Hugging Face's logo

AlekseyKorshuk
/
6.7b-dalio-book-handwritten-io-constant-3e-7

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
AlekseyKorshuk commited on
Commit
a54813f
•
1 Parent(s): f5c889d

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +166 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.5400499616350447,
4
+ "train_runtime": 12579.867,
5
+ "train_samples": 442,
6
+ "train_samples_per_second": 0.035,
7
+ "train_steps_per_second": 0.004
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.5400499616350447,
4
+ "train_runtime": 12579.867,
5
+ "train_samples": 442,
6
+ "train_samples_per_second": 0.035,
7
+ "train_steps_per_second": 0.004
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 56,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 3e-07,
13
+ "loss": 2.5647,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 3e-07,
19
+ "loss": 2.6398,
20
+ "step": 6
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "eval_accuracy": 0.29866204463905616,
25
+ "eval_loss": 2.505859375,
26
+ "eval_runtime": 65.7499,
27
+ "eval_samples_per_second": 4.791,
28
+ "eval_steps_per_second": 0.608,
29
+ "step": 6
30
+ },
31
+ {
32
+ "epoch": 0.21,
33
+ "learning_rate": 3e-07,
34
+ "loss": 2.5823,
35
+ "step": 12
36
+ },
37
+ {
38
+ "epoch": 0.21,
39
+ "eval_accuracy": 0.29880800340570457,
40
+ "eval_loss": 2.50390625,
41
+ "eval_runtime": 66.4342,
42
+ "eval_samples_per_second": 4.742,
43
+ "eval_steps_per_second": 0.602,
44
+ "step": 12
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 3e-07,
49
+ "loss": 2.6128,
50
+ "step": 18
51
+ },
52
+ {
53
+ "epoch": 0.32,
54
+ "eval_accuracy": 0.2991485738612175,
55
+ "eval_loss": 2.498046875,
56
+ "eval_runtime": 66.4484,
57
+ "eval_samples_per_second": 4.741,
58
+ "eval_steps_per_second": 0.602,
59
+ "step": 18
60
+ },
61
+ {
62
+ "epoch": 0.43,
63
+ "learning_rate": 3e-07,
64
+ "loss": 2.5775,
65
+ "step": 24
66
+ },
67
+ {
68
+ "epoch": 0.43,
69
+ "eval_accuracy": 0.2994526546250684,
70
+ "eval_loss": 2.4921875,
71
+ "eval_runtime": 66.4492,
72
+ "eval_samples_per_second": 4.74,
73
+ "eval_steps_per_second": 0.602,
74
+ "step": 24
75
+ },
76
+ {
77
+ "epoch": 0.54,
78
+ "learning_rate": 3e-07,
79
+ "loss": 2.527,
80
+ "step": 30
81
+ },
82
+ {
83
+ "epoch": 0.54,
84
+ "eval_accuracy": 0.2999452654625068,
85
+ "eval_loss": 2.486328125,
86
+ "eval_runtime": 65.4246,
87
+ "eval_samples_per_second": 4.815,
88
+ "eval_steps_per_second": 0.611,
89
+ "step": 30
90
+ },
91
+ {
92
+ "epoch": 0.64,
93
+ "learning_rate": 3e-07,
94
+ "loss": 2.5752,
95
+ "step": 36
96
+ },
97
+ {
98
+ "epoch": 0.64,
99
+ "eval_accuracy": 0.30033448884023595,
100
+ "eval_loss": 2.48046875,
101
+ "eval_runtime": 66.4667,
102
+ "eval_samples_per_second": 4.739,
103
+ "eval_steps_per_second": 0.602,
104
+ "step": 36
105
+ },
106
+ {
107
+ "epoch": 0.75,
108
+ "learning_rate": 3e-07,
109
+ "loss": 2.5131,
110
+ "step": 42
111
+ },
112
+ {
113
+ "epoch": 0.75,
114
+ "eval_accuracy": 0.30077844675545823,
115
+ "eval_loss": 2.474609375,
116
+ "eval_runtime": 66.403,
117
+ "eval_samples_per_second": 4.744,
118
+ "eval_steps_per_second": 0.602,
119
+ "step": 42
120
+ },
121
+ {
122
+ "epoch": 0.86,
123
+ "learning_rate": 3e-07,
124
+ "loss": 2.4436,
125
+ "step": 48
126
+ },
127
+ {
128
+ "epoch": 0.86,
129
+ "eval_accuracy": 0.3013501185914979,
130
+ "eval_loss": 2.46875,
131
+ "eval_runtime": 65.4356,
132
+ "eval_samples_per_second": 4.814,
133
+ "eval_steps_per_second": 0.611,
134
+ "step": 48
135
+ },
136
+ {
137
+ "epoch": 0.96,
138
+ "learning_rate": 3e-07,
139
+ "loss": 2.5114,
140
+ "step": 54
141
+ },
142
+ {
143
+ "epoch": 0.96,
144
+ "eval_accuracy": 0.30175150519978106,
145
+ "eval_loss": 2.462890625,
146
+ "eval_runtime": 66.4277,
147
+ "eval_samples_per_second": 4.742,
148
+ "eval_steps_per_second": 0.602,
149
+ "step": 54
150
+ },
151
+ {
152
+ "epoch": 1.0,
153
+ "step": 56,
154
+ "total_flos": 3701894676480.0,
155
+ "train_loss": 2.5400499616350447,
156
+ "train_runtime": 12579.867,
157
+ "train_samples_per_second": 0.035,
158
+ "train_steps_per_second": 0.004
159
+ }
160
+ ],
161
+ "max_steps": 56,
162
+ "num_train_epochs": 1,
163
+ "total_flos": 3701894676480.0,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }