File size: 3,058 Bytes
a33a630
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.7025482654571533,
  "best_model_checkpoint": "../../models/lora/codellama-34b-multitask_cot_reflection/checkpoint-200",
  "epoch": 12.5,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.62,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.9595,
      "step": 10
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.9443,
      "step": 20
    },
    {
      "epoch": 1.88,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.7826,
      "step": 30
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.4385,
      "step": 40
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00015,
      "loss": 1.0892,
      "step": 50
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.9362,
      "step": 60
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.9101,
      "step": 70
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8864,
      "step": 80
    },
    {
      "epoch": 5.62,
      "learning_rate": 0.00027,
      "loss": 0.8796,
      "step": 90
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.0003,
      "loss": 0.8521,
      "step": 100
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.0002921052631578947,
      "loss": 0.7999,
      "step": 110
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.0002842105263157894,
      "loss": 0.7828,
      "step": 120
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.0002763157894736842,
      "loss": 0.7696,
      "step": 130
    },
    {
      "epoch": 8.75,
      "learning_rate": 0.0002684210526315789,
      "loss": 0.7555,
      "step": 140
    },
    {
      "epoch": 9.38,
      "learning_rate": 0.0002605263157894737,
      "loss": 0.7609,
      "step": 150
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00025263157894736836,
      "loss": 0.7509,
      "step": 160
    },
    {
      "epoch": 10.62,
      "learning_rate": 0.00024473684210526314,
      "loss": 0.7587,
      "step": 170
    },
    {
      "epoch": 11.25,
      "learning_rate": 0.00023684210526315788,
      "loss": 0.7453,
      "step": 180
    },
    {
      "epoch": 11.88,
      "learning_rate": 0.00022894736842105263,
      "loss": 0.7222,
      "step": 190
    },
    {
      "epoch": 12.5,
      "learning_rate": 0.00022105263157894733,
      "loss": 0.7216,
      "step": 200
    },
    {
      "epoch": 12.5,
      "eval_loss": 0.7025482654571533,
      "eval_runtime": 3.0725,
      "eval_samples_per_second": 6.835,
      "eval_steps_per_second": 0.976,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 480,
  "num_train_epochs": 30,
  "save_steps": 200,
  "total_flos": 1.329044322253013e+18,
  "trial_name": null,
  "trial_params": null
}