Hugging Face's logo

kokovova
/
8e62130b-f5b6-4122-aa8d-9a14a3ee76c7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
8e62130b-f5b6-4122-aa8d-9a14a3ee76c7
File size: 4,207 Bytes 
47601e0
e4c28a6
 
 
47601e0
e4c28a6
47601e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e5685e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e4c28a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47601e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e4c28a6
47601e0
 
 
 
e4c28a6
47601e0
 
 
 
 
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
 
{
  "best_metric": 1.9812061786651611,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.042811273635390654,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014270424545130217,
      "eval_loss": 2.0832698345184326,
      "eval_runtime": 65.5341,
      "eval_samples_per_second": 9.003,
      "eval_steps_per_second": 2.258,
      "step": 1
    },
    {
      "epoch": 0.004281127363539065,
      "grad_norm": 0.7657609581947327,
      "learning_rate": 0.00012,
      "loss": 8.1135,
      "step": 3
    },
    {
      "epoch": 0.007135212272565109,
      "eval_loss": 2.0654828548431396,
      "eval_runtime": 65.9922,
      "eval_samples_per_second": 8.94,
      "eval_steps_per_second": 2.243,
      "step": 5
    },
    {
      "epoch": 0.00856225472707813,
      "grad_norm": 0.6937746405601501,
      "learning_rate": 0.0001992114701314478,
      "loss": 7.9043,
      "step": 6
    },
    {
      "epoch": 0.012843382090617196,
      "grad_norm": 0.9151648283004761,
      "learning_rate": 0.00018763066800438636,
      "loss": 8.0914,
      "step": 9
    },
    {
      "epoch": 0.014270424545130217,
      "eval_loss": 2.0186924934387207,
      "eval_runtime": 65.97,
      "eval_samples_per_second": 8.943,
      "eval_steps_per_second": 2.243,
      "step": 10
    },
    {
      "epoch": 0.01712450945415626,
      "grad_norm": 0.6517742276191711,
      "learning_rate": 0.000163742398974869,
      "loss": 8.3796,
      "step": 12
    },
    {
      "epoch": 0.021405636817695327,
      "grad_norm": 0.6615819931030273,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.1922,
      "step": 15
    },
    {
      "epoch": 0.021405636817695327,
      "eval_loss": 1.9932925701141357,
      "eval_runtime": 66.361,
      "eval_samples_per_second": 8.891,
      "eval_steps_per_second": 2.23,
      "step": 15
    },
    {
      "epoch": 0.025686764181234393,
      "grad_norm": 0.4475820064544678,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.1842,
      "step": 18
    },
    {
      "epoch": 0.028540849090260435,
      "eval_loss": 1.9884905815124512,
      "eval_runtime": 66.3425,
      "eval_samples_per_second": 8.893,
      "eval_steps_per_second": 2.231,
      "step": 20
    },
    {
      "epoch": 0.029967891544773455,
      "grad_norm": 1.08573579788208,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 8.3976,
      "step": 21
    },
    {
      "epoch": 0.03424901890831252,
      "grad_norm": 0.5004927515983582,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.3142,
      "step": 24
    },
    {
      "epoch": 0.03567606136282554,
      "eval_loss": 1.98249351978302,
      "eval_runtime": 66.0005,
      "eval_samples_per_second": 8.939,
      "eval_steps_per_second": 2.242,
      "step": 25
    },
    {
      "epoch": 0.038530146271851584,
      "grad_norm": 0.6029341816902161,
      "learning_rate": 7.022351411174866e-06,
      "loss": 8.2691,
      "step": 27
    },
    {
      "epoch": 0.042811273635390654,
      "grad_norm": 0.584296464920044,
      "learning_rate": 0.0,
      "loss": 7.9651,
      "step": 30
    },
    {
      "epoch": 0.042811273635390654,
      "eval_loss": 1.9812061786651611,
      "eval_runtime": 66.0349,
      "eval_samples_per_second": 8.935,
      "eval_steps_per_second": 2.241,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5450456956207104e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}