File size: 3,191 Bytes
969b29a
 
 
96bd113
969b29a
96bd113
969b29a
 
 
 
 
 
1a3cfb7
969b29a
 
 
 
 
 
 
1a3cfb7
 
969b29a
 
 
 
 
1a3cfb7
969b29a
 
 
 
 
 
1a3cfb7
969b29a
1a3cfb7
969b29a
 
 
 
1a3cfb7
 
 
 
969b29a
11a604d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49aa339
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96bd113
 
 
 
 
 
 
969b29a
 
 
 
 
 
 
 
 
 
 
 
 
 
96bd113
969b29a
 
 
 
96bd113
969b29a
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005647324579980234,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005647324579980235,
      "grad_norm": 6.638052463531494,
      "learning_rate": 2e-05,
      "loss": 3.0027,
      "step": 1
    },
    {
      "epoch": 0.0005647324579980235,
      "eval_loss": 2.7413086891174316,
      "eval_runtime": 209.2602,
      "eval_samples_per_second": 3.565,
      "eval_steps_per_second": 1.782,
      "step": 1
    },
    {
      "epoch": 0.001129464915996047,
      "grad_norm": 4.598910331726074,
      "learning_rate": 4e-05,
      "loss": 2.5806,
      "step": 2
    },
    {
      "epoch": 0.0016941973739940702,
      "grad_norm": 4.744904041290283,
      "learning_rate": 6e-05,
      "loss": 3.2161,
      "step": 3
    },
    {
      "epoch": 0.0016941973739940702,
      "eval_loss": 2.631173849105835,
      "eval_runtime": 213.0702,
      "eval_samples_per_second": 3.501,
      "eval_steps_per_second": 1.751,
      "step": 3
    },
    {
      "epoch": 0.002258929831992094,
      "grad_norm": 5.976100444793701,
      "learning_rate": 8e-05,
      "loss": 3.5525,
      "step": 4
    },
    {
      "epoch": 0.002823662289990117,
      "grad_norm": 3.7647323608398438,
      "learning_rate": 0.0001,
      "loss": 3.0432,
      "step": 5
    },
    {
      "epoch": 0.0033883947479881405,
      "grad_norm": 3.4719369411468506,
      "learning_rate": 0.00012,
      "loss": 2.3622,
      "step": 6
    },
    {
      "epoch": 0.0033883947479881405,
      "eval_loss": 2.1884851455688477,
      "eval_runtime": 211.9746,
      "eval_samples_per_second": 3.519,
      "eval_steps_per_second": 1.76,
      "step": 6
    },
    {
      "epoch": 0.003953127205986164,
      "grad_norm": 2.7659006118774414,
      "learning_rate": 0.00014,
      "loss": 2.2277,
      "step": 7
    },
    {
      "epoch": 0.004517859663984188,
      "grad_norm": 3.1263272762298584,
      "learning_rate": 0.00016,
      "loss": 1.9746,
      "step": 8
    },
    {
      "epoch": 0.005082592121982211,
      "grad_norm": 3.476619243621826,
      "learning_rate": 0.00018,
      "loss": 1.862,
      "step": 9
    },
    {
      "epoch": 0.005082592121982211,
      "eval_loss": 2.234940528869629,
      "eval_runtime": 211.6585,
      "eval_samples_per_second": 3.525,
      "eval_steps_per_second": 1.762,
      "step": 9
    },
    {
      "epoch": 0.005647324579980234,
      "grad_norm": 4.247814655303955,
      "learning_rate": 0.0002,
      "loss": 1.8169,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.533788723085312e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}