Hugging Face's logo

Best000
/
4fa97a39-1ba3-4bfc-987e-fd8625fb3956

PEFT
Safetensors
phi
axolotl
Generated from Trainer
Model card Files Community
4fa97a39-1ba3-4bfc-987e-fd8625fb3956
File size: 3,162 Bytes 
4b03c46
 
 
07e7319
4b03c46
07e7319
4b03c46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f8672c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
03e9040
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
07e7319
 
 
 
 
 
 
4b03c46
 
 
 
 
 
 
 
 
 
 
 
 
 
07e7319
4b03c46
 
 
 
07e7319
4b03c46
 
 
 
 
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": 0.08316008316008316,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008316008316008316,
      "grad_norm": 3.69275164604187,
      "learning_rate": 2e-05,
      "loss": 0.8451,
      "step": 1
    },
    {
      "epoch": 0.008316008316008316,
      "eval_loss": 0.845096230506897,
      "eval_runtime": 3.446,
      "eval_samples_per_second": 14.8,
      "eval_steps_per_second": 7.545,
      "step": 1
    },
    {
      "epoch": 0.016632016632016633,
      "grad_norm": 3.2952795028686523,
      "learning_rate": 4e-05,
      "loss": 0.9667,
      "step": 2
    },
    {
      "epoch": 0.02494802494802495,
      "grad_norm": 2.9131577014923096,
      "learning_rate": 6e-05,
      "loss": 0.8653,
      "step": 3
    },
    {
      "epoch": 0.02494802494802495,
      "eval_loss": 0.8450484871864319,
      "eval_runtime": 1.3979,
      "eval_samples_per_second": 36.482,
      "eval_steps_per_second": 18.599,
      "step": 3
    },
    {
      "epoch": 0.033264033264033266,
      "grad_norm": 2.838355779647827,
      "learning_rate": 8e-05,
      "loss": 0.7319,
      "step": 4
    },
    {
      "epoch": 0.04158004158004158,
      "grad_norm": 2.717000722885132,
      "learning_rate": 0.0001,
      "loss": 0.9133,
      "step": 5
    },
    {
      "epoch": 0.0498960498960499,
      "grad_norm": 3.1441810131073,
      "learning_rate": 0.00012,
      "loss": 0.8274,
      "step": 6
    },
    {
      "epoch": 0.0498960498960499,
      "eval_loss": 0.8306875824928284,
      "eval_runtime": 1.4115,
      "eval_samples_per_second": 36.132,
      "eval_steps_per_second": 18.42,
      "step": 6
    },
    {
      "epoch": 0.058212058212058215,
      "grad_norm": 3.0713138580322266,
      "learning_rate": 0.00014,
      "loss": 0.7636,
      "step": 7
    },
    {
      "epoch": 0.06652806652806653,
      "grad_norm": 3.598985195159912,
      "learning_rate": 0.00016,
      "loss": 0.9892,
      "step": 8
    },
    {
      "epoch": 0.07484407484407485,
      "grad_norm": 5.25281286239624,
      "learning_rate": 0.00018,
      "loss": 0.7988,
      "step": 9
    },
    {
      "epoch": 0.07484407484407485,
      "eval_loss": 0.7632012367248535,
      "eval_runtime": 1.4245,
      "eval_samples_per_second": 35.801,
      "eval_steps_per_second": 18.252,
      "step": 9
    },
    {
      "epoch": 0.08316008316008316,
      "grad_norm": 4.665212631225586,
      "learning_rate": 0.0002,
      "loss": 0.7269,
      "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": 784586338467840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}