File size: 3,689 Bytes
d9008cc
 
 
0e99df4
038540c
0e99df4
d9008cc
 
 
 
 
 
 
038540c
 
 
d9008cc
038540c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d9e33d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c652319
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e99df4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9008cc
 
 
038540c
d9008cc
 
038540c
d9008cc
 
 
 
 
 
 
0e99df4
d9008cc
 
 
 
0e99df4
d9008cc
 
 
 
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": 0.7936507936507936,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015873015873015872,
      "eval_loss": 5.212655544281006,
      "eval_runtime": 0.7189,
      "eval_samples_per_second": 37.556,
      "eval_steps_per_second": 19.474,
      "step": 1
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 4.168554782867432,
      "learning_rate": 5e-05,
      "loss": 4.8611,
      "step": 5
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 4.182918071746826,
      "learning_rate": 0.0001,
      "loss": 4.8016,
      "step": 10
    },
    {
      "epoch": 0.15873015873015872,
      "eval_loss": 4.441361904144287,
      "eval_runtime": 0.7142,
      "eval_samples_per_second": 37.805,
      "eval_steps_per_second": 19.602,
      "step": 10
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 4.0556817054748535,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.9843,
      "step": 15
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 2.6014246940612793,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.1812,
      "step": 20
    },
    {
      "epoch": 0.31746031746031744,
      "eval_loss": 3.064946413040161,
      "eval_runtime": 0.8004,
      "eval_samples_per_second": 33.732,
      "eval_steps_per_second": 17.491,
      "step": 20
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 2.9831440448760986,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.9105,
      "step": 25
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.131338596343994,
      "learning_rate": 5e-05,
      "loss": 2.7696,
      "step": 30
    },
    {
      "epoch": 0.47619047619047616,
      "eval_loss": 2.777977228164673,
      "eval_runtime": 0.7213,
      "eval_samples_per_second": 37.432,
      "eval_steps_per_second": 19.409,
      "step": 30
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.399858236312866,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.8032,
      "step": 35
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 3.2086362838745117,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.9717,
      "step": 40
    },
    {
      "epoch": 0.6349206349206349,
      "eval_loss": 2.7027430534362793,
      "eval_runtime": 0.7248,
      "eval_samples_per_second": 37.252,
      "eval_steps_per_second": 19.316,
      "step": 40
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 3.187225103378296,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.9323,
      "step": 45
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 3.1809988021850586,
      "learning_rate": 0.0,
      "loss": 2.6594,
      "step": 50
    },
    {
      "epoch": 0.7936507936507936,
      "eval_loss": 2.692059278488159,
      "eval_runtime": 0.7048,
      "eval_samples_per_second": 38.309,
      "eval_steps_per_second": 19.864,
      "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": 1202727577190400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}