Hugging Face's logo

nblinh63
/
65e522af-438e-44c6-86ee-bd0668430ddb

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
65e522af-438e-44c6-86ee-bd0668430ddb
File size: 3,054 Bytes 
3f99e3b
 
 
b2c24dc
3f99e3b
b2c24dc
3f99e3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f6661be
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2c24dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f99e3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2c24dc
3f99e3b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013644633110976349,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015160703456640388,
      "grad_norm": 16.83426284790039,
      "learning_rate": 2e-05,
      "loss": 11.4822,
      "step": 1
    },
    {
      "epoch": 0.00015160703456640388,
      "eval_loss": 11.705659866333008,
      "eval_runtime": 94.653,
      "eval_samples_per_second": 29.349,
      "eval_steps_per_second": 14.675,
      "step": 1
    },
    {
      "epoch": 0.00030321406913280777,
      "grad_norm": 24.82701301574707,
      "learning_rate": 4e-05,
      "loss": 11.0969,
      "step": 2
    },
    {
      "epoch": 0.00045482110369921165,
      "grad_norm": 12.29438591003418,
      "learning_rate": 6e-05,
      "loss": 12.4466,
      "step": 3
    },
    {
      "epoch": 0.00045482110369921165,
      "eval_loss": 11.678789138793945,
      "eval_runtime": 91.2328,
      "eval_samples_per_second": 30.45,
      "eval_steps_per_second": 15.225,
      "step": 3
    },
    {
      "epoch": 0.0006064281382656155,
      "grad_norm": 21.273990631103516,
      "learning_rate": 8e-05,
      "loss": 11.3351,
      "step": 4
    },
    {
      "epoch": 0.0007580351728320194,
      "grad_norm": 16.648815155029297,
      "learning_rate": 0.0001,
      "loss": 11.359,
      "step": 5
    },
    {
      "epoch": 0.0009096422073984233,
      "grad_norm": 19.553115844726562,
      "learning_rate": 0.00012,
      "loss": 11.2096,
      "step": 6
    },
    {
      "epoch": 0.0009096422073984233,
      "eval_loss": 11.353554725646973,
      "eval_runtime": 91.1262,
      "eval_samples_per_second": 30.485,
      "eval_steps_per_second": 15.243,
      "step": 6
    },
    {
      "epoch": 0.001061249241964827,
      "grad_norm": 15.552982330322266,
      "learning_rate": 0.00014,
      "loss": 10.9988,
      "step": 7
    },
    {
      "epoch": 0.001212856276531231,
      "grad_norm": 14.931906700134277,
      "learning_rate": 0.00016,
      "loss": 11.3466,
      "step": 8
    },
    {
      "epoch": 0.0013644633110976349,
      "grad_norm": 15.584132194519043,
      "learning_rate": 0.00018,
      "loss": 10.5936,
      "step": 9
    },
    {
      "epoch": 0.0013644633110976349,
      "eval_loss": 10.818541526794434,
      "eval_runtime": 91.1349,
      "eval_samples_per_second": 30.482,
      "eval_steps_per_second": 15.241,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4886913613824.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}