abhinavp commited on
Commit
d16acb6
1 Parent(s): 9b82ec8

Training in progress, epoch 0, checkpoint

Browse files
checkpoint-228960/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RNNForLanguageModeling"
4
+ ],
5
+ "bidirectional": false,
6
+ "dropout_p": 0.1,
7
+ "emb_init_range": 0.1,
8
+ "embedding_dim": 1024,
9
+ "embedding_kwargs": {},
10
+ "hidden_dim": 1024,
11
+ "lin_init_range": 0.03125,
12
+ "lm_in_features": 1024,
13
+ "model_type": "rnn",
14
+ "num_layers": 2,
15
+ "output_last_state": false,
16
+ "output_recurrent_outputs": false,
17
+ "recur_init_range": 0.03125,
18
+ "rnn_kwargs": {},
19
+ "rnn_type": "LSTM",
20
+ "tie_weights": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.33.3",
23
+ "vocab_size": 50002
24
+ }
checkpoint-228960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fde9b69c5bd42c849c9b656b1485610ba3fd2d97b7a2546fc73854178b2a7c
3
+ size 544373707
checkpoint-228960/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa40bb3528b98c786dfd1bb626182c3b53ccc4e508e544e1a3bc129fb36f266
3
+ size 272184705
checkpoint-228960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f502b978ff5bd694096cbf00a0e79ceaf3fca80b3c417c4adff7ed5f9a3237f4
3
+ size 14575
checkpoint-228960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8956414fa10b52259534b34d19d0c99ee2122d367fd5b40d1298c58c07bdfe
3
+ size 627
checkpoint-228960/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "<eos>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-228960/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-228960/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<eos>",
4
+ "max_length": null,
5
+ "model_max_length": 512,
6
+ "pad_to_multiple_of": null,
7
+ "pad_token": "<pad>",
8
+ "pad_token_type_id": 0,
9
+ "padding_side": "right",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "unk_token": "<unk>"
12
+ }
checkpoint-228960/trainer_state.json ADDED
@@ -0,0 +1,2731 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 4.330287933349609,
3
+ "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/lstm/1/checkpoints/checkpoint-228960",
4
+ "epoch": 0.025000606015738065,
5
+ "eval_steps": 10,
6
+ "global_step": 228960,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 4.999998362119627e-05,
14
+ "loss": 10.8191,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 4.999161405248948e-05,
20
+ "loss": 7.5474,
21
+ "step": 512
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 4.998322810497896e-05,
26
+ "loss": 7.0562,
27
+ "step": 1024
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 4.997484215746844e-05,
32
+ "loss": 6.9904,
33
+ "step": 1536
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 4.996645620995792e-05,
38
+ "loss": 6.9436,
39
+ "step": 2048
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "learning_rate": 4.99580702624474e-05,
44
+ "loss": 6.8394,
45
+ "step": 2560
46
+ },
47
+ {
48
+ "epoch": 0.0,
49
+ "learning_rate": 4.994968431493688e-05,
50
+ "loss": 6.682,
51
+ "step": 3072
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "learning_rate": 4.994129836742636e-05,
56
+ "loss": 6.5858,
57
+ "step": 3584
58
+ },
59
+ {
60
+ "epoch": 0.0,
61
+ "learning_rate": 4.993292879871958e-05,
62
+ "loss": 6.4898,
63
+ "step": 4096
64
+ },
65
+ {
66
+ "epoch": 0.0,
67
+ "learning_rate": 4.992454285120906e-05,
68
+ "loss": 6.4265,
69
+ "step": 4608
70
+ },
71
+ {
72
+ "epoch": 0.0,
73
+ "learning_rate": 4.991615690369854e-05,
74
+ "loss": 6.3737,
75
+ "step": 5120
76
+ },
77
+ {
78
+ "epoch": 0.0,
79
+ "learning_rate": 4.990777095618801e-05,
80
+ "loss": 6.3089,
81
+ "step": 5632
82
+ },
83
+ {
84
+ "epoch": 0.0,
85
+ "learning_rate": 4.989938500867749e-05,
86
+ "loss": 6.2352,
87
+ "step": 6144
88
+ },
89
+ {
90
+ "epoch": 0.0,
91
+ "learning_rate": 4.989099906116697e-05,
92
+ "loss": 6.1763,
93
+ "step": 6656
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "learning_rate": 4.988261311365645e-05,
98
+ "loss": 6.127,
99
+ "step": 7168
100
+ },
101
+ {
102
+ "epoch": 0.0,
103
+ "learning_rate": 4.987422716614593e-05,
104
+ "loss": 6.0632,
105
+ "step": 7680
106
+ },
107
+ {
108
+ "epoch": 0.0,
109
+ "learning_rate": 4.986584121863541e-05,
110
+ "loss": 6.0303,
111
+ "step": 8192
112
+ },
113
+ {
114
+ "epoch": 0.0,
115
+ "learning_rate": 4.985745527112489e-05,
116
+ "loss": 5.9826,
117
+ "step": 8704
118
+ },
119
+ {
120
+ "epoch": 0.0,
121
+ "learning_rate": 4.984906932361437e-05,
122
+ "loss": 5.9348,
123
+ "step": 9216
124
+ },
125
+ {
126
+ "epoch": 0.0,
127
+ "learning_rate": 4.984068337610385e-05,
128
+ "loss": 5.9037,
129
+ "step": 9728
130
+ },
131
+ {
132
+ "epoch": 0.0,
133
+ "learning_rate": 4.983229742859333e-05,
134
+ "loss": 5.8696,
135
+ "step": 10240
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "learning_rate": 4.982391148108281e-05,
140
+ "loss": 5.8321,
141
+ "step": 10752
142
+ },
143
+ {
144
+ "epoch": 0.0,
145
+ "learning_rate": 4.981552553357229e-05,
146
+ "loss": 5.8074,
147
+ "step": 11264
148
+ },
149
+ {
150
+ "epoch": 0.0,
151
+ "learning_rate": 4.980713958606178e-05,
152
+ "loss": 5.7667,
153
+ "step": 11776
154
+ },
155
+ {
156
+ "epoch": 0.0,
157
+ "learning_rate": 4.979875363855125e-05,
158
+ "loss": 5.749,
159
+ "step": 12288
160
+ },
161
+ {
162
+ "epoch": 0.0,
163
+ "learning_rate": 4.979036769104073e-05,
164
+ "loss": 5.7241,
165
+ "step": 12800
166
+ },
167
+ {
168
+ "epoch": 0.0,
169
+ "learning_rate": 4.978198174353021e-05,
170
+ "loss": 5.699,
171
+ "step": 13312
172
+ },
173
+ {
174
+ "epoch": 0.0,
175
+ "learning_rate": 4.9773612174823426e-05,
176
+ "loss": 5.6708,
177
+ "step": 13824
178
+ },
179
+ {
180
+ "epoch": 0.0,
181
+ "learning_rate": 4.97652262273129e-05,
182
+ "loss": 5.638,
183
+ "step": 14336
184
+ },
185
+ {
186
+ "epoch": 0.0,
187
+ "learning_rate": 4.975684027980238e-05,
188
+ "loss": 5.6277,
189
+ "step": 14848
190
+ },
191
+ {
192
+ "epoch": 0.01,
193
+ "learning_rate": 4.974845433229186e-05,
194
+ "loss": 5.6054,
195
+ "step": 15360
196
+ },
197
+ {
198
+ "epoch": 0.01,
199
+ "learning_rate": 4.974008476358507e-05,
200
+ "loss": 5.5934,
201
+ "step": 15872
202
+ },
203
+ {
204
+ "epoch": 0.01,
205
+ "learning_rate": 4.973169881607455e-05,
206
+ "loss": 5.5672,
207
+ "step": 16384
208
+ },
209
+ {
210
+ "epoch": 0.01,
211
+ "learning_rate": 4.972331286856403e-05,
212
+ "loss": 5.5493,
213
+ "step": 16896
214
+ },
215
+ {
216
+ "epoch": 0.01,
217
+ "learning_rate": 4.9714926921053515e-05,
218
+ "loss": 5.5388,
219
+ "step": 17408
220
+ },
221
+ {
222
+ "epoch": 0.01,
223
+ "learning_rate": 4.9706540973542995e-05,
224
+ "loss": 5.5212,
225
+ "step": 17920
226
+ },
227
+ {
228
+ "epoch": 0.01,
229
+ "learning_rate": 4.9698171404836204e-05,
230
+ "loss": 5.5041,
231
+ "step": 18432
232
+ },
233
+ {
234
+ "epoch": 0.01,
235
+ "learning_rate": 4.968980183612942e-05,
236
+ "loss": 5.4724,
237
+ "step": 18944
238
+ },
239
+ {
240
+ "epoch": 0.01,
241
+ "learning_rate": 4.96814158886189e-05,
242
+ "loss": 5.4676,
243
+ "step": 19456
244
+ },
245
+ {
246
+ "epoch": 0.01,
247
+ "learning_rate": 4.967302994110837e-05,
248
+ "loss": 5.4366,
249
+ "step": 19968
250
+ },
251
+ {
252
+ "epoch": 0.01,
253
+ "learning_rate": 4.966464399359785e-05,
254
+ "loss": 5.4384,
255
+ "step": 20480
256
+ },
257
+ {
258
+ "epoch": 0.01,
259
+ "learning_rate": 4.965625804608733e-05,
260
+ "loss": 5.4126,
261
+ "step": 20992
262
+ },
263
+ {
264
+ "epoch": 0.01,
265
+ "learning_rate": 4.964787209857681e-05,
266
+ "loss": 5.4148,
267
+ "step": 21504
268
+ },
269
+ {
270
+ "epoch": 0.01,
271
+ "learning_rate": 4.963948615106629e-05,
272
+ "loss": 5.3857,
273
+ "step": 22016
274
+ },
275
+ {
276
+ "epoch": 0.01,
277
+ "learning_rate": 4.963110020355577e-05,
278
