File size: 3,364 Bytes
3104c4e
836b140
 
 
3104c4e
836b140
3104c4e
 
 
 
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
 
 
 
 
 
3104c4e
 
 
836b140
3104c4e
836b140
3104c4e
 
 
 
 
 
 
 
 
 
 
 
 
836b140
3104c4e
 
 
 
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
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
{
  "best_metric": 0.09463215619325638,
  "best_model_checkpoint": "./falcons-finetuned\\checkpoint-222",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 370,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8604651162790697,
      "eval_loss": 0.502533495426178,
      "eval_runtime": 0.3011,
      "eval_samples_per_second": 428.436,
      "eval_steps_per_second": 109.6,
      "step": 37
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9612403100775194,
      "eval_loss": 0.13876038789749146,
      "eval_runtime": 0.2877,
      "eval_samples_per_second": 448.339,
      "eval_steps_per_second": 114.691,
      "step": 74
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9689922480620154,
      "eval_loss": 0.14742323756217957,
      "eval_runtime": 0.3019,
      "eval_samples_per_second": 427.325,
      "eval_steps_per_second": 109.316,
      "step": 111
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9767441860465116,
      "eval_loss": 0.12268275022506714,
      "eval_runtime": 0.292,
      "eval_samples_per_second": 441.765,
      "eval_steps_per_second": 113.01,
      "step": 148
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9767441860465116,
      "eval_loss": 0.12084222584962845,
      "eval_runtime": 0.2757,
      "eval_samples_per_second": 467.823,
      "eval_steps_per_second": 119.676,
      "step": 185
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9767441860465116,
      "eval_loss": 0.09463215619325638,
      "eval_runtime": 0.2864,
      "eval_samples_per_second": 450.424,
      "eval_steps_per_second": 115.225,
      "step": 222
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9844961240310077,
      "eval_loss": 0.10351040214300156,
      "eval_runtime": 0.2903,
      "eval_samples_per_second": 444.346,
      "eval_steps_per_second": 113.67,
      "step": 259
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9844961240310077,
      "eval_loss": 0.10580696165561676,
      "eval_runtime": 0.2804,
      "eval_samples_per_second": 460.04,
      "eval_steps_per_second": 117.685,
      "step": 296
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9844961240310077,
      "eval_loss": 0.10663236677646637,
      "eval_runtime": 0.2805,
      "eval_samples_per_second": 459.887,
      "eval_steps_per_second": 117.645,
      "step": 333
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9844961240310077,
      "eval_loss": 0.10691161453723907,
      "eval_runtime": 0.2546,
      "eval_samples_per_second": 506.593,
      "eval_steps_per_second": 129.593,
      "step": 370
    }
  ],
  "logging_steps": 500,
  "max_steps": 370,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 48351462773760.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}