Hugging Face's logo

vermoney
/
2f613ac1-a624-4cbf-9e15-bde4ab51585b

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
2f613ac1-a624-4cbf-9e15-bde4ab51585b
File size: 4,247 Bytes 
f2da1e2
1cbfdfc
 
 
f2da1e2
1cbfdfc
f2da1e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1509df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1cbfdfc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f2da1e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1cbfdfc
f2da1e2
 
 
 
1cbfdfc
f2da1e2
 
 
 
 
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": 11.933874130249023,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.008884282224031984,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002961427408010661,
      "eval_loss": 11.934436798095703,
      "eval_runtime": 15.9653,
      "eval_samples_per_second": 89.068,
      "eval_steps_per_second": 44.534,
      "step": 1
    },
    {
      "epoch": 0.0008884282224031983,
      "grad_norm": 0.046831801533699036,
      "learning_rate": 6e-05,
      "loss": 11.936,
      "step": 3
    },
    {
      "epoch": 0.0014807137040053306,
      "eval_loss": 11.934361457824707,
      "eval_runtime": 15.9493,
      "eval_samples_per_second": 89.157,
      "eval_steps_per_second": 44.579,
      "step": 5
    },
    {
      "epoch": 0.0017768564448063966,
      "grad_norm": 0.03125142306089401,
      "learning_rate": 9.96057350657239e-05,
      "loss": 11.9342,
      "step": 6
    },
    {
      "epoch": 0.002665284667209595,
      "grad_norm": 0.0406610444188118,
      "learning_rate": 9.381533400219318e-05,
      "loss": 11.9332,
      "step": 9
    },
    {
      "epoch": 0.0029614274080106613,
      "eval_loss": 11.934170722961426,
      "eval_runtime": 15.9818,
      "eval_samples_per_second": 88.976,
      "eval_steps_per_second": 44.488,
      "step": 10
    },
    {
      "epoch": 0.0035537128896127933,
      "grad_norm": 0.05989011749625206,
      "learning_rate": 8.18711994874345e-05,
      "loss": 11.932,
      "step": 12
    },
    {
      "epoch": 0.004442141112015992,
      "grad_norm": 0.037861209362745285,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9359,
      "step": 15
    },
    {
      "epoch": 0.004442141112015992,
      "eval_loss": 11.934015274047852,
      "eval_runtime": 16.0398,
      "eval_samples_per_second": 88.654,
      "eval_steps_per_second": 44.327,
      "step": 15
    },
    {
      "epoch": 0.00533056933441919,
      "grad_norm": 0.033359162509441376,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 11.9323,
      "step": 18
    },
    {
      "epoch": 0.0059228548160213225,
      "eval_loss": 11.933917999267578,
      "eval_runtime": 15.97,
      "eval_samples_per_second": 89.042,
      "eval_steps_per_second": 44.521,
      "step": 20
    },
    {
      "epoch": 0.006218997556822388,
      "grad_norm": 0.04174540936946869,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 11.9346,
      "step": 21
    },
    {
      "epoch": 0.0071074257792255865,
      "grad_norm": 0.05081101134419441,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 11.9317,
      "step": 24
    },
    {
      "epoch": 0.007403568520026653,
      "eval_loss": 11.933879852294922,
      "eval_runtime": 16.0535,
      "eval_samples_per_second": 88.579,
      "eval_steps_per_second": 44.289,
      "step": 25
    },
    {
      "epoch": 0.007995854001628786,
      "grad_norm": 0.02904302440583706,
      "learning_rate": 3.511175705587433e-06,
      "loss": 11.9339,
      "step": 27
    },
    {
      "epoch": 0.008884282224031984,
      "grad_norm": 0.044318776577711105,
      "learning_rate": 0.0,
      "loss": 11.9343,
      "step": 30
    },
    {
      "epoch": 0.008884282224031984,
      "eval_loss": 11.933874130249023,
      "eval_runtime": 16.0782,
      "eval_samples_per_second": 88.443,
      "eval_steps_per_second": 44.221,
      "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": 11242045440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}