Hugging Face's logo

nlp04
/
gpt_16_4_3e-5_lp5_nb5

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
54data commited on
Commit
f01d634
·
1 Parent(s): 094444c

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. train_results.txt +6 -0
  4. trainer_state.json +165 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 2.831424217569864,
4
+ "train_runtime": 8708.1966,
5
+ "train_samples": 42367,
6
+ "train_samples_per_second": 19.461,
7
+ "train_steps_per_second": 1.216
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 2.831424217569864,
4
+ "train_runtime": 8708.1966,
5
+ "train_samples": 42367,
6
+ "train_samples_per_second": 19.461,
7
+ "train_steps_per_second": 1.216
8
+ }
train_results.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch = 4.0
2
+ train_loss = 2.831424217569864
3
+ train_runtime = 8708.1966
4
+ train_samples = 42367
5
+ train_samples_per_second = 19.461
6
+ train_steps_per_second = 1.216
trainer_state.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.8871757984161377,
3
+ "best_model_checkpoint": "./models/gpt_test9/checkpoint-10000",
4
+ "epoch": 4.0,
5
+ "global_step": 10592,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.38,
12
+ "learning_rate": 2.830188679245283e-05,
13
+ "loss": 3.311,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.38,
18
+ "eval_loss": 4.033947467803955,
19
+ "eval_runtime": 6.7632,
20
+ "eval_samples_per_second": 63.432,
21
+ "eval_steps_per_second": 3.992,
22
+ "step": 1000
23
+ },
24
+ {
25
+ "epoch": 0.76,
26
+ "learning_rate": 2.7041544271926144e-05,
27
+ "loss": 3.1133,
28
+ "step": 2000
29
+ },
30
+ {
31
+ "epoch": 0.76,
32
+ "eval_loss": 3.9776785373687744,
33
+ "eval_runtime": 6.7558,
34
+ "eval_samples_per_second": 63.501,
35
+ "eval_steps_per_second": 3.997,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 1.13,
40
+ "learning_rate": 2.3894250944187998e-05,
41
+ "loss": 2.9875,
42
+ "step": 3000
43
+ },
44
+ {
45
+ "epoch": 1.13,
46
+ "eval_loss": 3.9545652866363525,
47
+ "eval_runtime": 6.7588,
48
+ "eval_samples_per_second": 63.472,
49
+ "eval_steps_per_second": 3.995,
50
+ "step": 3000
51
+ },
52
+ {
53
+ "epoch": 1.51,
54
+ "learning_rate": 2.0746957616449853e-05,
55
+ "loss": 2.8697,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.51,
60
+ "eval_loss": 3.9269347190856934,
61
+ "eval_runtime": 6.7568,
62
+ "eval_samples_per_second": 63.491,
63
+ "eval_steps_per_second": 3.996,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 1.89,
68
+ "learning_rate": 1.759966428871171e-05,
69
+ "loss": 2.8669,
70
+ "step": 5000
71
+ },
72
+ {
73
+ "epoch": 1.89,
74
+ "eval_loss": 3.915926933288574,
75
+ "eval_runtime": 6.7665,
76
+ "eval_samples_per_second": 63.401,
77
+ "eval_steps_per_second": 3.99,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 2.27,
82
+ "learning_rate": 1.4452370960973563e-05,
83
+ "loss": 2.7308,
84
+ "step": 6000
85
+ },
86
+ {
87
+ "epoch": 2.27,
88
+ "eval_loss": 3.9065561294555664,
89
+ "eval_runtime": 6.7494,
90
+ "eval_samples_per_second": 63.562,
91
+ "eval_steps_per_second": 4.0,
92
+ "step": 6000
93
+ },
94
+ {
95
+ "epoch": 2.64,
96
+ "learning_rate": 1.1305077633235418e-05,
97
+ "loss": 2.709,
98
+ "step": 7000
99
+ },
100
+ {
101
+ "epoch": 2.64,
102
+ "eval_loss": 3.899543285369873,
103
+ "eval_runtime": 6.761,
104
+ "eval_samples_per_second": 63.452,
105
+ "eval_steps_per_second": 3.993,
106
+ "step": 7000
107
+ },
108
+ {
109
+ "epoch": 3.02,
110
+ "learning_rate": 8.157784305497272e-06,
111
+ "loss": 2.6979,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 3.02,
116
+ "eval_loss": 3.8976171016693115,
117
+ "eval_runtime": 6.7563,
118
+ "eval_samples_per_second": 63.496,
119
+ "eval_steps_per_second": 3.996,
120
+ "step": 8000
121
+ },
122
+ {
123
+ "epoch": 3.4,
124
+ "learning_rate": 5.010490977759127e-06,
125
+ "loss": 2.5878,
126
+ "step": 9000
127
+ },
128
+ {
129
+ "epoch": 3.4,
130
+ "eval_loss": 3.897768020629883,
131
+ "eval_runtime": 6.7533,
132
+ "eval_samples_per_second": 63.524,
133
+ "eval_steps_per_second": 3.998,
134
+ "step": 9000
135
+ },
136
+ {
137
+ "epoch": 3.78,
138
+ "learning_rate": 1.863197650020982e-06,
139
+ "loss": 2.5824,
140
+ "step": 10000
141
+ },
142
+ {
143
+ "epoch": 3.78,
144
+ "eval_loss": 3.8871757984161377,
145
+ "eval_runtime": 6.7573,
146
+ "eval_samples_per_second": 63.487,
147
+ "eval_steps_per_second": 3.996,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "step": 10592,
153
+ "total_flos": 4.4280638078976e+16,
154
+ "train_loss": 2.831424217569864,
155
+ "train_runtime": 8708.1966,
156
+ "train_samples_per_second": 19.461,
157
+ "train_steps_per_second": 1.216
158
+ }
159
+ ],
160
+ "max_steps": 10592,
161
+ "num_train_epochs": 4,
162
+ "total_flos": 4.4280638078976e+16,
163
+ "trial_name": null,
164
+ "trial_params": null
165
+ }