File size: 3,729 Bytes
60f18aa
 
 
f9b46f7
d5a8ec0
f9b46f7
60f18aa
 
 
 
 
 
 
d5a8ec0
 
 
60f18aa
d5a8ec0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a01c72b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2bbe71b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9b46f7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60f18aa
 
 
d5a8ec0
60f18aa
 
d5a8ec0
60f18aa
 
 
 
 
 
 
f9b46f7
60f18aa
 
 
 
f9b46f7
60f18aa
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013343118286743613,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002668623657348722,
      "eval_loss": 1.4171478748321533,
      "eval_runtime": 51.4601,
      "eval_samples_per_second": 30.665,
      "eval_steps_per_second": 15.332,
      "step": 1
    },
    {
      "epoch": 0.0013343118286743613,
      "grad_norm": 0.20870009064674377,
      "learning_rate": 5e-05,
      "loss": 1.1958,
      "step": 5
    },
    {
      "epoch": 0.0026686236573487225,
      "grad_norm": 0.3936935365200043,
      "learning_rate": 0.0001,
      "loss": 1.4671,
      "step": 10
    },
    {
      "epoch": 0.0026686236573487225,
      "eval_loss": 1.3937021493911743,
      "eval_runtime": 51.4019,
      "eval_samples_per_second": 30.699,
      "eval_steps_per_second": 15.35,
      "step": 10
    },
    {
      "epoch": 0.004002935486023084,
      "grad_norm": 0.2306661754846573,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.3999,
      "step": 15
    },
    {
      "epoch": 0.005337247314697445,
      "grad_norm": 0.28997236490249634,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3391,
      "step": 20
    },
    {
      "epoch": 0.005337247314697445,
      "eval_loss": 1.331410527229309,
      "eval_runtime": 51.2329,
      "eval_samples_per_second": 30.801,
      "eval_steps_per_second": 15.4,
      "step": 20
    },
    {
      "epoch": 0.006671559143371806,
      "grad_norm": 0.2963295876979828,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3088,
      "step": 25
    },
    {
      "epoch": 0.008005870972046168,
      "grad_norm": 0.3198167383670807,
      "learning_rate": 5e-05,
      "loss": 1.3884,
      "step": 30
    },
    {
      "epoch": 0.008005870972046168,
      "eval_loss": 1.3172019720077515,
      "eval_runtime": 51.3541,
      "eval_samples_per_second": 30.728,
      "eval_steps_per_second": 15.364,
      "step": 30
    },
    {
      "epoch": 0.009340182800720529,
      "grad_norm": 0.271278440952301,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2783,
      "step": 35
    },
    {
      "epoch": 0.01067449462939489,
      "grad_norm": 0.31695592403411865,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2705,
      "step": 40
    },
    {
      "epoch": 0.01067449462939489,
      "eval_loss": 1.3098112344741821,
      "eval_runtime": 52.1649,
      "eval_samples_per_second": 30.25,
      "eval_steps_per_second": 15.125,
      "step": 40
    },
    {
      "epoch": 0.012008806458069251,
      "grad_norm": 0.33602485060691833,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.2586,
      "step": 45
    },
    {
      "epoch": 0.013343118286743613,
      "grad_norm": 0.3920798599720001,
      "learning_rate": 0.0,
      "loss": 1.3313,
      "step": 50
    },
    {
      "epoch": 0.013343118286743613,
      "eval_loss": 1.3084073066711426,
      "eval_runtime": 52.5608,
      "eval_samples_per_second": 30.022,
      "eval_steps_per_second": 15.011,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1752175051014144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}