Hugging Face's logo

tarabukinivan
/
7318b423-8316-49df-a383-964727148d7f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7318b423-8316-49df-a383-964727148d7f
File size: 4,190 Bytes 
4a4abfa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008437928488556059,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437928488556059e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.437928488556059e-05,
      "eval_loss": NaN,
      "eval_runtime": 1842.8607,
      "eval_samples_per_second": 2.708,
      "eval_steps_per_second": 1.354,
      "step": 1
    },
    {
      "epoch": 0.00016875856977112118,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00016875856977112118,
      "eval_loss": NaN,
      "eval_runtime": 1842.7402,
      "eval_samples_per_second": 2.708,
      "eval_steps_per_second": 1.354,
      "step": 2
    },
    {
      "epoch": 0.0002531378546566818,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002531378546566818,
      "eval_loss": NaN,
      "eval_runtime": 1842.9623,
      "eval_samples_per_second": 2.708,
      "eval_steps_per_second": 1.354,
      "step": 3
    },
    {
      "epoch": 0.00033751713954224236,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00033751713954224236,
      "eval_loss": NaN,
      "eval_runtime": 1843.277,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.354,
      "step": 4
    },
    {
      "epoch": 0.00042189642442780296,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00042189642442780296,
      "eval_loss": NaN,
      "eval_runtime": 1843.4451,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.353,
      "step": 5
    },
    {
      "epoch": 0.0005062757093133636,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005062757093133636,
      "eval_loss": NaN,
      "eval_runtime": 1843.4552,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.353,
      "step": 6
    },
    {
      "epoch": 0.0005906549941989242,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0005906549941989242,
      "eval_loss": NaN,
      "eval_runtime": 1843.235,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.354,
      "step": 7
    },
    {
      "epoch": 0.0006750342790844847,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0006750342790844847,
      "eval_loss": NaN,
      "eval_runtime": 1843.3534,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.354,
      "step": 8
    },
    {
      "epoch": 0.0007594135639700454,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0007594135639700454,
      "eval_loss": NaN,
      "eval_runtime": 1843.1976,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.354,
      "step": 9
    },
    {
      "epoch": 0.0008437928488556059,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008437928488556059,
      "eval_loss": NaN,
      "eval_runtime": 1843.6709,
      "eval_samples_per_second": 2.707,
      "eval_steps_per_second": 1.353,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2693163474944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}