Hugging Face's logo

leixa
/
ed3932c6-6698-4450-acf3-2c70d0024ae6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ed3932c6-6698-4450-acf3-2c70d0024ae6
File size: 3,982 Bytes 
f3e11ec
 
 
150108d
f3e11ec
150108d
f3e11ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be4ac70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
444defa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
06d2c51
 
 
 
 
 
 
 
 
 
 
 
 
 
 
924a1cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff89c02
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150108d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f3e11ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150108d
f3e11ec
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2229299363057325,
  "eval_steps": 5,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006369426751592357,
      "eval_loss": NaN,
      "eval_runtime": 23.2416,
      "eval_samples_per_second": 11.402,
      "eval_steps_per_second": 1.463,
      "step": 1
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.03184713375796178,
      "eval_loss": NaN,
      "eval_runtime": 22.968,
      "eval_samples_per_second": 11.538,
      "eval_steps_per_second": 1.48,
      "step": 5
    },
    {
      "epoch": 0.03821656050955414,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.05732484076433121,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.06369426751592357,
      "eval_loss": NaN,
      "eval_runtime": 23.0759,
      "eval_samples_per_second": 11.484,
      "eval_steps_per_second": 1.473,
      "step": 10
    },
    {
      "epoch": 0.07643312101910828,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.09554140127388536,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.09554140127388536,
      "eval_loss": NaN,
      "eval_runtime": 23.1097,
      "eval_samples_per_second": 11.467,
      "eval_steps_per_second": 1.471,
      "step": 15
    },
    {
      "epoch": 0.11464968152866242,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.12738853503184713,
      "eval_loss": NaN,
      "eval_runtime": 23.1132,
      "eval_samples_per_second": 11.465,
      "eval_steps_per_second": 1.471,
      "step": 20
    },
    {
      "epoch": 0.1337579617834395,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.15286624203821655,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1592356687898089,
      "eval_loss": NaN,
      "eval_runtime": 23.1113,
      "eval_samples_per_second": 11.466,
      "eval_steps_per_second": 1.471,
      "step": 25
    },
    {
      "epoch": 0.17197452229299362,
      "grad_norm": NaN,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1910828025477707,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.1910828025477707,
      "eval_loss": NaN,
      "eval_runtime": 23.1079,
      "eval_samples_per_second": 11.468,
      "eval_steps_per_second": 1.471,
      "step": 30
    },
    {
      "epoch": 0.21019108280254778,
      "grad_norm": NaN,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.2229299363057325,
      "eval_loss": NaN,
      "eval_runtime": 23.1162,
      "eval_samples_per_second": 11.464,
      "eval_steps_per_second": 1.471,
      "step": 35
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.87142782779392e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}