+ "loss": 5.3782,
279
+ "step": 22528
280
+ },
281
+ {
282
+ "epoch": 0.01,
283
+ "learning_rate": 4.962273063484898e-05,
284
+ "loss": 5.3726,
285
+ "step": 23040
286
+ },
287
+ {
288
+ "epoch": 0.01,
289
+ "learning_rate": 4.961434468733847e-05,
290
+ "loss": 5.3643,
291
+ "step": 23552
292
+ },
293
+ {
294
+ "epoch": 0.01,
295
+ "learning_rate": 4.960595873982795e-05,
296
+ "loss": 5.3487,
297
+ "step": 24064
298
+ },
299
+ {
300
+ "epoch": 0.01,
301
+ "learning_rate": 4.959757279231743e-05,
302
+ "loss": 5.3248,
303
+ "step": 24576
304
+ },
305
+ {
306
+ "epoch": 0.01,
307
+ "learning_rate": 4.958918684480691e-05,
308
+ "loss": 5.3222,
309
+ "step": 25088
310
+ },
311
+ {
312
+ "epoch": 0.01,
313
+ "learning_rate": 4.958081727610012e-05,
314
+ "loss": 5.3262,
315
+ "step": 25600
316
+ },
317
+ {
318
+ "epoch": 0.01,
319
+ "learning_rate": 4.95724313285896e-05,
320
+ "loss": 5.3132,
321
+ "step": 26112
322
+ },
323
+ {
324
+ "epoch": 0.01,
325
+ "learning_rate": 4.956404538107908e-05,
326
+ "loss": 5.2916,
327
+ "step": 26624
328
+ },
329
+ {
330
+ "epoch": 0.01,
331
+ "learning_rate": 4.955565943356856e-05,
332
+ "loss": 5.2797,
333
+ "step": 27136
334
+ },
335
+ {
336
+ "epoch": 0.01,
337
+ "learning_rate": 4.954728986486177e-05,
338
+ "loss": 5.2774,
339
+ "step": 27648
340
+ },
341
+ {
342
+ "epoch": 0.01,
343
+ "learning_rate": 4.953890391735125e-05,
344
+ "loss": 5.265,
345
+ "step": 28160
346
+ },
347
+ {
348
+ "epoch": 0.01,
349
+ "learning_rate": 4.9530517969840727e-05,
350
+ "loss": 5.2739,
351
+ "step": 28672
352
+ },
353
+ {
354
+ "epoch": 0.01,
355
+ "learning_rate": 4.9522132022330207e-05,
356
+ "loss": 5.2307,
357
+ "step": 29184
358
+ },
359
+ {
360
+ "epoch": 0.01,
361
+ "learning_rate": 4.9513746074819686e-05,
362
+ "loss": 5.2445,
363
+ "step": 29696
364
+ },
365
+ {
366
+ "epoch": 0.01,
367
+ "learning_rate": 4.95053765061129e-05,
368
+ "loss": 5.2294,
369
+ "step": 30208
370
+ },
371
+ {
372
+ "epoch": 0.01,
373
+ "learning_rate": 4.949699055860238e-05,
374
+ "loss": 5.2149,
375
+ "step": 30720
376
+ },
377
+ {
378
+ "epoch": 0.01,
379
+ "learning_rate": 4.948860461109186e-05,
380
+ "loss": 5.2218,
381
+ "step": 31232
382
+ },
383
+ {
384
+ "epoch": 0.01,
385
+ "learning_rate": 4.948021866358134e-05,
386
+ "loss": 5.2001,
387
+ "step": 31744
388
+ },
389
+ {
390
+ "epoch": 0.01,
391
+ "learning_rate": 4.947183271607082e-05,
392
+ "loss": 5.19,
393
+ "step": 32256
394
+ },
395
+ {
396
+ "epoch": 0.01,
397
+ "learning_rate": 4.94634467685603e-05,
398
+ "loss": 5.1862,
399
+ "step": 32768
400
+ },
401
+ {
402
+ "epoch": 0.01,
403
+ "learning_rate": 4.945507719985351e-05,
404
+ "loss": 5.1966,
405
+ "step": 33280
406
+ },
407
+ {
408
+ "epoch": 0.01,
409
+ "learning_rate": 4.944669125234299e-05,
410
+ "loss": 5.173,
411
+ "step": 33792
412
+ },
413
+ {
414
+ "epoch": 0.01,
415
+ "learning_rate": 4.943830530483247e-05,
416
+ "loss": 5.1667,
417
+ "step": 34304
418
+ },
419
+ {
420
+ "epoch": 0.01,
421
+ "learning_rate": 4.942991935732195e-05,
422
+ "loss": 5.152,
423
+ "step": 34816
424
+ },
425
+ {
426
+ "epoch": 0.01,
427
+ "learning_rate": 4.942154978861516e-05,
428
+ "loss": 5.1446,
429
+ "step": 35328
430
+ },
431
+ {
432
+ "epoch": 0.01,
433
+ "learning_rate": 4.941316384110464e-05,
434
+ "loss": 5.1489,
435
+ "step": 35840
436
+ },
437
+ {
438
+ "epoch": 0.01,
439
+ "learning_rate": 4.940477789359412e-05,
440
+ "loss": 5.1518,
441
+ "step": 36352
442
+ },
443
+ {
444
+ "epoch": 0.01,
445
+ "learning_rate": 4.93963919460836e-05,
446
+ "loss": 5.1258,
447
+ "step": 36864
448
+ },
449
+ {
450
+ "epoch": 0.01,
451
+ "learning_rate": 4.938800599857309e-05,
452
+ "loss": 5.1368,
453
+ "step": 37376
454
+ },
455
+ {
456
+ "epoch": 0.01,
457
+ "learning_rate": 4.9379636429866296e-05,
458
+ "loss": 5.1374,
459
+ "step": 37888
460
+ },
461
+ {
462
+ "epoch": 0.01,
463
+ "learning_rate": 4.9371250482355776e-05,
464
+ "loss": 5.1157,
465
+ "step": 38400
466
+ },
467
+ {
468
+ "epoch": 0.01,
469
+ "learning_rate": 4.9362880913648985e-05,
470
+ "loss": 5.0994,
471
+ "step": 38912
472
+ },
473
+ {
474
+ "epoch": 0.01,
475
+ "learning_rate": 4.9354494966138465e-05,
476
+ "loss": 5.0998,
477
+ "step": 39424
478
+ },
479
+ {
480
+ "epoch": 0.01,
481
+ "learning_rate": 4.9346109018627945e-05,
482
+ "loss": 5.0942,
483
+ "step": 39936
484
+ },
485
+ {
486
+ "epoch": 0.01,
487
+ "learning_rate": 4.9337723071117425e-05,
488
+ "loss": 5.0812,
489
+ "step": 40448
490
+ },
491
+ {
492
+ "epoch": 0.01,
493
+ "learning_rate": 4.9329337123606905e-05,
494
+ "loss": 5.0807,
495
+ "step": 40960
496
+ },
497
+ {
498
+ "epoch": 0.01,
499
+ "learning_rate": 4.932095117609638e-05,
500
+ "loss": 5.0829,
501
+ "step": 41472
502
+ },
503
+ {
504
+ "epoch": 0.01,
505
+ "learning_rate": 4.931256522858586e-05,
506
+ "loss": 5.0821,
507
+ "step": 41984
508
+ },
509
+ {
510
+ "epoch": 0.01,
511
+ "learning_rate": 4.930417928107534e-05,
512
+ "loss": 5.0646,
513
+ "step": 42496
514
+ },
515
+ {
516
+ "epoch": 0.01,
517
+ "learning_rate": 4.9295809712368554e-05,
518
+ "loss": 5.0424,
519
+ "step": 43008
520
+ },
521
+ {
522
+ "epoch": 0.01,
523
+ "learning_rate": 4.9287423764858034e-05,
524
+ "loss": 5.049,
525
+ "step": 43520
526
+ },
527
+ {
528
+ "epoch": 0.01,
529
+ "learning_rate": 4.9279037817347514e-05,
530
+ "loss": 5.0537,
531
+ "step": 44032
532
+ },
533
+ {
534
+ "epoch": 0.01,
535
+ "learning_rate": 4.9270651869836994e-05,
536
+ "loss": 5.042,
537
+ "step": 44544
538
+ },
539
+ {
540
+ "epoch": 0.01,
541
+ "learning_rate": 4.9262265922326474e-05,
542
+ "loss": 5.0399,
543
+ "step": 45056
544
+ },
545
+ {
546
+ "epoch": 0.01,
547
+ "learning_rate": 4.925389635361968e-05,
548
+ "loss": 5.0213,
549
+ "step": 45568
550
+ },
551
+ {
552
+ "epoch": 0.02,
553
+ "learning_rate": 4.92455267849129e-05,
554
+ "loss": 5.0208,
555
+ "step": 46080
556
+ },
557
+ {
558
+ "epoch": 0.02,
559
+ "learning_rate": 4.923714083740238e-05,
560
+ "loss": 5.0139,
561
+ "step": 46592
562
+ },
563
+ {
564
+ "epoch": 0.02,
565
+ "learning_rate": 4.922875488989185e-05,
566
+ "loss": 5.0135,
567
+ "step": 47104
568
+ },
569
+ {
570
+ "epoch": 0.02,
571
+ "learning_rate": 4.922038532118507e-05,
572
+ "loss": 5.0129,
573
+ "step": 47616
574
+ },
575
+ {
576
+ "epoch": 0.02,
577
+ "learning_rate": 4.921199937367455e-05,
578
+ "loss": 4.9952,
579
+ "step": 48128
580
+ },
581
+ {
582
+ "epoch": 0.02,
583
+ "learning_rate": 4.920361342616403e-05,
584
+ "loss": 5.012,
585
+ "step": 48640
586
+ },
587
+ {
588
+ "epoch": 0.02,
589
+ "learning_rate": 4.919522747865351e-05,
590
+ "loss": 4.9972,
591
+ "step": 49152
592
+ },
593
+ {
594
+ "epoch": 0.02,
595
+ "learning_rate": 4.918684153114299e-05,
596
+ "loss": 4.9764,
597
+ "step": 49664
598
+ },
599
+ {
600
+ "epoch": 0.02,
601
+ "learning_rate": 4.917845558363247e-05,
602
+ "loss": 4.9733,
603
+ "step": 50176
604
+ },
605
+ {
606
+ "epoch": 0.02,
607
+ "learning_rate": 4.917006963612195e-05,
608
+ "loss": 4.9738,
609
+ "step": 50688
610
+ },
611
+ {
612
+ "epoch": 0.02,
613
+ "learning_rate": 4.916168368861143e-05,
614
+ "loss": 4.971,
615
+ "step": 51200
616
+ },
617
+ {
618
+ "epoch": 0.02,
619
+ "learning_rate": 4.915329774110091e-05,
620
+ "loss": 4.9701,
621
+ "step": 51712
622
+ },
623
+ {
624
+ "epoch": 0.02,
625
+ "learning_rate": 4.914491179359039e-05,
626
+ "loss": 4.9629,
627
+ "step": 52224
628
+ },
629
+ {
630
+ "epoch": 0.02,
631
+ "learning_rate": 4.913652584607987e-05,
632
+ "loss": 4.9552,
633
+ "step": 52736
634
+ },
635
+ {
636
+ "epoch": 0.02,
637
+ "learning_rate": 4.9128156277373076e-05,
638
+ "loss": 4.9505,
639
+ "step": 53248
640
+ },
641
+ {
642
+ "epoch": 0.02,
643
+ "learning_rate": 4.9119770329862556e-05,
644
