File size: 2,226 Bytes
4aa6dca
 
 
dab7a00
5ce3c2b
dab7a00
4aa6dca
 
 
 
 
 
 
5ce3c2b
 
 
4aa6dca
5ce3c2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dab7a00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4aa6dca
 
 
5ce3c2b
4aa6dca
 
5ce3c2b
4aa6dca
 
 
 
 
 
 
5ce3c2b
4aa6dca
 
 
 
dab7a00
4aa6dca
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1216374269005848,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 2.005504608154297,
      "eval_runtime": 4.0241,
      "eval_samples_per_second": 22.365,
      "eval_steps_per_second": 11.183,
      "step": 1
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.7950891256332397,
      "learning_rate": 5e-05,
      "loss": 2.0743,
      "step": 5
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 1.2534737586975098,
      "learning_rate": 0.0001,
      "loss": 2.0283,
      "step": 10
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 1.9290282726287842,
      "eval_runtime": 2.8458,
      "eval_samples_per_second": 31.626,
      "eval_steps_per_second": 15.813,
      "step": 10
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 1.6386820077896118,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9657,
      "step": 15
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 1.2416112422943115,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7649,
      "step": 20
    },
    {
      "epoch": 0.0935672514619883,
      "eval_loss": 1.619399905204773,
      "eval_runtime": 2.8407,
      "eval_samples_per_second": 31.683,
      "eval_steps_per_second": 15.841,
      "step": 20
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 1.6186881065368652,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6088,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1184686663532544.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}