Hugging Face's logo

fedovtt
/
06567845-c2e3-4c73-9437-c40f29b94112

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
06567845-c2e3-4c73-9437-c40f29b94112
File size: 4,159 Bytes 
ab19cab
b0fb67b
 
 
ab19cab
b0fb67b
ab19cab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a80d26e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b0fb67b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab19cab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b0fb67b
ab19cab
 
 
 
b0fb67b
ab19cab
 
 
 
 
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": 3.3020966053009033,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.17543859649122806,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005847953216374269,
      "eval_loss": 4.815151214599609,
      "eval_runtime": 3.7796,
      "eval_samples_per_second": 19.049,
      "eval_steps_per_second": 9.525,
      "step": 1
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 4.078864097595215,
      "learning_rate": 6e-05,
      "loss": 4.7019,
      "step": 3
    },
    {
      "epoch": 0.029239766081871343,
      "eval_loss": 4.256248474121094,
      "eval_runtime": 3.7876,
      "eval_samples_per_second": 19.009,
      "eval_steps_per_second": 9.505,
      "step": 5
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 3.195171356201172,
      "learning_rate": 0.00012,
      "loss": 4.3382,
      "step": 6
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 3.5134713649749756,
      "learning_rate": 0.00018,
      "loss": 3.9086,
      "step": 9
    },
    {
      "epoch": 0.05847953216374269,
      "eval_loss": 3.64383864402771,
      "eval_runtime": 3.7859,
      "eval_samples_per_second": 19.018,
      "eval_steps_per_second": 9.509,
      "step": 10
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 3.6851561069488525,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.5827,
      "step": 12
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 2.6502652168273926,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.328,
      "step": 15
    },
    {
      "epoch": 0.08771929824561403,
      "eval_loss": 3.435582160949707,
      "eval_runtime": 3.7881,
      "eval_samples_per_second": 19.007,
      "eval_steps_per_second": 9.503,
      "step": 15
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.3518097400665283,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.348,
      "step": 18
    },
    {
      "epoch": 0.11695906432748537,
      "eval_loss": 3.360213041305542,
      "eval_runtime": 3.7903,
      "eval_samples_per_second": 18.996,
      "eval_steps_per_second": 9.498,
      "step": 20
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 2.3523964881896973,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.2867,
      "step": 21
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 2.754035472869873,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.2694,
      "step": 24
    },
    {
      "epoch": 0.14619883040935672,
      "eval_loss": 3.3148889541625977,
      "eval_runtime": 3.7993,
      "eval_samples_per_second": 18.951,
      "eval_steps_per_second": 9.475,
      "step": 25
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 2.3271331787109375,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.1204,
      "step": 27
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.160839557647705,
      "learning_rate": 0.0,
      "loss": 3.0623,
      "step": 30
    },
    {
      "epoch": 0.17543859649122806,
      "eval_loss": 3.3020966053009033,
      "eval_runtime": 3.7873,
      "eval_samples_per_second": 19.011,
      "eval_steps_per_second": 9.506,
      "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": 3015894871572480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}