830157068062828,
1381
+ "grad_norm": 1.0351334810256958,
1382
+ "learning_rate": 3.1550000000000003e-06,
1383
+ "loss": 0.3981,
1384
+ "step": 8850
1385
+ },
1386
+ {
1387
+ "epoch": 14.91392670157068,
1388
+ "grad_norm": 2.326068878173828,
1389
+ "learning_rate": 3.1050000000000003e-06,
1390
+ "loss": 0.3948,
1391
+ "step": 8900
1392
+ },
1393
+ {
1394
+ "epoch": 14.997696335078533,
1395
+ "grad_norm": 1.4447543621063232,
1396
+ "learning_rate": 3.0550000000000004e-06,
1397
+ "loss": 0.3908,
1398
+ "step": 8950
1399
+ },
1400
+ {
1401
+ "epoch": 15.081465968586388,
1402
+ "grad_norm": 1.365200161933899,
1403
+ "learning_rate": 3.005e-06,
1404
+ "loss": 0.3933,
1405
+ "step": 9000
1406
+ },
1407
+ {
1408
+ "epoch": 15.081465968586388,
1409
+ "eval_loss": 0.35749351978302,
1410
+ "eval_runtime": 283.7549,
1411
+ "eval_samples_per_second": 29.917,
1412
+ "eval_steps_per_second": 3.743,
1413
+ "step": 9000
1414
+ },
1415
+ {
1416
+ "epoch": 15.16523560209424,
1417
+ "grad_norm": 1.0825339555740356,
1418
+ "learning_rate": 2.955e-06,
1419
+ "loss": 0.3923,
1420
+ "step": 9050
1421
+ },
1422
+ {
1423
+ "epoch": 15.249005235602095,
1424
+ "grad_norm": 1.0156179666519165,
1425
+ "learning_rate": 2.905e-06,
1426
+ "loss": 0.3913,
1427
+ "step": 9100
1428
+ },
1429
+ {
1430
+ "epoch": 15.332774869109947,
1431
+ "grad_norm": 1.0104918479919434,
1432
+ "learning_rate": 2.855e-06,
1433
+ "loss": 0.3893,
1434
+ "step": 9150
1435
+ },
1436
+ {
1437
+ "epoch": 15.416544502617802,
1438
+ "grad_norm": 0.9494548439979553,
1439
+ "learning_rate": 2.8050000000000007e-06,
1440
+ "loss": 0.391,
1441
+ "step": 9200
1442
+ },
1443
+ {
1444
+ "epoch": 15.500314136125654,
1445
+ "grad_norm": 1.2736467123031616,
1446
+ "learning_rate": 2.7550000000000003e-06,
1447
+ "loss": 0.3946,
1448
+ "step": 9250
1449
+ },
1450
+ {
1451
+ "epoch": 15.584083769633509,
1452
+ "grad_norm": 0.81021648645401,
1453
+ "learning_rate": 2.7050000000000004e-06,
1454
+ "loss": 0.3961,
1455
+ "step": 9300
1456
+ },
1457
+ {
1458
+ "epoch": 15.667853403141361,
1459
+ "grad_norm": 1.0645405054092407,
1460
+ "learning_rate": 2.6550000000000004e-06,
1461
+ "loss": 0.3912,
1462
+ "step": 9350
1463
+ },
1464
+ {
1465
+ "epoch": 15.751623036649214,
1466
+ "grad_norm": 4.980652809143066,
1467
+ "learning_rate": 2.6050000000000005e-06,
1468
+ "loss": 0.3902,
1469
+ "step": 9400
1470
+ },
1471
+ {
1472
+ "epoch": 15.835392670157068,
1473
+ "grad_norm": 1.4880826473236084,
1474
+ "learning_rate": 2.555e-06,
1475
+ "loss": 0.3939,
1476
+ "step": 9450
1477
+ },
1478
+ {
1479
+ "epoch": 15.91916230366492,
1480
+ "grad_norm": 0.8299314379692078,
1481
+ "learning_rate": 2.505e-06,
1482
+ "loss": 0.3928,
1483
+ "step": 9500
1484
+ },
1485
+ {
1486
+ "epoch": 15.91916230366492,
1487
+ "eval_loss": 0.3572653830051422,
1488
+ "eval_runtime": 261.7949,
1489
