File size: 1,494 Bytes
bf318a5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 1000,
  "global_step": 192,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 3.1876933574676514,
      "learning_rate": 2.794447789131517e-05,
      "loss": 6.9797,
      "step": 50
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 3.0499606132507324,
      "learning_rate": 1.691261184798162e-05,
      "loss": 3.4736,
      "step": 100
    },
    {
      "epoch": 6.25,
      "grad_norm": 2.7588396072387695,
      "learning_rate": 4.393398282201788e-06,
      "loss": 3.1606,
      "step": 150
    }
  ],
  "logging_steps": 50,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1138408789377024.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}