File size: 3,435 Bytes
1e5d4b0
 
 
da6644b
ecb490e
da6644b
1e5d4b0
 
 
 
 
 
 
68e2142
 
 
1e5d4b0
ecb490e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68e2142
 
 
ecb490e
5663cfb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4590fb1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da6644b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e5d4b0
 
 
ecb490e
1e5d4b0
 
ecb490e
1e5d4b0
 
 
 
 
 
 
da6644b
1e5d4b0
 
 
 
da6644b
1e5d4b0
 
 
 
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": 0.14450867052023122,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002890173410404624,
      "eval_loss": NaN,
      "eval_runtime": 21.3252,
      "eval_samples_per_second": 6.846,
      "eval_steps_per_second": 3.423,
      "step": 1
    },
    {
      "epoch": 0.014450867052023121,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.028901734104046242,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.028901734104046242,
      "eval_loss": NaN,
      "eval_runtime": 19.2525,
      "eval_samples_per_second": 7.583,
      "eval_steps_per_second": 3.792,
      "step": 10
    },
    {
      "epoch": 0.04335260115606936,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.057803468208092484,
      "eval_loss": NaN,
      "eval_runtime": 25.0682,
      "eval_samples_per_second": 5.824,
      "eval_steps_per_second": 2.912,
      "step": 20
    },
    {
      "epoch": 0.07225433526011561,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.08670520231213873,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.08670520231213873,
      "eval_loss": NaN,
      "eval_runtime": 19.2346,
      "eval_samples_per_second": 7.59,
      "eval_steps_per_second": 3.795,
      "step": 30
    },
    {
      "epoch": 0.10115606936416185,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.11560693641618497,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.11560693641618497,
      "eval_loss": NaN,
      "eval_runtime": 19.2386,
      "eval_samples_per_second": 7.589,
      "eval_steps_per_second": 3.794,
      "step": 40
    },
    {
      "epoch": 0.13005780346820808,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.14450867052023122,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.14450867052023122,
      "eval_loss": NaN,
      "eval_runtime": 19.3451,
      "eval_samples_per_second": 7.547,
      "eval_steps_per_second": 3.774,
      "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": 3234875128676352.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}