+ "loss": 4.9288,
645
+ "step": 53760
646
+ },
647
+ {
648
+ "epoch": 0.02,
649
+ "learning_rate": 4.9111384382352036e-05,
650
+ "loss": 4.9351,
651
+ "step": 54272
652
+ },
653
+ {
654
+ "epoch": 0.02,
655
+ "learning_rate": 4.9102998434841516e-05,
656
+ "loss": 4.9326,
657
+ "step": 54784
658
+ },
659
+ {
660
+ "epoch": 0.02,
661
+ "learning_rate": 4.9094612487330996e-05,
662
+ "loss": 4.9279,
663
+ "step": 55296
664
+ },
665
+ {
666
+ "epoch": 0.02,
667
+ "learning_rate": 4.9086226539820476e-05,
668
+ "loss": 4.9228,
669
+ "step": 55808
670
+ },
671
+ {
672
+ "epoch": 0.02,
673
+ "learning_rate": 4.907784059230996e-05,
674
+ "loss": 4.9293,
675
+ "step": 56320
676
+ },
677
+ {
678
+ "epoch": 0.02,
679
+ "learning_rate": 4.906947102360317e-05,
680
+ "loss": 4.9039,
681
+ "step": 56832
682
+ },
683
+ {
684
+ "epoch": 0.02,
685
+ "learning_rate": 4.906108507609265e-05,
686
+ "loss": 4.9066,
687
+ "step": 57344
688
+ },
689
+ {
690
+ "epoch": 0.02,
691
+ "learning_rate": 4.905269912858213e-05,
692
+ "loss": 4.9007,
693
+ "step": 57856
694
+ },
695
+ {
696
+ "epoch": 0.02,
697
+ "learning_rate": 4.904431318107161e-05,
698
+ "loss": 4.9075,
699
+ "step": 58368
700
+ },
701
+ {
702
+ "epoch": 0.02,
703
+ "learning_rate": 4.903592723356109e-05,
704
+ "loss": 4.9122,
705
+ "step": 58880
706
+ },
707
+ {
708
+ "epoch": 0.02,
709
+ "learning_rate": 4.9027541286050565e-05,
710
+ "loss": 4.8949,
711
+ "step": 59392
712
+ },
713
+ {
714
+ "epoch": 0.02,
715
+ "learning_rate": 4.901917171734378e-05,
716
+ "loss": 4.8927,
717
+ "step": 59904
718
+ },
719
+ {
720
+ "epoch": 0.02,
721
+ "learning_rate": 4.901078576983326e-05,
722
+ "loss": 4.8831,
723
+ "step": 60416
724
+ },
725
+ {
726
+ "epoch": 0.02,
727
+ "learning_rate": 4.900239982232274e-05,
728
+ "loss": 4.8897,
729
+ "step": 60928
730
+ },
731
+ {
732
+ "epoch": 0.02,
733
+ "learning_rate": 4.8994013874812214e-05,
734
+ "loss": 4.8835,
735
+ "step": 61440
736
+ },
737
+ {
738
+ "epoch": 0.02,
739
+ "learning_rate": 4.89856279273017e-05,
740
+ "loss": 4.8797,
741
+ "step": 61952
742
+ },
743
+ {
744
+ "epoch": 0.02,
745
+ "learning_rate": 4.897724197979118e-05,
746
+ "loss": 4.8706,
747
+ "step": 62464
748
+ },
749
+ {
750
+ "epoch": 0.02,
751
+ "learning_rate": 4.896885603228066e-05,
752
+ "loss": 4.8661,
753
+ "step": 62976
754
+ },
755
+ {
756
+ "epoch": 0.02,
757
+ "learning_rate": 4.896047008477014e-05,
758
+ "loss": 4.8592,
759
+ "step": 63488
760
+ },
761
+ {
762
+ "epoch": 0.02,
763
+ "learning_rate": 4.895208413725962e-05,
764
+ "loss": 4.8493,
765
+ "step": 64000
766
+ },
767
+ {
768
+ "epoch": 0.02,
769
+ "learning_rate": 4.894371456855283e-05,
770
+ "loss": 4.8547,
771
+ "step": 64512
772
+ },
773
+ {
774
+ "epoch": 0.02,
775
+ "learning_rate": 4.893532862104231e-05,
776
+ "loss": 4.8485,
777
+ "step": 65024
778
+ },
779
+ {
780
+ "epoch": 0.02,
781
+ "learning_rate": 4.892694267353179e-05,
782
+ "loss": 4.8435,
783
+ "step": 65536
784
+ },
785
+ {
786
+ "epoch": 0.02,
787
+ "learning_rate": 4.891855672602127e-05,
788
+ "loss": 4.8358,
789
+ "step": 66048
790
+ },
791
+ {
792
+ "epoch": 0.02,
793
+ "learning_rate": 4.891017077851075e-05,
794
+ "loss": 4.8512,
795
+ "step": 66560
796
+ },
797
+ {
798
+ "epoch": 0.02,
799
+ "learning_rate": 4.890178483100023e-05,
800
+ "loss": 4.8501,
801
+ "step": 67072
802
+ },
803
+ {
804
+ "epoch": 0.02,
805
+ "learning_rate": 4.889341526229344e-05,
806
+ "loss": 4.8396,
807
+ "step": 67584
808
+ },
809
+ {
810
+ "epoch": 0.02,
811
+ "learning_rate": 4.888504569358665e-05,
812
+ "loss": 4.8285,
813
+ "step": 68096
814
+ },
815
+ {
816
+ "epoch": 0.02,
817
+ "learning_rate": 4.8876659746076134e-05,
818
+ "loss": 4.8275,
819
+ "step": 68608
820
+ },
821
+ {
822
+ "epoch": 0.02,
823
+ "learning_rate": 4.8868273798565614e-05,
824
+ "loss": 4.8306,
825
+ "step": 69120
826
+ },
827
+ {
828
+ "epoch": 0.02,
829
+ "learning_rate": 4.8859887851055094e-05,
830
+ "loss": 4.8264,
831
+ "step": 69632
832
+ },
833
+ {
834
+ "epoch": 0.02,
835
+ "learning_rate": 4.8851501903544574e-05,
836
+ "loss": 4.8222,
837
+ "step": 70144
838
+ },
839
+ {
840
+ "epoch": 0.02,
841
+ "learning_rate": 4.8843115956034054e-05,
842
+ "loss": 4.8184,
843
+ "step": 70656
844
+ },
845
+ {
846
+ "epoch": 0.02,
847
+ "learning_rate": 4.8834730008523534e-05,
848
+ "loss": 4.815,
849
+ "step": 71168
850
+ },
851
+ {
852
+ "epoch": 0.02,
853
+ "learning_rate": 4.8826344061013014e-05,
854
+ "loss": 4.8085,
855
+ "step": 71680
856
+ },
857
+ {
858
+ "epoch": 0.02,
859
+ "learning_rate": 4.8817958113502494e-05,
860
+ "loss": 4.8032,
861
+ "step": 72192
862
+ },
863
+ {
864
+ "epoch": 0.02,
865
+ "learning_rate": 4.8809572165991974e-05,
866
+ "loss": 4.8079,
867
+ "step": 72704
868
+ },
869
+ {
870
+ "epoch": 0.02,
871
+ "learning_rate": 4.8801186218481454e-05,
872
+ "loss": 4.7961,
873
+ "step": 73216
874
+ },
875
+ {
876
+ "epoch": 0.02,
877
+ "learning_rate": 4.879281664977466e-05,
878
+ "loss": 4.7909,
879
+ "step": 73728
880
+ },
881
+ {
882
+ "epoch": 0.02,
883
+ "learning_rate": 4.878443070226414e-05,
884
+ "loss": 4.7983,
885
+ "step": 74240
886
+ },
887
+ {
888
+ "epoch": 0.02,
889
+ "learning_rate": 4.877604475475362e-05,
890
+ "loss": 4.7846,
891
+ "step": 74752
892
+ },
893
+ {
894
+ "epoch": 0.02,
895
+ "learning_rate": 4.87676588072431e-05,
896
+ "loss": 4.793,
897
+ "step": 75264
898
+ },
899
+ {
900
+ "epoch": 0.02,
901
+ "learning_rate": 4.875927285973258e-05,
902
+ "loss": 4.782,
903
+ "step": 75776
904
+ },
905
+ {
906
+ "epoch": 0.02,
907
+ "learning_rate": 4.87509032910258e-05,
908
+ "loss": 4.7741,
909
+ "step": 76288
910
+ },
911
+ {
912
+ "epoch": 0.03,
913
+ "eval_loss": 4.741952896118164,
914
+ "eval_runtime": 347.3647,
915
+ "eval_samples_per_second": 1098.531,
916
+ "eval_steps_per_second": 34.33,
917
+ "step": 76320
918
+ },
919
+ {
920
+ "epoch": 1.0,
921
+ "learning_rate": 4.874251734351528e-05,
922
+ "loss": 4.7684,
923
+ "step": 76800
924
+ },
925
+ {
926
+ "epoch": 1.0,
927
+ "learning_rate": 4.873413139600475e-05,
928
+ "loss": 4.7679,
929
+ "step": 77312
930
+ },
931
+ {
932
+ "epoch": 1.0,
933
+ "learning_rate": 4.872576182729797e-05,
934
+ "loss": 4.7801,
935
+ "step": 77824
936
+ },
937
+ {
938
+ "epoch": 1.0,
939
+ "learning_rate": 4.871737587978745e-05,
940
+ "loss": 4.7668,
941
+ "step": 78336
942
+ },
943
+ {
944
+ "epoch": 1.0,
945
+ "learning_rate": 4.870898993227693e-05,
946
+ "loss": 4.7692,
947
+ "step": 78848
948
+ },
949
+ {
950
+ "epoch": 1.0,
951
+ "learning_rate": 4.87006039847664e-05,
952
+ "loss": 4.756,
953
+ "step": 79360
954
+ },
955
+ {
956
+ "epoch": 1.0,
957
+ "learning_rate": 4.869221803725588e-05,
958
+ "loss": 4.7591,
959
+ "step": 79872
960
+ },
961
+ {
962
+ "epoch": 1.0,
963
+ "learning_rate": 4.868383208974536e-05,
964
+ "loss": 4.743,
965
+ "step": 80384
966
+ },
967
+ {
968
+ "epoch": 1.0,
969
+ "learning_rate": 4.867544614223484e-05,
970
+ "loss": 4.7566,
971
+ "step": 80896
972
+ },
973
+ {
974
+ "epoch": 1.0,
975
+ "learning_rate": 4.866706019472432e-05,
976
+ "loss": 4.7545,
977
+ "step": 81408
978
+ },
979
+ {
980
+ "epoch": 1.0,
981
+ "learning_rate": 4.86586742472138e-05,
982
+ "loss": 4.7603,
983
+ "step": 81920
984
+ },
985
+ {
986
+ "epoch": 1.0,
987
+ "learning_rate": 4.8650304678507016e-05,
988
+ "loss": 4.7405,
989
+ "step": 82432
990
+ },
991
+ {
992
+ "epoch": 1.0,
993
+ "learning_rate": 4.8641918730996496e-05,
994
+ "loss": 4.7387,
995
+ "step": 82944
996
+ },
997
+ {
998
+ "epoch": 1.0,
999
+ "learning_rate": 4.8633532783485976e-05,
1000
+ "loss": 4.7343,
1001
+ "step": 83456
1002
+ },
1003
+ {
1004
+ "epoch": 1.0,
1005
+ "learning_rate": 4.8625146835975456e-05,
1006
+ "loss": 4.726,
1007
+ "step": 83968
1008
+ },
1009
