Hugging Face's logo

kokovova
/
d51e8f29-8b2f-4c15-8653-61d8461ea996

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
d51e8f29-8b2f-4c15-8653-61d8461ea996
File size: 3,287 Bytes
e85e8ed
 
 
d2ec866
e85e8ed
d2ec866
e85e8ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf70435
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2ec866
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e85e8ed
 
 
 
 
 
 
 
 
 
 
 
 
 
d2ec866
e85e8ed
 
 
 
d2ec866
e85e8ed
 
 
 
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": 0.017069701280227598,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 9.121294021606445,
      "eval_runtime": 43.1024,
      "eval_samples_per_second": 17.168,
      "eval_steps_per_second": 8.584,
      "step": 1
    },
    {
      "epoch": 0.0017069701280227596,
      "grad_norm": 16.72486686706543,
      "learning_rate": 6e-05,
      "loss": 8.6592,
      "step": 3
    },
    {
      "epoch": 0.0034139402560455193,
      "grad_norm": 14.888457298278809,
      "learning_rate": 0.00012,
      "loss": 7.913,
      "step": 6
    },
    {
      "epoch": 0.004551920341394026,
      "eval_loss": 3.8307814598083496,
      "eval_runtime": 42.5013,
      "eval_samples_per_second": 17.411,
      "eval_steps_per_second": 8.706,
      "step": 8
    },
    {
      "epoch": 0.005120910384068279,
      "grad_norm": 12.3302001953125,
      "learning_rate": 0.00018,
      "loss": 4.487,
      "step": 9
    },
    {
      "epoch": 0.0068278805120910386,
      "grad_norm": 18.477922439575195,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.4117,
      "step": 12
    },
    {
      "epoch": 0.008534850640113799,
      "grad_norm": 13.56683349609375,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.1899,
      "step": 15
    },
    {
      "epoch": 0.009103840682788052,
      "eval_loss": 1.833335280418396,
      "eval_runtime": 42.6016,
      "eval_samples_per_second": 17.37,
      "eval_steps_per_second": 8.685,
      "step": 16
    },
    {
      "epoch": 0.010241820768136558,
      "grad_norm": 18.128826141357422,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.728,
      "step": 18
    },
    {
      "epoch": 0.011948790896159318,
      "grad_norm": 15.941401481628418,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.4067,
      "step": 21
    },
    {
      "epoch": 0.013655761024182077,
      "grad_norm": 10.316154479980469,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.4947,
      "step": 24
    },
    {
      "epoch": 0.013655761024182077,
      "eval_loss": 1.5885289907455444,
      "eval_runtime": 42.6387,
      "eval_samples_per_second": 17.355,
      "eval_steps_per_second": 8.678,
      "step": 24
    },
    {
      "epoch": 0.015362731152204837,
      "grad_norm": 5.8392181396484375,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.4468,
      "step": 27
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": 8.035550117492676,
      "learning_rate": 0.0,
      "loss": 1.823,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}