Hugging Face's logo

Best000
/
ecbed47a-4eda-41b5-8918-1293ed04a164

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
ecbed47a-4eda-41b5-8918-1293ed04a164
File size: 3,222 Bytes 
3b842ee
 
 
a1c35cc
3b842ee
a1c35cc
3b842ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41e194e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87273ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1c35cc
 
 
 
 
 
 
3b842ee
 
 
 
 
 
 
 
 
 
 
 
 
 
a1c35cc
3b842ee
 
 
 
a1c35cc
3b842ee
 
 
 
 
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
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00023621256768966393,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.3621256768966393e-05,
      "grad_norm": 0.8800978660583496,
      "learning_rate": 2e-05,
      "loss": 7.4129,
      "step": 1
    },
    {
      "epoch": 2.3621256768966393e-05,
      "eval_loss": 1.6822291612625122,
      "eval_runtime": 1333.2677,
      "eval_samples_per_second": 13.37,
      "eval_steps_per_second": 6.685,
      "step": 1
    },
    {
      "epoch": 4.7242513537932786e-05,
      "grad_norm": 0.8495243191719055,
      "learning_rate": 4e-05,
      "loss": 5.8307,
      "step": 2
    },
    {
      "epoch": 7.086377030689917e-05,
      "grad_norm": 0.8420003652572632,
      "learning_rate": 6e-05,
      "loss": 6.893,
      "step": 3
    },
    {
      "epoch": 7.086377030689917e-05,
      "eval_loss": 1.6812106370925903,
      "eval_runtime": 1336.9399,
      "eval_samples_per_second": 13.333,
      "eval_steps_per_second": 6.667,
      "step": 3
    },
    {
      "epoch": 9.448502707586557e-05,
      "grad_norm": 0.9201523065567017,
      "learning_rate": 8e-05,
      "loss": 6.5537,
      "step": 4
    },
    {
      "epoch": 0.00011810628384483197,
      "grad_norm": 0.8098495006561279,
      "learning_rate": 0.0001,
      "loss": 7.3419,
      "step": 5
    },
    {
      "epoch": 0.00014172754061379835,
      "grad_norm": 1.112677812576294,
      "learning_rate": 0.00012,
      "loss": 7.3867,
      "step": 6
    },
    {
      "epoch": 0.00014172754061379835,
      "eval_loss": 1.644856333732605,
      "eval_runtime": 1337.5689,
      "eval_samples_per_second": 13.327,
      "eval_steps_per_second": 6.664,
      "step": 6
    },
    {
      "epoch": 0.00016534879738276475,
      "grad_norm": 1.1206536293029785,
      "learning_rate": 0.00014,
      "loss": 6.9054,
      "step": 7
    },
    {
      "epoch": 0.00018897005415173114,
      "grad_norm": 0.9806450605392456,
      "learning_rate": 0.00016,
      "loss": 6.1312,
      "step": 8
    },
    {
      "epoch": 0.00021259131092069754,
      "grad_norm": 1.225191593170166,
      "learning_rate": 0.00018,
      "loss": 7.6522,
      "step": 9
    },
    {
      "epoch": 0.00021259131092069754,
      "eval_loss": 1.5392491817474365,
      "eval_runtime": 1337.6222,
      "eval_samples_per_second": 13.327,
      "eval_steps_per_second": 6.663,
      "step": 9
    },
    {
      "epoch": 0.00023621256768966393,
      "grad_norm": 1.4865165948867798,
      "learning_rate": 0.0002,
      "loss": 6.1353,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6196217134448640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}