Hugging Face's logo

sn56
/
550672cf-3886-48d6-98d3-eca599a6691e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
550672cf-3886-48d6-98d3-eca599a6691e
File size: 5,722 Bytes 
41681f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
 
{
  "best_metric": 2.7142794132232666,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.014761509364332502,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005904603745733001,
      "grad_norm": 17.38508415222168,
      "learning_rate": 5e-05,
      "loss": 6.2419,
      "step": 1
    },
    {
      "epoch": 0.0005904603745733001,
      "eval_loss": 8.437135696411133,
      "eval_runtime": 0.5006,
      "eval_samples_per_second": 99.887,
      "eval_steps_per_second": 25.971,
      "step": 1
    },
    {
      "epoch": 0.0011809207491466002,
      "grad_norm": 36.33082580566406,
      "learning_rate": 0.0001,
      "loss": 7.2628,
      "step": 2
    },
    {
      "epoch": 0.0017713811237199005,
      "grad_norm": 31.663164138793945,
      "learning_rate": 9.990365154573717e-05,
      "loss": 7.5891,
      "step": 3
    },
    {
      "epoch": 0.0023618414982932005,
      "grad_norm": 11.801265716552734,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.2904,
      "step": 4
    },
    {
      "epoch": 0.0029523018728665005,
      "grad_norm": 48.22990417480469,
      "learning_rate": 9.913533761814537e-05,
      "loss": 6.6358,
      "step": 5
    },
    {
      "epoch": 0.003542762247439801,
      "grad_norm": 17.07508659362793,
      "learning_rate": 9.846666218300807e-05,
      "loss": 6.1791,
      "step": 6
    },
    {
      "epoch": 0.0041332226220131005,
      "grad_norm": 6.440609455108643,
      "learning_rate": 9.761185582727977e-05,
      "loss": 6.1573,
      "step": 7
    },
    {
      "epoch": 0.004723682996586401,
      "grad_norm": 5.693165302276611,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.9697,
      "step": 8
    },
    {
      "epoch": 0.005314143371159701,
      "grad_norm": 4.884424686431885,
      "learning_rate": 9.535927336897098e-05,
      "loss": 5.557,
      "step": 9
    },
    {
      "epoch": 0.005904603745733001,
      "grad_norm": 4.971529483795166,
      "learning_rate": 9.397114317029975e-05,
      "loss": 5.5059,
      "step": 10
    },
    {
      "epoch": 0.006495064120306301,
      "grad_norm": 4.848908424377441,
      "learning_rate": 9.241613255361455e-05,
      "loss": 5.6318,
      "step": 11
    },
    {
      "epoch": 0.007085524494879602,
      "grad_norm": 4.540520191192627,
      "learning_rate": 9.070090031310558e-05,
      "loss": 5.2879,
      "step": 12
    },
    {
      "epoch": 0.0076759848694529014,
      "grad_norm": 5.37409782409668,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.3364,
      "step": 13
    },
    {
      "epoch": 0.008266445244026201,
      "grad_norm": 5.091475486755371,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.3171,
      "step": 14
    },
    {
      "epoch": 0.008856905618599501,
      "grad_norm": 4.849145889282227,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.2864,
      "step": 15
    },
    {
      "epoch": 0.009447365993172802,
      "grad_norm": 5.3735809326171875,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.5548,
      "step": 16
    },
    {
      "epoch": 0.010037826367746102,
      "grad_norm": 5.725705146789551,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.5118,
      "step": 17
    },
    {
      "epoch": 0.010628286742319403,
      "grad_norm": 6.016762733459473,
      "learning_rate": 7.75e-05,
      "loss": 4.0229,
      "step": 18
    },
    {
      "epoch": 0.011218747116892702,
      "grad_norm": 7.6975250244140625,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.2581,
      "step": 19
    },
    {
      "epoch": 0.011809207491466002,
      "grad_norm": 7.248927116394043,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.945,
      "step": 20
    },
    {
      "epoch": 0.012399667866039302,
      "grad_norm": 8.233935356140137,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.5037,
      "step": 21
    },
    {
      "epoch": 0.012990128240612603,
      "grad_norm": 7.0697407722473145,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.6214,
      "step": 22
    },
    {
      "epoch": 0.013580588615185903,
      "grad_norm": 13.036471366882324,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.6104,
      "step": 23
    },
    {
      "epoch": 0.014171048989759204,
      "grad_norm": 10.6988525390625,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.4308,
      "step": 24
    },
    {
      "epoch": 0.014761509364332502,
      "grad_norm": 8.208454132080078,
      "learning_rate": 5.794314081535644e-05,
      "loss": 3.4858,
      "step": 25
    },
    {
      "epoch": 0.014761509364332502,
      "eval_loss": 2.7142794132232666,
      "eval_runtime": 0.4999,
      "eval_samples_per_second": 100.026,
      "eval_steps_per_second": 26.007,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.16708196040704e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}