Hugging Face's logo

kokovova
/
8dc07871-e16a-4b51-9d02-6b8025a4a5c6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
8dc07871-e16a-4b51-9d02-6b8025a4a5c6
File size: 4,204 Bytes 
5782c19
30ef993
 
 
5782c19
30ef993
5782c19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3038d1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30ef993
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5782c19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30ef993
5782c19
 
 
 
30ef993
5782c19
 
 
 
 
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": 0.5702555179595947,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06359300476947535,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021197668256491787,
      "eval_loss": 1.1466405391693115,
      "eval_runtime": 57.3747,
      "eval_samples_per_second": 6.937,
      "eval_steps_per_second": 1.743,
      "step": 1
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.8094033002853394,
      "learning_rate": 0.00012,
      "loss": 4.3741,
      "step": 3
    },
    {
      "epoch": 0.010598834128245893,
      "eval_loss": 1.0699783563613892,
      "eval_runtime": 57.8117,
      "eval_samples_per_second": 6.884,
      "eval_steps_per_second": 1.73,
      "step": 5
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 0.9818021059036255,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.1815,
      "step": 6
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 1.0205563306808472,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.6212,
      "step": 9
    },
    {
      "epoch": 0.021197668256491786,
      "eval_loss": 0.7989693880081177,
      "eval_runtime": 57.6089,
      "eval_samples_per_second": 6.909,
      "eval_steps_per_second": 1.736,
      "step": 10
    },
    {
      "epoch": 0.025437201907790145,
      "grad_norm": 1.0461260080337524,
      "learning_rate": 0.000163742398974869,
      "loss": 2.9535,
      "step": 12
    },
    {
      "epoch": 0.03179650238473768,
      "grad_norm": 0.7129300832748413,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.645,
      "step": 15
    },
    {
      "epoch": 0.03179650238473768,
      "eval_loss": 0.6562170386314392,
      "eval_runtime": 57.0299,
      "eval_samples_per_second": 6.979,
      "eval_steps_per_second": 1.753,
      "step": 15
    },
    {
      "epoch": 0.03815580286168521,
      "grad_norm": 0.5910429954528809,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.3756,
      "step": 18
    },
    {
      "epoch": 0.04239533651298357,
      "eval_loss": 0.5977821946144104,
      "eval_runtime": 57.8021,
      "eval_samples_per_second": 6.886,
      "eval_steps_per_second": 1.73,
      "step": 20
    },
    {
      "epoch": 0.04451510333863275,
      "grad_norm": 0.5103761553764343,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.2397,
      "step": 21
    },
    {
      "epoch": 0.05087440381558029,
      "grad_norm": 0.573857307434082,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.169,
      "step": 24
    },
    {
      "epoch": 0.052994170641229466,
      "eval_loss": 0.5750617384910583,
      "eval_runtime": 57.4007,
      "eval_samples_per_second": 6.934,
      "eval_steps_per_second": 1.742,
      "step": 25
    },
    {
      "epoch": 0.057233704292527825,
      "grad_norm": 0.5762279629707336,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.1634,
      "step": 27
    },
    {
      "epoch": 0.06359300476947535,
      "grad_norm": 0.566165566444397,
      "learning_rate": 0.0,
      "loss": 2.1161,
      "step": 30
    },
    {
      "epoch": 0.06359300476947535,
      "eval_loss": 0.5702555179595947,
      "eval_runtime": 57.4317,
      "eval_samples_per_second": 6.93,
      "eval_steps_per_second": 1.741,
      "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": 3.920787866124288e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}