+ {
1010
+ "epoch": 1.0,
1011
+ "learning_rate": 4.8616760888464936e-05,
1012
+ "loss": 4.7295,
1013
+ "step": 84480
1014
+ },
1015
+ {
1016
+ "epoch": 1.0,
1017
+ "learning_rate": 4.8608374940954416e-05,
1018
+ "loss": 4.7363,
1019
+ "step": 84992
1020
+ },
1021
+ {
1022
+ "epoch": 1.0,
1023
+ "learning_rate": 4.8600005372247625e-05,
1024
+ "loss": 4.7194,
1025
+ "step": 85504
1026
+ },
1027
+ {
1028
+ "epoch": 1.0,
1029
+ "learning_rate": 4.8591619424737105e-05,
1030
+ "loss": 4.7201,
1031
+ "step": 86016
1032
+ },
1033
+ {
1034
+ "epoch": 1.0,
1035
+ "learning_rate": 4.8583233477226585e-05,
1036
+ "loss": 4.735,
1037
+ "step": 86528
1038
+ },
1039
+ {
1040
+ "epoch": 1.0,
1041
+ "learning_rate": 4.8574847529716065e-05,
1042
+ "loss": 4.7232,
1043
+ "step": 87040
1044
+ },
1045
+ {
1046
+ "epoch": 1.0,
1047
+ "learning_rate": 4.8566477961009274e-05,
1048
+ "loss": 4.7218,
1049
+ "step": 87552
1050
+ },
1051
+ {
1052
+ "epoch": 1.0,
1053
+ "learning_rate": 4.8558092013498754e-05,
1054
+ "loss": 4.7101,
1055
+ "step": 88064
1056
+ },
1057
+ {
1058
+ "epoch": 1.0,
1059
+ "learning_rate": 4.854970606598824e-05,
1060
+ "loss": 4.7232,
1061
+ "step": 88576
1062
+ },
1063
+ {
1064
+ "epoch": 1.0,
1065
+ "learning_rate": 4.854132011847772e-05,
1066
+ "loss": 4.7093,
1067
+ "step": 89088
1068
+ },
1069
+ {
1070
+ "epoch": 1.0,
1071
+ "learning_rate": 4.85329341709672e-05,
1072
+ "loss": 4.7072,
1073
+ "step": 89600
1074
+ },
1075
+ {
1076
+ "epoch": 1.0,
1077
+ "learning_rate": 4.852456460226041e-05,
1078
+ "loss": 4.703,
1079
+ "step": 90112
1080
+ },
1081
+ {
1082
+ "epoch": 1.0,
1083
+ "learning_rate": 4.851617865474989e-05,
1084
+ "loss": 4.6972,
1085
+ "step": 90624
1086
+ },
1087
+ {
1088
+ "epoch": 1.0,
1089
+ "learning_rate": 4.850779270723937e-05,
1090
+ "loss": 4.6902,
1091
+ "step": 91136
1092
+ },
1093
+ {
1094
+ "epoch": 1.01,
1095
+ "learning_rate": 4.849940675972885e-05,
1096
+ "loss": 4.692,
1097
+ "step": 91648
1098
+ },
1099
+ {
1100
+ "epoch": 1.01,
1101
+ "learning_rate": 4.849102081221833e-05,
1102
+ "loss": 4.7025,
1103
+ "step": 92160
1104
+ },
1105
+ {
1106
+ "epoch": 1.01,
1107
+ "learning_rate": 4.848263486470781e-05,
1108
+ "loss": 4.6971,
1109
+ "step": 92672
1110
+ },
1111
+ {
1112
+ "epoch": 1.01,
1113
+ "learning_rate": 4.847426529600102e-05,
1114
+ "loss": 4.6882,
1115
+ "step": 93184
1116
+ },
1117
+ {
1118
+ "epoch": 1.01,
1119
+ "learning_rate": 4.84658793484905e-05,
1120
+ "loss": 4.6979,
1121
+ "step": 93696
1122
+ },
1123
+ {
1124
+ "epoch": 1.01,
1125
+ "learning_rate": 4.845749340097998e-05,
1126
+ "loss": 4.6894,
1127
+ "step": 94208
1128
+ },
1129
+ {
1130
+ "epoch": 1.01,
1131
+ "learning_rate": 4.844910745346946e-05,
1132
+ "loss": 4.6875,
1133
+ "step": 94720
1134
+ },
1135
+ {
1136
+ "epoch": 1.01,
1137
+ "learning_rate": 4.8440737884762674e-05,
1138
+ "loss": 4.6746,
1139
+ "step": 95232
1140
+ },
1141
+ {
1142
+ "epoch": 1.01,
1143
+ "learning_rate": 4.8432351937252154e-05,
1144
+ "loss": 4.6753,
1145
+ "step": 95744
1146
+ },
1147
+ {
1148
+ "epoch": 1.01,
1149
+ "learning_rate": 4.8423965989741634e-05,
1150
+ "loss": 4.6641,
1151
+ "step": 96256
1152
+ },
1153
+ {
1154
+ "epoch": 1.01,
1155
+ "learning_rate": 4.8415580042231114e-05,
1156
+ "loss": 4.6747,
1157
+ "step": 96768
1158
+ },
1159
+ {
1160
+ "epoch": 1.01,
1161
+ "learning_rate": 4.840721047352432e-05,
1162
+ "loss": 4.6601,
1163
+ "step": 97280
1164
+ },
1165
+ {
1166
+ "epoch": 1.01,
1167
+ "learning_rate": 4.83988245260138e-05,
1168
+ "loss": 4.6734,
1169
+ "step": 97792
1170
+ },
1171
+ {
1172
+ "epoch": 1.01,
1173
+ "learning_rate": 4.839043857850328e-05,
1174
+ "loss": 4.6556,
1175
+ "step": 98304
1176
+ },
1177
+ {
1178
+ "epoch": 1.01,
1179
+ "learning_rate": 4.838205263099276e-05,
1180
+ "loss": 4.6638,
1181
+ "step": 98816
1182
+ },
1183
+ {
1184
+ "epoch": 1.01,
1185
+ "learning_rate": 4.8373666683482236e-05,
1186
+ "loss": 4.6621,
1187
+ "step": 99328
1188
+ },
1189
+ {
1190
+ "epoch": 1.01,
1191
+ "learning_rate": 4.8365280735971716e-05,
1192
+ "loss": 4.6611,
1193
+ "step": 99840
1194
+ },
1195
+ {
1196
+ "epoch": 1.01,
1197
+ "learning_rate": 4.8356894788461196e-05,
1198
+ "loss": 4.6551,
1199
+ "step": 100352
1200
+ },
1201
+ {
1202
+ "epoch": 1.01,
1203
+ "learning_rate": 4.834852521975441e-05,
1204
+ "loss": 4.6433,
1205
+ "step": 100864
1206
+ },
1207
+ {
1208
+ "epoch": 1.01,
1209
+ "learning_rate": 4.834013927224389e-05,
1210
+ "loss": 4.6412,
1211
+ "step": 101376
1212
+ },
1213
+ {
1214
+ "epoch": 1.01,
1215
+ "learning_rate": 4.833175332473337e-05,
1216
+ "loss": 4.659,
1217
+ "step": 101888
1218
+ },
1219
+ {
1220
+ "epoch": 1.01,
1221
+ "learning_rate": 4.832336737722285e-05,
1222
+ "loss": 4.6489,
1223
+ "step": 102400
1224
+ },
1225
+ {
1226
+ "epoch": 1.01,
1227
+ "learning_rate": 4.831498142971233e-05,
1228
+ "loss": 4.6443,
1229
+ "step": 102912
1230
+ },
1231
+ {
1232
+ "epoch": 1.01,
1233
+ "learning_rate": 4.830659548220181e-05,
1234
+ "loss": 4.6313,
1235
+ "step": 103424
1236
+ },
1237
+ {
1238
+ "epoch": 1.01,
1239
+ "learning_rate": 4.829820953469129e-05,
1240
+ "loss": 4.6415,
1241
+ "step": 103936
1242
+ },
1243
+ {
1244
+ "epoch": 1.01,
1245
+ "learning_rate": 4.82898399659845e-05,
1246
+ "loss": 4.6282,
1247
+ "step": 104448
1248
+ },
1249
+ {
1250
+ "epoch": 1.01,
1251
+ "learning_rate": 4.828145401847398e-05,
1252
+ "loss": 4.6545,
1253
+ "step": 104960
1254
+ },
1255
+ {
1256
+ "epoch": 1.01,
1257
+ "learning_rate": 4.827306807096346e-05,
1258
+ "loss": 4.6175,
1259
+ "step": 105472
1260
+ },
1261
+ {
1262
+ "epoch": 1.01,
1263
+ "learning_rate": 4.826468212345294e-05,
1264
+ "loss": 4.6399,
1265
+ "step": 105984
1266
+ },
1267
+ {
1268
+ "epoch": 1.01,
1269
+ "learning_rate": 4.825629617594242e-05,
1270
+ "loss": 4.6293,
1271
+ "step": 106496
1272
+ },
1273
+ {
1274
+ "epoch": 1.01,
1275
+ "learning_rate": 4.82479102284319e-05,
1276
+ "loss": 4.6187,
1277
+ "step": 107008
1278
+ },
1279
+ {
1280
+ "epoch": 1.01,
1281
+ "learning_rate": 4.823952428092138e-05,
1282
+ "loss": 4.6296,
1283
+ "step": 107520
1284
+ },
1285
+ {
1286
+ "epoch": 1.01,
1287
+ "learning_rate": 4.823113833341086e-05,
1288
+ "loss": 4.6248,
1289
+ "step": 108032
1290
+ },
1291
+ {
1292
+ "epoch": 1.01,
1293
+ "learning_rate": 4.8222768764704077e-05,
1294
+ "loss": 4.6091,
1295
+ "step": 108544
1296
+ },
1297
+ {
1298
+ "epoch": 1.01,
1299
+ "learning_rate": 4.8214382817193557e-05,
1300
+ "loss": 4.6171,
1301
+ "step": 109056
1302
+ },
1303
+ {
1304
+ "epoch": 1.01,
1305
+ "learning_rate": 4.8205996869683037e-05,
1306
+ "loss": 4.6293,
1307
+ "step": 109568
1308
+ },
1309
+ {
1310
+ "epoch": 1.01,
1311
+ "learning_rate": 4.8197610922172516e-05,
1312
+ "loss": 4.6132,
1313
+ "step": 110080
1314
+ },
1315
+ {
1316
+ "epoch": 1.01,
1317
+ "learning_rate": 4.8189241353465726e-05,
1318
+ "loss": 4.6107,
1319
+ "step": 110592
1320
+ },
1321
+ {
1322
+ "epoch": 1.01,
1323
+ "learning_rate": 4.8180855405955206e-05,
1324
+ "loss": 4.6082,
1325
+ "step": 111104
1326
+ },
1327
+ {
1328
+ "epoch": 1.01,
1329
+ "learning_rate": 4.8172502216052144e-05,
1330
+ "loss": 4.6029,
1331
+ "step": 111616
1332
+ },
1333
+ {
1334
+ "epoch": 1.01,
1335
+ "learning_rate": 4.8164116268541624e-05,
1336
+ "loss": 4.6119,
1337
+ "step": 112128
1338
+ },
1339
+ {
1340
+ "epoch": 1.01,
1341
+ "learning_rate": 4.8155730321031104e-05,
1342
+ "loss": 4.6251,
1343
+ "step": 112640
1344
+ },
1345
+ {
1346
+ "epoch": 1.01,
1347
+ "learning_rate": 4.8147344373520584e-05,
1348
+ "loss": 4.5999,
1349
+ "step": 113152
1350
+ },
1351
+ {
1352
+ "epoch": 1.01,
1353
+ "learning_rate": 4.8138958426010064e-05,
1354
+ "loss": 4.6179,
1355
+ "step": 113664
1356
+ },
1357
