Hugging Face's logo

oldiday
/
52c874f2-b880-4b3e-9a2f-a4daac899630

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
52c874f2-b880-4b3e-9a2f-a4daac899630
File size: 3,841 Bytes 
cf6bb11
 
 
3ef51c3
cf6bb11
3ef51c3
cf6bb11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2727d78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a7dc203
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ef51c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf6bb11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ef51c3
cf6bb11
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8888888888888888,
  "eval_steps": 9,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024691358024691357,
      "eval_loss": 2.1480655670166016,
      "eval_runtime": 1.0117,
      "eval_samples_per_second": 68.202,
      "eval_steps_per_second": 8.896,
      "step": 1
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.17830029129981995,
      "learning_rate": 1.5e-05,
      "loss": 2.2572,
      "step": 3
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.21468417346477509,
      "learning_rate": 3e-05,
      "loss": 2.2267,
      "step": 6
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.22635942697525024,
      "learning_rate": 4.5e-05,
      "loss": 2.271,
      "step": 9
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 2.143685817718506,
      "eval_runtime": 1.0061,
      "eval_samples_per_second": 68.58,
      "eval_steps_per_second": 8.945,
      "step": 9
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.1852104514837265,
      "learning_rate": 4.993910125649561e-05,
      "loss": 2.2203,
      "step": 12
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.24263235926628113,
      "learning_rate": 4.962019382530521e-05,
      "loss": 2.165,
      "step": 15
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.24341049790382385,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 2.2557,
      "step": 18
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 2.1180965900421143,
      "eval_runtime": 1.0063,
      "eval_samples_per_second": 68.568,
      "eval_steps_per_second": 8.944,
      "step": 18
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.2104165405035019,
      "learning_rate": 4.817959636416969e-05,
      "loss": 2.2173,
      "step": 21
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1979183554649353,
      "learning_rate": 4.707368982147318e-05,
      "loss": 2.1982,
      "step": 24
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.23016861081123352,
      "learning_rate": 4.572593931387604e-05,
      "loss": 2.2124,
      "step": 27
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 2.072659730911255,
      "eval_runtime": 1.0059,
      "eval_samples_per_second": 68.595,
      "eval_steps_per_second": 8.947,
      "step": 27
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.14867456257343292,
      "learning_rate": 4.415111107797445e-05,
      "loss": 2.1073,
      "step": 30
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.20560601353645325,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 2.1231,
      "step": 33
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.20878741145133972,
      "learning_rate": 4.039153688314145e-05,
      "loss": 2.1412,
      "step": 36
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 2.027235746383667,
      "eval_runtime": 1.0148,
      "eval_samples_per_second": 67.995,
      "eval_steps_per_second": 8.869,
      "step": 36
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2288413688463360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}