Hugging Face's logo

cot2output
/
007bbfb7_1B_ttt

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
007bbfb7_1B_ttt
File size: 3,010 Bytes 
47d382c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
125
126
127
128
129
130
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.30759354865342,
      "learning_rate": 0.0002,
      "loss": 0.1652,
      "step": 1
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.1131666477408941,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.138,
      "step": 2
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.47524766678471886,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0704,
      "step": 3
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.05938142538070679,
      "eval_runtime": 0.4827,
      "eval_samples_per_second": 10.359,
      "eval_steps_per_second": 2.072,
      "step": 3
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4069628072320713,
      "learning_rate": 0.000138268343236509,
      "loss": 0.057,
      "step": 4
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.130205569009941,
      "learning_rate": 0.0001,
      "loss": 0.036,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1675979787627749,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0379,
      "step": 6
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.04690684378147125,
      "eval_runtime": 0.3769,
      "eval_samples_per_second": 13.268,
      "eval_steps_per_second": 2.654,
      "step": 6
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.12675730588511827,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0295,
      "step": 7
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.12228622531109234,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0335,
      "step": 8
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10097323878812325,
      "learning_rate": 0.0,
      "loss": 0.0248,
      "step": 9
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.04368260130286217,
      "eval_runtime": 0.5921,
      "eval_samples_per_second": 8.445,
      "eval_steps_per_second": 1.689,
      "step": 9
    },
    {
      "epoch": 3.0,
      "step": 9,
      "total_flos": 1111501938688.0,
      "train_loss": 0.06581349981327851,
      "train_runtime": 50.5729,
      "train_samples_per_second": 5.042,
      "train_steps_per_second": 0.178
    }
  ],
  "logging_steps": 1,
  "max_steps": 9,
  "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": 1111501938688.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}