+ {
1358
+ "epoch": 1.01,
1359
+ "learning_rate": 4.813057247849955e-05,
1360
+ "loss": 4.6179,
1361
+ "step": 114176
1362
+ },
1363
+ {
1364
+ "epoch": 1.01,
1365
+ "learning_rate": 4.812218653098903e-05,
1366
+ "loss": 4.6057,
1367
+ "step": 114688
1368
+ },
1369
+ {
1370
+ "epoch": 1.01,
1371
+ "learning_rate": 4.811380058347851e-05,
1372
+ "loss": 4.5928,
1373
+ "step": 115200
1374
+ },
1375
+ {
1376
+ "epoch": 1.01,
1377
+ "learning_rate": 4.810541463596799e-05,
1378
+ "loss": 4.6043,
1379
+ "step": 115712
1380
+ },
1381
+ {
1382
+ "epoch": 1.01,
1383
+ "learning_rate": 4.809702868845747e-05,
1384
+ "loss": 4.5988,
1385
+ "step": 116224
1386
+ },
1387
+ {
1388
+ "epoch": 1.01,
1389
+ "learning_rate": 4.808864274094695e-05,
1390
+ "loss": 4.5911,
1391
+ "step": 116736
1392
+ },
1393
+ {
1394
+ "epoch": 1.01,
1395
+ "learning_rate": 4.808025679343642e-05,
1396
+ "loss": 4.5924,
1397
+ "step": 117248
1398
+ },
1399
+ {
1400
+ "epoch": 1.01,
1401
+ "learning_rate": 4.807188722472964e-05,
1402
+ "loss": 4.5963,
1403
+ "step": 117760
1404
+ },
1405
+ {
1406
+ "epoch": 1.01,
1407
+ "learning_rate": 4.806350127721912e-05,
1408
+ "loss": 4.6038,
1409
+ "step": 118272
1410
+ },
1411
+ {
1412
+ "epoch": 1.01,
1413
+ "learning_rate": 4.80551153297086e-05,
1414
+ "loss": 4.5919,
1415
+ "step": 118784
1416
+ },
1417
+ {
1418
+ "epoch": 1.01,
1419
+ "learning_rate": 4.804672938219807e-05,
1420
+ "loss": 4.5764,
1421
+ "step": 119296
1422
+ },
1423
+ {
1424
+ "epoch": 1.01,
1425
+ "learning_rate": 4.803835981349129e-05,
1426
+ "loss": 4.5863,
1427
+ "step": 119808
1428
+ },
1429
+ {
1430
+ "epoch": 1.01,
1431
+ "learning_rate": 4.802997386598077e-05,
1432
+ "loss": 4.5889,
1433
+ "step": 120320
1434
+ },
1435
+ {
1436
+ "epoch": 1.01,
1437
+ "learning_rate": 4.802158791847025e-05,
1438
+ "loss": 4.5849,
1439
+ "step": 120832
1440
+ },
1441
+ {
1442
+ "epoch": 1.01,
1443
+ "learning_rate": 4.801320197095973e-05,
1444
+ "loss": 4.5908,
1445
+ "step": 121344
1446
+ },
1447
+ {
1448
+ "epoch": 1.01,
1449
+ "learning_rate": 4.8004832402252944e-05,
1450
+ "loss": 4.5767,
1451
+ "step": 121856
1452
+ },
1453
+ {
1454
+ "epoch": 1.02,
1455
+ "learning_rate": 4.7996446454742424e-05,
1456
+ "loss": 4.5708,
1457
+ "step": 122368
1458
+ },
1459
+ {
1460
+ "epoch": 1.02,
1461
+ "learning_rate": 4.79880605072319e-05,
1462
+ "loss": 4.5729,
1463
+ "step": 122880
1464
+ },
1465
+ {
1466
+ "epoch": 1.02,
1467
+ "learning_rate": 4.797967455972138e-05,
1468
+ "loss": 4.5769,
1469
+ "step": 123392
1470
+ },
1471
+ {
1472
+ "epoch": 1.02,
1473
+ "learning_rate": 4.797130499101459e-05,
1474
+ "loss": 4.5755,
1475
+ "step": 123904
1476
+ },
1477
+ {
1478
+ "epoch": 1.02,
1479
+ "learning_rate": 4.796291904350407e-05,
1480
+ "loss": 4.5669,
1481
+ "step": 124416
1482
+ },
1483
+ {
1484
+ "epoch": 1.02,
1485
+ "learning_rate": 4.7954533095993546e-05,
1486
+ "loss": 4.5889,
1487
+ "step": 124928
1488
+ },
1489
+ {
1490
+ "epoch": 1.02,
1491
+ "learning_rate": 4.7946147148483026e-05,
1492
+ "loss": 4.5758,
1493
+ "step": 125440
1494
+ },
1495
+ {
1496
+ "epoch": 1.02,
1497
+ "learning_rate": 4.7937761200972506e-05,
1498
+ "loss": 4.5584,
1499
+ "step": 125952
1500
+ },
1501
+ {
1502
+ "epoch": 1.02,
1503
+ "learning_rate": 4.7929375253461986e-05,
1504
+ "loss": 4.5614,
1505
+ "step": 126464
1506
+ },
1507
+ {
1508
+ "epoch": 1.02,
1509
+ "learning_rate": 4.792098930595147e-05,
1510
+ "loss": 4.5651,
1511
+ "step": 126976
1512
+ },
1513
+ {
1514
+ "epoch": 1.02,
1515
+ "learning_rate": 4.791261973724468e-05,
1516
+ "loss": 4.5648,
1517
+ "step": 127488
1518
+ },
1519
+ {
1520
+ "epoch": 1.02,
1521
+ "learning_rate": 4.790423378973416e-05,
1522
+ "loss": 4.5645,
1523
+ "step": 128000
1524
+ },
1525
+ {
1526
+ "epoch": 1.02,
1527
+ "learning_rate": 4.789584784222364e-05,
1528
+ "loss": 4.5614,
1529
+ "step": 128512
1530
+ },
1531
+ {
1532
+ "epoch": 1.02,
1533
+ "learning_rate": 4.788746189471312e-05,
1534
+ "loss": 4.556,
1535
+ "step": 129024
1536
+ },
1537
+ {
1538
+ "epoch": 1.02,
1539
+ "learning_rate": 4.78790759472026e-05,
1540
+ "loss": 4.56,
1541
+ "step": 129536
1542
+ },
1543
+ {
1544
+ "epoch": 1.02,
1545
+ "learning_rate": 4.787068999969208e-05,
1546
+ "loss": 4.5356,
1547
+ "step": 130048
1548
+ },
1549
+ {
1550
+ "epoch": 1.02,
1551
+ "learning_rate": 4.786230405218156e-05,
1552
+ "loss": 4.5516,
1553
+ "step": 130560
1554
+ },
1555
+ {
1556
+ "epoch": 1.02,
1557
+ "learning_rate": 4.785391810467104e-05,
1558
+ "loss": 4.5463,
1559
+ "step": 131072
1560
+ },
1561
+ {
1562
+ "epoch": 1.02,
1563
+ "learning_rate": 4.784554853596425e-05,
1564
+ "loss": 4.5496,
1565
+ "step": 131584
1566
+ },
1567
+ {
1568
+ "epoch": 1.02,
1569
+ "learning_rate": 4.783717896725746e-05,
1570
+ "loss": 4.5434,
1571
+ "step": 132096
1572
+ },
1573
+ {
1574
+ "epoch": 1.02,
1575
+ "learning_rate": 4.782879301974694e-05,
1576
+ "loss": 4.5531,
1577
+ "step": 132608
1578
+ },
1579
+ {
1580
+ "epoch": 1.02,
1581
+ "learning_rate": 4.782040707223642e-05,
1582
+ "loss": 4.5343,
1583
+ "step": 133120
1584
+ },
1585
+ {
1586
+ "epoch": 1.02,
1587
+ "learning_rate": 4.7812021124725906e-05,
1588
+ "loss": 4.5372,
1589
+ "step": 133632
1590
+ },
1591
+ {
1592
+ "epoch": 1.02,
1593
+ "learning_rate": 4.7803635177215386e-05,
1594
+ "loss": 4.5391,
1595
+ "step": 134144
1596
+ },
1597
+ {
1598
+ "epoch": 1.02,
1599
+ "learning_rate": 4.7795249229704866e-05,
1600
+ "loss": 4.5392,
1601
+ "step": 134656
1602
+ },
1603
+ {
1604
+ "epoch": 1.02,
1605
+ "learning_rate": 4.7786863282194346e-05,
1606
+ "loss": 4.553,
1607
+ "step": 135168
1608
+ },
1609
+ {
1610
+ "epoch": 1.02,
1611
+ "learning_rate": 4.7778477334683826e-05,
1612
+ "loss": 4.542,
1613
+ "step": 135680
1614
+ },
1615
+ {
1616
+ "epoch": 1.02,
1617
+ "learning_rate": 4.7770091387173306e-05,
1618
+ "loss": 4.5389,
1619
+ "step": 136192
1620
+ },
1621
+ {
1622
+ "epoch": 1.02,
1623
+ "learning_rate": 4.7761705439662786e-05,
1624
+ "loss": 4.5328,
1625
+ "step": 136704
1626
+ },
1627
+ {
1628
+ "epoch": 1.02,
1629
+ "learning_rate": 4.7753352249759724e-05,
1630
+ "loss": 4.5381,
1631
+ "step": 137216
1632
+ },
1633
+ {
1634
+ "epoch": 1.02,
1635
+ "learning_rate": 4.7744966302249204e-05,
1636
+ "loss": 4.5379,
1637
+ "step": 137728
1638
+ },
1639
+ {
1640
+ "epoch": 1.02,
1641
+ "learning_rate": 4.7736580354738684e-05,
1642
+ "loss": 4.5299,
1643
+ "step": 138240
1644
+ },
1645
+ {
1646
+ "epoch": 1.02,
1647
+ "learning_rate": 4.7728194407228164e-05,
1648
+ "loss": 4.5315,
1649
+ "step": 138752
1650
+ },
1651
+ {
1652
+ "epoch": 1.02,
1653
+ "learning_rate": 4.7719808459717644e-05,
1654
+ "loss": 4.526,
1655
+ "step": 139264
1656
+ },
1657
+ {
1658
+ "epoch": 1.02,
1659
+ "learning_rate": 4.7711422512207124e-05,
1660
+ "loss": 4.5235,
1661
+ "step": 139776
1662
+ },
1663
+ {
1664
+ "epoch": 1.02,
1665
+ "learning_rate": 4.7703036564696604e-05,
1666
+ "loss": 4.5155,
1667
+ "step": 140288
1668
+ },
1669
+ {
1670
+ "epoch": 1.02,
1671
+ "learning_rate": 4.7694650617186084e-05,
1672
+ "loss": 4.5208,
1673
+ "step": 140800
1674
+ },
1675
+ {
1676
+ "epoch": 1.02,
1677
+ "learning_rate": 4.76862810484793e-05,
1678
+ "loss": 4.5158,
1679
+ "step": 141312
1680
+ },
1681
+ {
1682
+ "epoch": 1.02,
1683
+ "learning_rate": 4.767791147977251e-05,
1684
+ "loss": 4.5227,
1685
+ "step": 141824
1686
+ },
1687
+ {
1688
+ "epoch": 1.02,
1689
+ "learning_rate": 4.766952553226199e-05,
1690
+ "loss": 4.5068,
1691
+ "step": 142336
1692
+ },
1693
+ {
1694
+ "epoch": 1.02,
1695
+ "learning_rate": 4.766113958475147e-05,
1696
+ "loss": 4.5297,
1697
+ "step": 142848
1698
+ },
1699
+ {
1700
+ "epoch": 1.02,
1701
+ "learning_rate": 4.765275363724095e-05,
1702
+ "loss": 4.5347,
