File size: 1,764 Bytes
fe78d3e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 18.8138,
      "eval_loss": 1.9523861408233643,
      "eval_rouge1": 0.4483,
      "eval_rouge2": 0.1963,
      "eval_rougeL": 0.3162,
      "eval_rougeLsum": 0.3163,
      "eval_runtime": 2953.9269,
      "eval_samples_per_second": 0.271,
      "eval_steps_per_second": 0.135,
      "step": 400
    },
    {
      "epoch": 1.25,
      "grad_norm": 29.538663864135742,
      "learning_rate": 1.1733333333333335e-05,
      "loss": 2.2642,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 18.815,
      "eval_loss": 1.878754734992981,
      "eval_rouge1": 0.4566,
      "eval_rouge2": 0.2145,
      "eval_rougeL": 0.3285,
      "eval_rougeLsum": 0.3287,
      "eval_runtime": 3021.6367,
      "eval_samples_per_second": 0.265,
      "eval_steps_per_second": 0.132,
      "step": 800
    },
    {
      "epoch": 2.5,
      "grad_norm": 38.89383316040039,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 1.8259,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5999610134753280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}