File size: 1,650 Bytes
8fbb652
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9411764705882355,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.6052117347717285,
      "learning_rate": 0.000941764705882353,
      "loss": 0.4992,
      "step": 100
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.9228031635284424,
      "learning_rate": 0.0008829411764705883,
      "loss": 0.3017,
      "step": 200
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.9054152965545654,
      "learning_rate": 0.0008241176470588235,
      "loss": 0.2262,
      "step": 300
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 1.4709264039993286,
      "learning_rate": 0.0007652941176470588,
      "loss": 0.2054,
      "step": 400
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.9707149267196655,
      "learning_rate": 0.0007064705882352941,
      "loss": 0.189,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 1700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 33070633058304.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}