1703
+ "step": 143360
1704
+ },
1705
+ {
1706
+ "epoch": 1.02,
1707
+ "learning_rate": 4.764438406853416e-05,
1708
+ "loss": 4.5192,
1709
+ "step": 143872
1710
+ },
1711
+ {
1712
+ "epoch": 1.02,
1713
+ "learning_rate": 4.763599812102364e-05,
1714
+ "loss": 4.5134,
1715
+ "step": 144384
1716
+ },
1717
+ {
1718
+ "epoch": 1.02,
1719
+ "learning_rate": 4.762761217351312e-05,
1720
+ "loss": 4.5143,
1721
+ "step": 144896
1722
+ },
1723
+ {
1724
+ "epoch": 1.02,
1725
+ "learning_rate": 4.76192262260026e-05,
1726
+ "loss": 4.5187,
1727
+ "step": 145408
1728
+ },
1729
+ {
1730
+ "epoch": 1.02,
1731
+ "learning_rate": 4.761084027849208e-05,
1732
+ "loss": 4.5203,
1733
+ "step": 145920
1734
+ },
1735
+ {
1736
+ "epoch": 1.02,
1737
+ "learning_rate": 4.760245433098156e-05,
1738
+ "loss": 4.5122,
1739
+ "step": 146432
1740
+ },
1741
+ {
1742
+ "epoch": 1.02,
1743
+ "learning_rate": 4.759406838347104e-05,
1744
+ "loss": 4.5129,
1745
+ "step": 146944
1746
+ },
1747
+ {
1748
+ "epoch": 1.02,
1749
+ "learning_rate": 4.758568243596052e-05,
1750
+ "loss": 4.5091,
1751
+ "step": 147456
1752
+ },
1753
+ {
1754
+ "epoch": 1.02,
1755
+ "learning_rate": 4.757729648845e-05,
1756
+ "loss": 4.5123,
1757
+ "step": 147968
1758
+ },
1759
+ {
1760
+ "epoch": 1.02,
1761
+ "learning_rate": 4.756891054093948e-05,
1762
+ "loss": 4.5042,
1763
+ "step": 148480
1764
+ },
1765
+ {
1766
+ "epoch": 1.02,
1767
+ "learning_rate": 4.756052459342896e-05,
1768
+ "loss": 4.5134,
1769
+ "step": 148992
1770
+ },
1771
+ {
1772
+ "epoch": 1.02,
1773
+ "learning_rate": 4.755213864591844e-05,
1774
+ "loss": 4.5023,
1775
+ "step": 149504
1776
+ },
1777
+ {
1778
+ "epoch": 1.02,
1779
+ "learning_rate": 4.7543785456015375e-05,
1780
+ "loss": 4.4979,
1781
+ "step": 150016
1782
+ },
1783
+ {
1784
+ "epoch": 1.02,
1785
+ "learning_rate": 4.7535399508504855e-05,
1786
+ "loss": 4.5086,
1787
+ "step": 150528
1788
+ },
1789
+ {
1790
+ "epoch": 1.02,
1791
+ "learning_rate": 4.7527013560994335e-05,
1792
+ "loss": 4.4967,
1793
+ "step": 151040
1794
+ },
1795
+ {
1796
+ "epoch": 1.02,
1797
+ "learning_rate": 4.7518627613483815e-05,
1798
+ "loss": 4.5055,
1799
+ "step": 151552
1800
+ },
1801
+ {
1802
+ "epoch": 1.02,
1803
+ "learning_rate": 4.7510241665973295e-05,
1804
+ "loss": 4.4936,
1805
+ "step": 152064
1806
+ },
1807
+ {
1808
+ "epoch": 1.02,
1809
+ "learning_rate": 4.750185571846278e-05,
1810
+ "loss": 4.4915,
1811
+ "step": 152576
1812
+ },
1813
+ {
1814
+ "epoch": 1.03,
1815
+ "eval_loss": 4.463145732879639,
1816
+ "eval_runtime": 354.3654,
1817
+ "eval_samples_per_second": 1076.829,
1818
+ "eval_steps_per_second": 33.652,
1819
+ "step": 152640
1820
+ },
1821
+ {
1822
+ "epoch": 0.0,
1823
+ "learning_rate": 4.749346977095226e-05,
1824
+ "loss": 4.49,
1825
+ "step": 153088
1826
+ },
1827
+ {
1828
+ "epoch": 0.0,
1829
+ "learning_rate": 4.748508382344174e-05,
1830
+ "loss": 4.4806,
1831
+ "step": 153600
1832
+ },
1833
+ {
1834
+ "epoch": 0.0,
1835
+ "learning_rate": 4.747669787593122e-05,
1836
+ "loss": 4.5043,
1837
+ "step": 154112
1838
+ },
1839
+ {
1840
+ "epoch": 0.0,
1841
+ "learning_rate": 4.74683119284207e-05,
1842
+ "loss": 4.4889,
1843
+ "step": 154624
1844
+ },
1845
+ {
1846
+ "epoch": 0.0,
1847
+ "learning_rate": 4.745992598091018e-05,
1848
+ "loss": 4.4979,
1849
+ "step": 155136
1850
+ },
1851
+ {
1852
+ "epoch": 0.0,
1853
+ "learning_rate": 4.745154003339966e-05,
1854
+ "loss": 4.4814,
1855
+ "step": 155648
1856
+ },
1857
+ {
1858
+ "epoch": 0.0,
1859
+ "learning_rate": 4.744315408588914e-05,
1860
+ "loss": 4.4901,
1861
+ "step": 156160
1862
+ },
1863
+ {
1864
+ "epoch": 0.0,
1865
+ "learning_rate": 4.743476813837862e-05,
1866
+ "loss": 4.4715,
1867
+ "step": 156672
1868
+ },
1869
+ {
1870
+ "epoch": 0.0,
1871
+ "learning_rate": 4.7426382190868095e-05,
1872
+ "loss": 4.4877,
1873
+ "step": 157184
1874
+ },
1875
+ {
1876
+ "epoch": 0.0,
1877
+ "learning_rate": 4.7417996243357575e-05,
1878
+ "loss": 4.4914,
1879
+ "step": 157696
1880
+ },
1881
+ {
1882
+ "epoch": 0.0,
1883
+ "learning_rate": 4.7409610295847055e-05,
1884
+ "loss": 4.4922,
1885
+ "step": 158208
1886
+ },
1887
+ {
1888
+ "epoch": 0.0,
1889
+ "learning_rate": 4.7401224348336535e-05,
1890
+ "loss": 4.4831,
1891
+ "step": 158720
1892
+ },
1893
+ {
1894
+ "epoch": 0.0,
1895
+ "learning_rate": 4.7392838400826015e-05,
1896
+ "loss": 4.4717,
1897
+ "step": 159232
1898
+ },
1899
+ {
1900
+ "epoch": 0.0,
1901
+ "learning_rate": 4.7384452453315495e-05,
1902
+ "loss": 4.4745,
1903
+ "step": 159744
1904
+ },
1905
+ {
1906
+ "epoch": 0.0,
1907
+ "learning_rate": 4.7376066505804975e-05,
1908
+ "loss": 4.4694,
1909
+ "step": 160256
1910
+ },
1911
+ {
1912
+ "epoch": 0.0,
1913
+ "learning_rate": 4.736768055829446e-05,
1914
+ "loss": 4.4726,
1915
+ "step": 160768
1916
+ },
1917
+ {
1918
+ "epoch": 0.0,
1919
+ "learning_rate": 4.735929461078394e-05,
1920
+ "loss": 4.4791,
1921
+ "step": 161280
1922
+ },
1923
+ {
1924
+ "epoch": 0.0,
1925
+ "learning_rate": 4.735092504207715e-05,
1926
+ "loss": 4.4653,
1927
+ "step": 161792
1928
+ },
1929
+ {
1930
+ "epoch": 0.0,
1931
+ "learning_rate": 4.734253909456663e-05,
1932
+ "loss": 4.4677,
1933
+ "step": 162304
1934
+ },
1935
+ {
1936
+ "epoch": 0.0,
1937
+ "learning_rate": 4.733415314705611e-05,
1938
+ "loss": 4.4889,
1939
+ "step": 162816
1940
+ },
1941
+ {
1942
+ "epoch": 0.0,
1943
+ "learning_rate": 4.732578357834932e-05,
1944
+ "loss": 4.4729,
1945
+ "step": 163328
1946
+ },
1947
+ {
1948
+ "epoch": 0.0,
1949
+ "learning_rate": 4.73173976308388e-05,
1950
+ "loss": 4.4754,
1951
+ "step": 163840
1952
+ },
1953
+ {
1954
+ "epoch": 0.0,
1955
+ "learning_rate": 4.730901168332828e-05,
1956
+ "loss": 4.4647,
1957
+ "step": 164352
1958
+ },
1959
+ {
1960
+ "epoch": 0.0,
1961
+ "learning_rate": 4.730062573581776e-05,
1962
+ "loss": 4.4819,
1963
+ "step": 164864
1964
+ },
1965
+ {
1966
+ "epoch": 0.0,
1967
+ "learning_rate": 4.729223978830724e-05,
1968
+ "loss": 4.4592,
1969
+ "step": 165376
1970
+ },
1971
+ {
1972
+ "epoch": 0.0,
1973
+ "learning_rate": 4.728385384079672e-05,
1974
+ "loss": 4.4666,
1975
+ "step": 165888
1976
+ },
1977
+ {
1978
+ "epoch": 0.0,
1979
+ "learning_rate": 4.72754678932862e-05,
1980
+ "loss": 4.4612,
1981
+ "step": 166400
1982
+ },
1983
+ {
1984
+ "epoch": 0.0,
1985
+ "learning_rate": 4.726708194577568e-05,
1986
+ "loss": 4.462,
1987
+ "step": 166912
1988
+ },
1989
+ {
1990
+ "epoch": 0.0,
1991
+ "learning_rate": 4.725869599826516e-05,
1992
+ "loss": 4.4481,
1993
+ "step": 167424
1994
+ },
1995
+ {
1996
+ "epoch": 0.01,
1997
+ "learning_rate": 4.725031005075464e-05,
1998
+ "loss": 4.4558,
1999
+ "step": 167936
2000
+ },
2001
+ {
2002
+ "epoch": 0.01,
2003
+ "learning_rate": 4.724192410324412e-05,
2004
+ "loss": 4.4639,
2005
+ "step": 168448
2006
+ },
2007
+ {
2008
+ "epoch": 0.01,
2009
+ "learning_rate": 4.7233554534537335e-05,
2010
+ "loss": 4.4641,
2011
+ "step": 168960
2012
+ },
2013
+ {
2014
+ "epoch": 0.01,
2015
+ "learning_rate": 4.722516858702681e-05,
2016
+ "loss": 4.4589,
2017
+ "step": 169472
2018
+ },
2019
+ {
2020
+ "epoch": 0.01,
2021
+ "learning_rate": 4.721678263951629e-05,
2022
+ "loss": 4.4603,
2023
+ "step": 169984
2024
+ },
2025
+ {
2026
+ "epoch": 0.01,
2027
+ "learning_rate": 4.720839669200577e-05,
2028
+ "loss": 4.4573,
2029
+ "step": 170496
2030
+ },
2031
+ {
2032
+ "epoch": 0.01,
2033
+ "learning_rate": 4.7200027123298984e-05,
2034
+ "loss": 4.4596,
2035
+ "step": 171008
2036
+ },
2037
+ {
2038
+ "epoch": 0.01,
2039
+ "learning_rate": 4.719167393339592e-05,
2040
+ "loss": 4.4456,
2041
+ "step": 171520
2042
+ },
2043
+ {
2044
+ "epoch": 0.01,
2045
+ "learning_rate": 4.71832879858854e-05,
2046
+ "loss": 4.4484,
2047
+ "step": 172032
2048
+ },
2049
+ {
2050
