File size: 1,397 Bytes
5a53578
 
 
 
 
 
 
 
 
 
 
 
918f4cd
 
 
 
5a53578
 
 
 
918f4cd
 
 
 
5a53578
 
 
 
 
918f4cd
 
 
 
5a53578
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
918f4cd
5a53578
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 1.8345922231674194,
      "eval_runtime": 13.5492,
      "eval_samples_per_second": 7.454,
      "eval_steps_per_second": 0.295,
      "step": 1
    },
    {
      "epoch": 1.6,
      "eval_loss": 1.7085474729537964,
      "eval_runtime": 13.4084,
      "eval_samples_per_second": 7.533,
      "eval_steps_per_second": 0.298,
      "step": 3
    },
    {
      "epoch": 1.6,
      "step": 3,
      "total_flos": 1.9221024474136576e+16,
      "train_loss": 1.8231021563212078,
      "train_runtime": 1450.8496,
      "train_samples_per_second": 3.968,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 10,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9221024474136576e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}