File size: 3,730 Bytes
d6da939
 
 
f70de15
69aaa39
f70de15
d6da939
 
 
 
 
 
 
69aaa39
 
 
d6da939
69aaa39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1615d63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aca8e8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f70de15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d6da939
 
 
69aaa39
d6da939
 
69aaa39
d6da939
 
 
 
 
 
 
f70de15
d6da939
 
 
 
f70de15
d6da939
 
 
 
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": 0.008152284677780949,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016304569355561895,
      "eval_loss": 1.2448554039001465,
      "eval_runtime": 99.7518,
      "eval_samples_per_second": 25.894,
      "eval_steps_per_second": 12.952,
      "step": 1
    },
    {
      "epoch": 0.0008152284677780948,
      "grad_norm": 0.6304170489311218,
      "learning_rate": 5e-05,
      "loss": 1.1856,
      "step": 5
    },
    {
      "epoch": 0.0016304569355561896,
      "grad_norm": 0.6049215197563171,
      "learning_rate": 0.0001,
      "loss": 1.0576,
      "step": 10
    },
    {
      "epoch": 0.0016304569355561896,
      "eval_loss": 1.2192050218582153,
      "eval_runtime": 100.1668,
      "eval_samples_per_second": 25.787,
      "eval_steps_per_second": 12.898,
      "step": 10
    },
    {
      "epoch": 0.0024456854033342843,
      "grad_norm": 0.649795413017273,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0736,
      "step": 15
    },
    {
      "epoch": 0.003260913871112379,
      "grad_norm": 0.6032206416130066,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1729,
      "step": 20
    },
    {
      "epoch": 0.003260913871112379,
      "eval_loss": 1.1580919027328491,
      "eval_runtime": 99.6128,
      "eval_samples_per_second": 25.93,
      "eval_steps_per_second": 12.97,
      "step": 20
    },
    {
      "epoch": 0.004076142338890474,
      "grad_norm": 0.7519647479057312,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.096,
      "step": 25
    },
    {
      "epoch": 0.004891370806668569,
      "grad_norm": 0.6601759195327759,
      "learning_rate": 5e-05,
      "loss": 1.0926,
      "step": 30
    },
    {
      "epoch": 0.004891370806668569,
      "eval_loss": 1.1310490369796753,
      "eval_runtime": 98.6894,
      "eval_samples_per_second": 26.173,
      "eval_steps_per_second": 13.092,
      "step": 30
    },
    {
      "epoch": 0.005706599274446664,
      "grad_norm": 0.8596938848495483,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0772,
      "step": 35
    },
    {
      "epoch": 0.006521827742224758,
      "grad_norm": 0.7148851752281189,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1107,
      "step": 40
    },
    {
      "epoch": 0.006521827742224758,
      "eval_loss": 1.120132565498352,
      "eval_runtime": 98.2234,
      "eval_samples_per_second": 26.297,
      "eval_steps_per_second": 13.154,
      "step": 40
    },
    {
      "epoch": 0.0073370562100028534,
      "grad_norm": 0.7597112655639648,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.0479,
      "step": 45
    },
    {
      "epoch": 0.008152284677780949,
      "grad_norm": 0.608223021030426,
      "learning_rate": 0.0,
      "loss": 1.0353,
      "step": 50
    },
    {
      "epoch": 0.008152284677780949,
      "eval_loss": 1.1179903745651245,
      "eval_runtime": 99.164,
      "eval_samples_per_second": 26.048,
      "eval_steps_per_second": 13.029,
      "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": 1954432312934400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}