+ "epoch": 0.01,
2051
+ "learning_rate": 4.717490203837488e-05,
2052
+ "loss": 4.4392,
2053
+ "step": 172544
2054
+ },
2055
+ {
2056
+ "epoch": 0.01,
2057
+ "learning_rate": 4.716651609086437e-05,
2058
+ "loss": 4.4543,
2059
+ "step": 173056
2060
+ },
2061
+ {
2062
+ "epoch": 0.01,
2063
+ "learning_rate": 4.715813014335385e-05,
2064
+ "loss": 4.4382,
2065
+ "step": 173568
2066
+ },
2067
+ {
2068
+ "epoch": 0.01,
2069
+ "learning_rate": 4.714974419584333e-05,
2070
+ "loss": 4.4487,
2071
+ "step": 174080
2072
+ },
2073
+ {
2074
+ "epoch": 0.01,
2075
+ "learning_rate": 4.714135824833281e-05,
2076
+ "loss": 4.4401,
2077
+ "step": 174592
2078
+ },
2079
+ {
2080
+ "epoch": 0.01,
2081
+ "learning_rate": 4.713297230082228e-05,
2082
+ "loss": 4.4409,
2083
+ "step": 175104
2084
+ },
2085
+ {
2086
+ "epoch": 0.01,
2087
+ "learning_rate": 4.712458635331176e-05,
2088
+ "loss": 4.449,
2089
+ "step": 175616
2090
+ },
2091
+ {
2092
+ "epoch": 0.01,
2093
+ "learning_rate": 4.711621678460498e-05,
2094
+ "loss": 4.44,
2095
+ "step": 176128
2096
+ },
2097
+ {
2098
+ "epoch": 0.01,
2099
+ "learning_rate": 4.710783083709446e-05,
2100
+ "loss": 4.4411,
2101
+ "step": 176640
2102
+ },
2103
+ {
2104
+ "epoch": 0.01,
2105
+ "learning_rate": 4.709944488958393e-05,
2106
+ "loss": 4.4249,
2107
+ "step": 177152
2108
+ },
2109
+ {
2110
+ "epoch": 0.01,
2111
+ "learning_rate": 4.709105894207341e-05,
2112
+ "loss": 4.4301,
2113
+ "step": 177664
2114
+ },
2115
+ {
2116
+ "epoch": 0.01,
2117
+ "learning_rate": 4.7082689373366627e-05,
2118
+ "loss": 4.4441,
2119
+ "step": 178176
2120
+ },
2121
+ {
2122
+ "epoch": 0.01,
2123
+ "learning_rate": 4.7074303425856106e-05,
2124
+ "loss": 4.4357,
2125
+ "step": 178688
2126
+ },
2127
+ {
2128
+ "epoch": 0.01,
2129
+ "learning_rate": 4.7065917478345586e-05,
2130
+ "loss": 4.436,
2131
+ "step": 179200
2132
+ },
2133
+ {
2134
+ "epoch": 0.01,
2135
+ "learning_rate": 4.7057531530835066e-05,
2136
+ "loss": 4.4212,
2137
+ "step": 179712
2138
+ },
2139
+ {
2140
+ "epoch": 0.01,
2141
+ "learning_rate": 4.7049145583324546e-05,
2142
+ "loss": 4.4338,
2143
+ "step": 180224
2144
+ },
2145
+ {
2146
+ "epoch": 0.01,
2147
+ "learning_rate": 4.7040776014617755e-05,
2148
+ "loss": 4.4206,
2149
+ "step": 180736
2150
+ },
2151
+ {
2152
+ "epoch": 0.01,
2153
+ "learning_rate": 4.7032390067107235e-05,
2154
+ "loss": 4.4457,
2155
+ "step": 181248
2156
+ },
2157
+ {
2158
+ "epoch": 0.01,
2159
+ "learning_rate": 4.7024004119596715e-05,
2160
+ "loss": 4.4139,
2161
+ "step": 181760
2162
+ },
2163
+ {
2164
+ "epoch": 0.01,
2165
+ "learning_rate": 4.7015618172086195e-05,
2166
+ "loss": 4.4341,
2167
+ "step": 182272
2168
+ },
2169
+ {
2170
+ "epoch": 0.01,
2171
+ "learning_rate": 4.7007232224575675e-05,
2172
+ "loss": 4.4279,
2173
+ "step": 182784
2174
+ },
2175
+ {
2176
+ "epoch": 0.01,
2177
+ "learning_rate": 4.6998846277065155e-05,
2178
+ "loss": 4.4125,
2179
+ "step": 183296
2180
+ },
2181
+ {
2182
+ "epoch": 0.01,
2183
+ "learning_rate": 4.6990460329554635e-05,
2184
+ "loss": 4.4232,
2185
+ "step": 183808
2186
+ },
2187
+ {
2188
+ "epoch": 0.01,
2189
+ "learning_rate": 4.6982074382044115e-05,
2190
+ "loss": 4.4271,
2191
+ "step": 184320
2192
+ },
2193
+ {
2194
+ "epoch": 0.01,
2195
+ "learning_rate": 4.6973704813337324e-05,
2196
+ "loss": 4.4103,
2197
+ "step": 184832
2198
+ },
2199
+ {
2200
+ "epoch": 0.01,
2201
+ "learning_rate": 4.6965318865826804e-05,
2202
+ "loss": 4.4185,
2203
+ "step": 185344
2204
+ },
2205
+ {
2206
+ "epoch": 0.01,
2207
+ "learning_rate": 4.695693291831629e-05,
2208
+ "loss": 4.4273,
2209
+ "step": 185856
2210
+ },
2211
+ {
2212
+ "epoch": 0.01,
2213
+ "learning_rate": 4.69485633496095e-05,
2214
+ "loss": 4.4188,
2215
+ "step": 186368
2216
+ },
2217
+ {
2218
+ "epoch": 0.01,
2219
+ "learning_rate": 4.694017740209898e-05,
2220
+ "loss": 4.4127,
2221
+ "step": 186880
2222
+ },
2223
+ {
2224
+ "epoch": 0.01,
2225
+ "learning_rate": 4.693179145458846e-05,
2226
+ "loss": 4.4145,
2227
+ "step": 187392
2228
+ },
2229
+ {
2230
+ "epoch": 0.01,
2231
+ "learning_rate": 4.692340550707794e-05,
2232
+ "loss": 4.4069,
2233
+ "step": 187904
2234
+ },
2235
+ {
2236
+ "epoch": 0.01,
2237
+ "learning_rate": 4.691503593837115e-05,
2238
+ "loss": 4.4192,
2239
+ "step": 188416
2240
+ },
2241
+ {
2242
+ "epoch": 0.01,
2243
+ "learning_rate": 4.690664999086063e-05,
2244
+ "loss": 4.4339,
2245
+ "step": 188928
2246
+ },
2247
+ {
2248
+ "epoch": 0.01,
2249
+ "learning_rate": 4.689826404335011e-05,
2250
+ "loss": 4.4092,
2251
+ "step": 189440
2252
+ },
2253
+ {
2254
+ "epoch": 0.01,
2255
+ "learning_rate": 4.688987809583959e-05,
2256
+ "loss": 4.4267,
2257
+ "step": 189952
2258
+ },
2259
+ {
2260
+ "epoch": 0.01,
2261
+ "learning_rate": 4.688149214832907e-05,
2262
+ "loss": 4.4256,
2263
+ "step": 190464
2264
+ },
2265
+ {
2266
+ "epoch": 0.01,
2267
+ "learning_rate": 4.687310620081855e-05,
2268
+ "loss": 4.4177,
2269
+ "step": 190976
2270
+ },
2271
+ {
2272
+ "epoch": 0.01,
2273
+ "learning_rate": 4.686472025330803e-05,
2274
+ "loss": 4.4024,
2275
+ "step": 191488
2276
+ },
2277
+ {
2278
+ "epoch": 0.01,
2279
+ "learning_rate": 4.6856350684601245e-05,
2280
+ "loss": 4.421,
2281
+ "step": 192000
2282
+ },
2283
+ {
2284
+ "epoch": 0.01,
2285
+ "learning_rate": 4.6847981115894454e-05,
2286
+ "loss": 4.411,
2287
+ "step": 192512
2288
+ },
2289
+ {
2290
+ "epoch": 0.01,
2291
+ "learning_rate": 4.6839595168383934e-05,
2292
+ "loss": 4.4095,
2293
+ "step": 193024
2294
+ },
2295
+ {
2296
+ "epoch": 0.01,
2297
+ "learning_rate": 4.6831209220873414e-05,
2298
+ "loss": 4.4062,
2299
+ "step": 193536
2300
+ },
2301
+ {
2302
+ "epoch": 0.01,
2303
+ "learning_rate": 4.6822823273362894e-05,
2304
+ "loss": 4.4113,
2305
+ "step": 194048
2306
+ },
2307
+ {
2308
+ "epoch": 0.01,
2309
+ "learning_rate": 4.6814437325852373e-05,
2310
+ "loss": 4.4249,
2311
+ "step": 194560
2312
+ },
2313
+ {
2314
+ "epoch": 0.01,
2315
+ "learning_rate": 4.6806051378341853e-05,
2316
+ "loss": 4.4079,
2317
+ "step": 195072
2318
+ },
2319
+ {
2320
+ "epoch": 0.01,
2321
+ "learning_rate": 4.6797665430831333e-05,
2322
+ "loss": 4.3941,
2323
+ "step": 195584
2324
+ },
2325
+ {
2326
+ "epoch": 0.01,
2327
+ "learning_rate": 4.678929586212454e-05,
2328
+ "loss": 4.4025,
2329
+ "step": 196096
2330
+ },
2331
+ {
2332
+ "epoch": 0.01,
2333
+ "learning_rate": 4.678090991461402e-05,
2334
+ "loss": 4.4084,
2335
+ "step": 196608
2336
+ },
2337
+ {
2338
+ "epoch": 0.01,
2339
+ "learning_rate": 4.67725239671035e-05,
2340
+ "loss": 4.4079,
2341
+ "step": 197120
2342
+ },
2343
+ {
2344
+ "epoch": 0.01,
2345
+ "learning_rate": 4.676413801959298e-05,
2346
+ "loss": 4.4135,
2347
+ "step": 197632
2348
+ },
2349
+ {
2350
+ "epoch": 0.01,
2351
+ "learning_rate": 4.675575207208246e-05,
2352
+ "loss": 4.3973,
2353
+ "step": 198144
2354
+ },
2355
+ {
2356
+ "epoch": 0.02,
2357
+ "learning_rate": 4.674736612457194e-05,
2358
+ "loss": 4.396,
2359
+ "step": 198656
2360
+ },
2361
+ {
2362
+ "epoch": 0.02,
2363
+ "learning_rate": 4.673898017706142e-05,
2364
+ "loss": 4.3902,
2365
+ "step": 199168
2366
+ },
2367
+ {
2368
+ "epoch": 0.02,
2369
+ "learning_rate": 4.67305942295509e-05,
2370
+ "loss": 4.3978,
2371
+ "step": 199680
2372
+ },
2373
+ {
2374
+ "epoch": 0.02,
2375
+ "learning_rate": 4.672220828204038e-05,
2376
+ "loss": 4.4004,
2377
+ "step": 200192
2378
+ },
2379
+ {
2380
+ "epoch": 0.02,
2381
+ "learning_rate": 4.671382233452986e-05,
2382
+ "loss": 4.399,
2383
+ "step": 200704
2384
+ },
2385
+ {
2386
+ "epoch": 0.02,
2387
+ "learning_rate": 4.670545276582307e-05,
2388
+ "loss": 4.4168,
2389
+ "step": 201216
2390
+ },
2391
+ {
2392
+ "epoch": 0.02,
2393
+ "learning_rate": 4.669706681831255e-05,
2394
+ "loss": 4.3953,
2395
