Hugging Face's logo

Dnsx077
/
9afab859-041c-4be2-bc68-d445a6d8e40f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
9afab859-041c-4be2-bc68-d445a6d8e40f
File size: 3,201 Bytes 
8922e0c
 
 
5937331
8922e0c
5937331
8922e0c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
172b7d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a035e29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5937331
 
 
 
 
 
 
8922e0c
 
 
 
 
 
 
 
 
 
 
 
 
 
5937331
8922e0c
 
 
 
5937331
8922e0c
 
 
 
 
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": 0.02622950819672131,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002622950819672131,
      "grad_norm": 0.031223058700561523,
      "learning_rate": 2e-05,
      "loss": 11.756,
      "step": 1
    },
    {
      "epoch": 0.002622950819672131,
      "eval_loss": 11.759812355041504,
      "eval_runtime": 5.877,
      "eval_samples_per_second": 27.395,
      "eval_steps_per_second": 13.782,
      "step": 1
    },
    {
      "epoch": 0.005245901639344262,
      "grad_norm": 0.03421200439333916,
      "learning_rate": 4e-05,
      "loss": 11.756,
      "step": 2
    },
    {
      "epoch": 0.007868852459016393,
      "grad_norm": 0.04382362961769104,
      "learning_rate": 6e-05,
      "loss": 11.7597,
      "step": 3
    },
    {
      "epoch": 0.007868852459016393,
      "eval_loss": 11.759759902954102,
      "eval_runtime": 6.9009,
      "eval_samples_per_second": 23.33,
      "eval_steps_per_second": 11.738,
      "step": 3
    },
    {
      "epoch": 0.010491803278688525,
      "grad_norm": 0.02897525578737259,
      "learning_rate": 8e-05,
      "loss": 11.7588,
      "step": 4
    },
    {
      "epoch": 0.013114754098360656,
      "grad_norm": 0.04384247586131096,
      "learning_rate": 0.0001,
      "loss": 11.7601,
      "step": 5
    },
    {
      "epoch": 0.015737704918032787,
      "grad_norm": 0.04108477011322975,
      "learning_rate": 0.00012,
      "loss": 11.7592,
      "step": 6
    },
    {
      "epoch": 0.015737704918032787,
      "eval_loss": 11.75953197479248,
      "eval_runtime": 6.1771,
      "eval_samples_per_second": 26.064,
      "eval_steps_per_second": 13.113,
      "step": 6
    },
    {
      "epoch": 0.018360655737704918,
      "grad_norm": 0.03210461512207985,
      "learning_rate": 0.00014,
      "loss": 11.7568,
      "step": 7
    },
    {
      "epoch": 0.02098360655737705,
      "grad_norm": 0.042795587331056595,
      "learning_rate": 0.00016,
      "loss": 11.7597,
      "step": 8
    },
    {
      "epoch": 0.02360655737704918,
      "grad_norm": 0.03623143583536148,
      "learning_rate": 0.00018,
      "loss": 11.7611,
      "step": 9
    },
    {
      "epoch": 0.02360655737704918,
      "eval_loss": 11.759139060974121,
      "eval_runtime": 6.1857,
      "eval_samples_per_second": 26.028,
      "eval_steps_per_second": 13.095,
      "step": 9
    },
    {
      "epoch": 0.02622950819672131,
      "grad_norm": 0.03370063751935959,
      "learning_rate": 0.0002,
      "loss": 11.7614,
      "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": 4074000875520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}