File size: 1,273 Bytes
57186e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.952755905511811,
  "eval_steps": 500,
  "global_step": 31,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.44528138637542725,
      "learning_rate": 0.00019992479525042303,
      "loss": 0.2258,
      "step": 10
    },
    {
      "epoch": 1.2598425196850394,
      "grad_norm": 0.5534960627555847,
      "learning_rate": 0.0001910362940966147,
      "loss": 0.1043,
      "step": 20
    },
    {
      "epoch": 1.889763779527559,
      "grad_norm": 0.2573888301849365,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.0748,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 3.59581784881152e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}