File size: 2,161 Bytes
fa3ac10
 
 
6e977ac
fa3ac10
6e977ac
fa3ac10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b4f6a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6e977ac
 
 
 
 
 
 
fa3ac10
 
 
 
 
 
 
 
 
 
 
 
 
 
6e977ac
fa3ac10
 
 
 
6e977ac
fa3ac10
 
 
 
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": 0.07804878048780488,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015609756097560976,
      "grad_norm": 0.6015342473983765,
      "learning_rate": 1e-05,
      "loss": 6.8893,
      "step": 1
    },
    {
      "epoch": 0.015609756097560976,
      "eval_loss": 6.875264644622803,
      "eval_runtime": 11.2183,
      "eval_samples_per_second": 9.627,
      "eval_steps_per_second": 4.814,
      "step": 1
    },
    {
      "epoch": 0.03121951219512195,
      "grad_norm": 0.6219642162322998,
      "learning_rate": 2e-05,
      "loss": 6.877,
      "step": 2
    },
    {
      "epoch": 0.03121951219512195,
      "eval_loss": 6.875111103057861,
      "eval_runtime": 0.1733,
      "eval_samples_per_second": 623.041,
      "eval_steps_per_second": 311.52,
      "step": 2
    },
    {
      "epoch": 0.04682926829268293,
      "grad_norm": 0.595236599445343,
      "learning_rate": 3e-05,
      "loss": 6.8781,
      "step": 3
    },
    {
      "epoch": 0.0624390243902439,
      "grad_norm": 0.6043254733085632,
      "learning_rate": 4e-05,
      "loss": 6.8834,
      "step": 4
    },
    {
      "epoch": 0.0624390243902439,
      "eval_loss": 6.87425422668457,
      "eval_runtime": 0.1762,
      "eval_samples_per_second": 613.036,
      "eval_steps_per_second": 306.518,
      "step": 4
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 0.5619105696678162,
      "learning_rate": 5e-05,
      "loss": 6.8799,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 29662433280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}