Hugging Face's logo

kokovova
/
50638f60-4fa8-4a8d-a168-0aecffb42697

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
50638f60-4fa8-4a8d-a168-0aecffb42697
File size: 3,309 Bytes 
211cda4
 
 
67559ac
211cda4
67559ac
211cda4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd01227
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67559ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
211cda4
 
 
 
 
 
 
 
 
 
 
 
 
 
67559ac
211cda4
 
 
 
67559ac
211cda4
 
 
 
 
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": 0.0013417715857503858,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.472571952501286e-05,
      "eval_loss": 2.630528450012207,
      "eval_runtime": 540.3305,
      "eval_samples_per_second": 17.425,
      "eval_steps_per_second": 8.713,
      "step": 1
    },
    {
      "epoch": 0.00013417715857503857,
      "grad_norm": 3.278907060623169,
      "learning_rate": 6e-05,
      "loss": 2.3091,
      "step": 3
    },
    {
      "epoch": 0.00026835431715007714,
      "grad_norm": 3.802938461303711,
      "learning_rate": 0.00012,
      "loss": 2.0507,
      "step": 6
    },
    {
      "epoch": 0.00035780575620010286,
      "eval_loss": 1.4963546991348267,
      "eval_runtime": 540.1565,
      "eval_samples_per_second": 17.43,
      "eval_steps_per_second": 8.716,
      "step": 8
    },
    {
      "epoch": 0.00040253147572511574,
      "grad_norm": 3.5205678939819336,
      "learning_rate": 0.00018,
      "loss": 1.6357,
      "step": 9
    },
    {
      "epoch": 0.0005367086343001543,
      "grad_norm": 3.1275179386138916,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3408,
      "step": 12
    },
    {
      "epoch": 0.0006708857928751929,
      "grad_norm": 2.2836456298828125,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.1946,
      "step": 15
    },
    {
      "epoch": 0.0007156115124002057,
      "eval_loss": 1.2563506364822388,
      "eval_runtime": 539.8455,
      "eval_samples_per_second": 17.44,
      "eval_steps_per_second": 8.721,
      "step": 16
    },
    {
      "epoch": 0.0008050629514502315,
      "grad_norm": 3.6944832801818848,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1612,
      "step": 18
    },
    {
      "epoch": 0.0009392401100252701,
      "grad_norm": 2.832472324371338,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.014,
      "step": 21
    },
    {
      "epoch": 0.0010734172686003086,
      "grad_norm": 2.603668451309204,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.9522,
      "step": 24
    },
    {
      "epoch": 0.0010734172686003086,
      "eval_loss": 1.1618468761444092,
      "eval_runtime": 539.6973,
      "eval_samples_per_second": 17.445,
      "eval_steps_per_second": 8.723,
      "step": 24
    },
    {
      "epoch": 0.0012075944271753472,
      "grad_norm": 2.582103967666626,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2137,
      "step": 27
    },
    {
      "epoch": 0.0013417715857503858,
      "grad_norm": 2.5562214851379395,
      "learning_rate": 0.0,
      "loss": 1.1791,
      "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
}