+ "eval_samples_per_second": 32.426,
1490
+ "eval_steps_per_second": 4.057,
1491
+ "step": 9500
1492
+ },
1493
+ {
1494
+ "epoch": 16.002931937172775,
1495
+ "grad_norm": 1.1118539571762085,
1496
+ "learning_rate": 2.4550000000000002e-06,
1497
+ "loss": 0.3938,
1498
+ "step": 9550
1499
+ },
1500
+ {
1501
+ "epoch": 16.086701570680628,
1502
+ "grad_norm": 1.1094309091567993,
1503
+ "learning_rate": 2.4050000000000003e-06,
1504
+ "loss": 0.3903,
1505
+ "step": 9600
1506
+ },
1507
+ {
1508
+ "epoch": 16.17047120418848,
1509
+ "grad_norm": 0.9645286202430725,
1510
+ "learning_rate": 2.355e-06,
1511
+ "loss": 0.3928,
1512
+ "step": 9650
1513
+ },
1514
+ {
1515
+ "epoch": 16.254240837696337,
1516
+ "grad_norm": 1.376489520072937,
1517
+ "learning_rate": 2.3050000000000004e-06,
1518
+ "loss": 0.39,
1519
+ "step": 9700
1520
+ },
1521
+ {
1522
+ "epoch": 16.33801047120419,
1523
+ "grad_norm": 1.0610970258712769,
1524
+ "learning_rate": 2.2550000000000004e-06,
1525
+ "loss": 0.3861,
1526
+ "step": 9750
1527
+ },
1528
+ {
1529
+ "epoch": 16.42178010471204,
1530
+ "grad_norm": 1.481760859489441,
1531
+ "learning_rate": 2.205e-06,
1532
+ "loss": 0.3964,
1533
+ "step": 9800
1534
+ },
1535
+ {
1536
+ "epoch": 16.505549738219894,
1537
+ "grad_norm": 1.0688999891281128,
1538
+ "learning_rate": 2.155e-06,
1539
+ "loss": 0.3965,
1540
+ "step": 9850
1541
+ },
1542
+ {
1543
+ "epoch": 16.589319371727747,
1544
+ "grad_norm": 1.2465980052947998,
1545
+ "learning_rate": 2.105e-06,
1546
+ "loss": 0.3904,
1547
+ "step": 9900
1548
+ },
1549
+ {
1550
+ "epoch": 16.673089005235603,
1551
+ "grad_norm": 2.9295108318328857,
1552
+ "learning_rate": 2.0550000000000002e-06,
1553
+ "loss": 0.3944,
1554
+ "step": 9950
1555
+ },
1556
+ {
1557
+ "epoch": 16.756858638743456,
1558
+ "grad_norm": 1.1967060565948486,
1559
+ "learning_rate": 2.0050000000000003e-06,
1560
+ "loss": 0.3951,
1561
+ "step": 10000
1562
+ },
1563
+ {
1564
+ "epoch": 16.756858638743456,
1565
+ "eval_loss": 0.35580456256866455,
1566
+ "eval_runtime": 268.9079,
1567
+ "eval_samples_per_second": 31.568,
1568
+ "eval_steps_per_second": 3.949,
1569
+ "step": 10000
1570
+ }
1571
+ ],
1572
+ "logging_steps": 50,
1573
+ "max_steps": 12000,
1574
+ "num_input_tokens_seen": 0,
1575
+ "num_train_epochs": 21,
1576
+ "save_steps": 500,
1577
+ "stateful_callbacks": {
1578
+ "TrainerControl": {
1579
+ "args": {
1580
+ "should_epoch_stop": false,
1581
+ "should_evaluate": false,
1582
+ "should_log": false,
1583
+ "should_save": true,
1584
+ "should_training_stop": false
1585
+ },
1586
+ "attributes": {}
1587
+ }
1588
+ },
1589
+ "total_flos": 1.7942143460477702e+17,
1590
+ "train_batch_size": 16,
1591
+ "trial_name": null,
1592
+ "trial_params": null
1593
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3271e94c7230c79ad74395a607b3d03fda68860c191e572f07beb52b230aeff7
3
+ size 5304