+ "step": 201728
2396
+ },
2397
+ {
2398
+ "epoch": 0.02,
2399
+ "learning_rate": 4.668868087080203e-05,
2400
+ "loss": 4.3918,
2401
+ "step": 202240
2402
+ },
2403
+ {
2404
+ "epoch": 0.02,
2405
+ "learning_rate": 4.668029492329151e-05,
2406
+ "loss": 4.3888,
2407
+ "step": 202752
2408
+ },
2409
+ {
2410
+ "epoch": 0.02,
2411
+ "learning_rate": 4.667190897578099e-05,
2412
+ "loss": 4.3919,
2413
+ "step": 203264
2414
+ },
2415
+ {
2416
+ "epoch": 0.02,
2417
+ "learning_rate": 4.66635394070742e-05,
2418
+ "loss": 4.3973,
2419
+ "step": 203776
2420
+ },
2421
+ {
2422
+ "epoch": 0.02,
2423
+ "learning_rate": 4.665515345956368e-05,
2424
+ "loss": 4.3959,
2425
+ "step": 204288
2426
+ },
2427
+ {
2428
+ "epoch": 0.02,
2429
+ "learning_rate": 4.664676751205316e-05,
2430
+ "loss": 4.3908,
2431
+ "step": 204800
2432
+ },
2433
+ {
2434
+ "epoch": 0.02,
2435
+ "learning_rate": 4.663838156454265e-05,
2436
+ "loss": 4.3875,
2437
+ "step": 205312
2438
+ },
2439
+ {
2440
+ "epoch": 0.02,
2441
+ "learning_rate": 4.662999561703213e-05,
2442
+ "loss": 4.3946,
2443
+ "step": 205824
2444
+ },
2445
+ {
2446
+ "epoch": 0.02,
2447
+ "learning_rate": 4.662160966952161e-05,
2448
+ "loss": 4.3699,
2449
+ "step": 206336
2450
+ },
2451
+ {
2452
+ "epoch": 0.02,
2453
+ "learning_rate": 4.661322372201109e-05,
2454
+ "loss": 4.3875,
2455
+ "step": 206848
2456
+ },
2457
+ {
2458
+ "epoch": 0.02,
2459
+ "learning_rate": 4.6604837774500567e-05,
2460
+ "loss": 4.3795,
2461
+ "step": 207360
2462
+ },
2463
+ {
2464
+ "epoch": 0.02,
2465
+ "learning_rate": 4.6596484584597505e-05,
2466
+ "loss": 4.3851,
2467
+ "step": 207872
2468
+ },
2469
+ {
2470
+ "epoch": 0.02,
2471
+ "learning_rate": 4.6588098637086985e-05,
2472
+ "loss": 4.3804,
2473
+ "step": 208384
2474
+ },
2475
+ {
2476
+ "epoch": 0.02,
2477
+ "learning_rate": 4.6579712689576465e-05,
2478
+ "loss": 4.3902,
2479
+ "step": 208896
2480
+ },
2481
+ {
2482
+ "epoch": 0.02,
2483
+ "learning_rate": 4.6571326742065945e-05,
2484
+ "loss": 4.3719,
2485
+ "step": 209408
2486
+ },
2487
+ {
2488
+ "epoch": 0.02,
2489
+ "learning_rate": 4.6562940794555425e-05,
2490
+ "loss": 4.3729,
2491
+ "step": 209920
2492
+ },
2493
+ {
2494
+ "epoch": 0.02,
2495
+ "learning_rate": 4.6554571225848634e-05,
2496
+ "loss": 4.3828,
2497
+ "step": 210432
2498
+ },
2499
+ {
2500
+ "epoch": 0.02,
2501
+ "learning_rate": 4.6546185278338114e-05,
2502
+ "loss": 4.3745,
2503
+ "step": 210944
2504
+ },
2505
+ {
2506
+ "epoch": 0.02,
2507
+ "learning_rate": 4.65377993308276e-05,
2508
+ "loss": 4.3944,
2509
+ "step": 211456
2510
+ },
2511
+ {
2512
+ "epoch": 0.02,
2513
+ "learning_rate": 4.652941338331708e-05,
2514
+ "loss": 4.3859,
2515
+ "step": 211968
2516
+ },
2517
+ {
2518
+ "epoch": 0.02,
2519
+ "learning_rate": 4.652104381461029e-05,
2520
+ "loss": 4.3842,
2521
+ "step": 212480
2522
+ },
2523
+ {
2524
+ "epoch": 0.02,
2525
+ "learning_rate": 4.651265786709977e-05,
2526
+ "loss": 4.3719,
2527
+ "step": 212992
2528
+ },
2529
+ {
2530
+ "epoch": 0.02,
2531
+ "learning_rate": 4.650427191958925e-05,
2532
+ "loss": 4.3777,
2533
+ "step": 213504
2534
+ },
2535
+ {
2536
+ "epoch": 0.02,
2537
+ "learning_rate": 4.649588597207873e-05,
2538
+ "loss": 4.3802,
2539
+ "step": 214016
2540
+ },
2541
+ {
2542
+ "epoch": 0.02,
2543
+ "learning_rate": 4.648750002456821e-05,
2544
+ "loss": 4.3765,
2545
+ "step": 214528
2546
+ },
2547
+ {
2548
+ "epoch": 0.02,
2549
+ "learning_rate": 4.647911407705769e-05,
2550
+ "loss": 4.3774,
2551
+ "step": 215040
2552
+ },
2553
+ {
2554
+ "epoch": 0.02,
2555
+ "learning_rate": 4.647072812954717e-05,
2556
+ "loss": 4.3667,
2557
+ "step": 215552
2558
+ },
2559
+ {
2560
+ "epoch": 0.02,
2561
+ "learning_rate": 4.646234218203665e-05,
2562
+ "loss": 4.3733,
2563
+ "step": 216064
2564
+ },
2565
+ {
2566
+ "epoch": 0.02,
2567
+ "learning_rate": 4.645395623452612e-05,
2568
+ "loss": 4.363,
2569
+ "step": 216576
2570
+ },
2571
+ {
2572
+ "epoch": 0.02,
2573
+ "learning_rate": 4.64455702870156e-05,
2574
+ "loss": 4.3685,
2575
+ "step": 217088
2576
+ },
2577
+ {
2578
+ "epoch": 0.02,
2579
+ "learning_rate": 4.643720071830882e-05,
2580
+ "loss": 4.365,
2581
+ "step": 217600
2582
+ },
2583
+ {
2584
+ "epoch": 0.02,
2585
+ "learning_rate": 4.6428831149602034e-05,
2586
+ "loss": 4.3689,
2587
+ "step": 218112
2588
+ },
2589
+ {
2590
+ "epoch": 0.02,
2591
+ "learning_rate": 4.6420445202091514e-05,
2592
+ "loss": 4.355,
2593
+ "step": 218624
2594
+ },
2595
+ {
2596
+ "epoch": 0.02,
2597
+ "learning_rate": 4.6412059254580994e-05,
2598
+ "loss": 4.3806,
2599
+ "step": 219136
2600
+ },
2601
+ {
2602
+ "epoch": 0.02,
2603
+ "learning_rate": 4.6403673307070474e-05,
2604
+ "loss": 4.3818,
2605
+ "step": 219648
2606
+ },
2607
+ {
2608
+ "epoch": 0.02,
2609
+ "learning_rate": 4.639528735955995e-05,
2610
+ "loss": 4.3732,
2611
+ "step": 220160
2612
+ },
2613
+ {
2614
+ "epoch": 0.02,
2615
+ "learning_rate": 4.638691779085316e-05,
2616
+ "loss": 4.3591,
2617
+ "step": 220672
2618
+ },
2619
+ {
2620
+ "epoch": 0.02,
2621
+ "learning_rate": 4.637853184334264e-05,
2622
+ "loss": 4.3679,
2623
+ "step": 221184
2624
+ },
2625
+ {
2626
+ "epoch": 0.02,
2627
+ "learning_rate": 4.637014589583212e-05,
2628
+ "loss": 4.3683,
2629
+ "step": 221696
2630
+ },
2631
+ {
2632
+ "epoch": 0.02,
2633
+ "learning_rate": 4.6361759948321596e-05,
2634
+ "loss": 4.3747,
2635
+ "step": 222208
2636
+ },
2637
+ {
2638
+ "epoch": 0.02,
2639
+ "learning_rate": 4.6353374000811076e-05,
2640
+ "loss": 4.3658,
2641
+ "step": 222720
2642
+ },
2643
+ {
2644
+ "epoch": 0.02,
2645
+ "learning_rate": 4.6344988053300556e-05,
2646
+ "loss": 4.3644,
2647
+ "step": 223232
2648
+ },
2649
+ {
2650
+ "epoch": 0.02,
2651
+ "learning_rate": 4.6336602105790036e-05,
2652
+ "loss": 4.3636,
2653
+ "step": 223744
2654
+ },
2655
+ {
2656
+ "epoch": 0.02,
2657
+ "learning_rate": 4.632821615827952e-05,
2658
+ "loss": 4.3695,
2659
+ "step": 224256
2660
+ },
2661
+ {
2662
+ "epoch": 0.02,
2663
+ "learning_rate": 4.6319830210769e-05,
2664
+ "loss": 4.3613,
2665
+ "step": 224768
2666
+ },
2667
+ {
2668
+ "epoch": 0.02,
2669
+ "learning_rate": 4.631144426325848e-05,
2670
+ "loss": 4.3671,
2671
+ "step": 225280
2672
+ },
2673
+ {
2674
+ "epoch": 0.02,
2675
+ "learning_rate": 4.630305831574796e-05,
2676
+ "loss": 4.3593,
2677
+ "step": 225792
2678
+ },
2679
+ {
2680
+ "epoch": 0.02,
2681
+ "learning_rate": 4.629467236823744e-05,
2682
+ "loss": 4.3565,
2683
+ "step": 226304
2684
+ },
2685
+ {
2686
+ "epoch": 0.02,
2687
+ "learning_rate": 4.628630279953065e-05,
2688
+ "loss": 4.3658,
2689
+ "step": 226816
2690
+ },
2691
+ {
2692
+ "epoch": 0.02,
2693
+ "learning_rate": 4.627793323082386e-05,
2694
+ "loss": 4.3593,
2695
+ "step": 227328
2696
+ },
2697
+ {
2698
+ "epoch": 0.02,
2699
+ "learning_rate": 4.626954728331334e-05,
2700
+ "loss": 4.3577,
2701
+ "step": 227840
2702
+ },
2703
+ {
2704
+ "epoch": 0.02,
2705
+ "learning_rate": 4.626116133580282e-05,
2706
+ "loss": 4.3518,
2707
+ "step": 228352
2708
+ },
2709
+ {
2710
+ "epoch": 0.02,
2711
+ "learning_rate": 4.625279176709603e-05,
2712
+ "loss": 4.3483,
2713
+ "step": 228864
2714
+ },
2715
+ {
2716
+ "epoch": 0.03,
2717
+ "eval_loss": 4.330287933349609,
2718
+ "eval_runtime": 302.6809,
2719
+ "eval_samples_per_second": 1260.704,
2720
+ "eval_steps_per_second": 39.398,
2721
+ "step": 228960
2722
+ }
2723
+ ],
2724
+ "logging_steps": 512,
2725
+ "max_steps": 3052726,
2726
+ "num_train_epochs": 9223372036854775807,
2727
+ "save_steps": 10,
2728
+ "total_flos": 9.477738216745003e+16,
2729
+ "trial_name": null,
2730
+ "trial_params": null
2731
+ }
checkpoint-228960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ec28fbc23b52d96d5b397b843fab1323f9aeb9a61c2a25faab2b2bebfcbba3
3
+ size 4219