Hugging Face's logo

jssky
/
d382ccac-6fe4-4666-ab30-471b41683145

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d382ccac-6fe4-4666-ab30-471b41683145
File size: 3,095 Bytes 
eee33b1
 
 
732159a
eee33b1
732159a
eee33b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24537dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb8316b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
732159a
 
 
 
 
 
 
eee33b1
 
 
 
 
 
 
 
 
 
 
 
 
 
732159a
eee33b1
 
 
 
732159a
eee33b1
 
 
 
 
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": 0.04287245444801715,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004287245444801715,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 15.9631,
      "step": 1
    },
    {
      "epoch": 0.004287245444801715,
      "eval_loss": 16.551647186279297,
      "eval_runtime": 0.5073,
      "eval_samples_per_second": 98.556,
      "eval_steps_per_second": 98.556,
      "step": 1
    },
    {
      "epoch": 0.00857449088960343,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 16.1876,
      "step": 2
    },
    {
      "epoch": 0.012861736334405145,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 16.0269,
      "step": 3
    },
    {
      "epoch": 0.012861736334405145,
      "eval_loss": 16.551647186279297,
      "eval_runtime": 0.492,
      "eval_samples_per_second": 101.631,
      "eval_steps_per_second": 101.631,
      "step": 3
    },
    {
      "epoch": 0.01714898177920686,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 17.5816,
      "step": 4
    },
    {
      "epoch": 0.021436227224008574,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 16.6133,
      "step": 5
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 18.79177474975586,
      "learning_rate": 2e-05,
      "loss": 17.427,
      "step": 6
    },
    {
      "epoch": 0.02572347266881029,
      "eval_loss": 16.551647186279297,
      "eval_runtime": 0.4925,
      "eval_samples_per_second": 101.517,
      "eval_steps_per_second": 101.517,
      "step": 6
    },
    {
      "epoch": 0.030010718113612004,
      "grad_norm": 17.39157485961914,
      "learning_rate": 4e-05,
      "loss": 17.1975,
      "step": 7
    },
    {
      "epoch": 0.03429796355841372,
      "grad_norm": 18.5988826751709,
      "learning_rate": 6e-05,
      "loss": 16.2112,
      "step": 8
    },
    {
      "epoch": 0.03858520900321544,
      "grad_norm": 19.167139053344727,
      "learning_rate": 8e-05,
      "loss": 17.2223,
      "step": 9
    },
    {
      "epoch": 0.03858520900321544,
      "eval_loss": 16.201391220092773,
      "eval_runtime": 0.4652,
      "eval_samples_per_second": 107.473,
      "eval_steps_per_second": 107.473,
      "step": 9
    },
    {
      "epoch": 0.04287245444801715,
      "grad_norm": 17.39168930053711,
      "learning_rate": 0.0001,
      "loss": 15.691,
      "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": 43272886026240.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}