Hugging Face's logo

vmpsergio
/
b0ea689f-b196-4024-ab48-7003307122cf

PEFT
Safetensors
bloom
axolotl
Generated from Trainer
Model card Files Community
b0ea689f-b196-4024-ab48-7003307122cf
File size: 4,221 Bytes 
770be71
a83b9f3
 
 
770be71
a83b9f3
770be71
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fe5ed63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a83b9f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
770be71
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a83b9f3
770be71
 
 
 
a83b9f3
770be71
 
 
 
 
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": 3.839513063430786,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0005850775959161584,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9502586530538612e-05,
      "eval_loss": 4.488034725189209,
      "eval_runtime": 736.639,
      "eval_samples_per_second": 29.309,
      "eval_steps_per_second": 14.654,
      "step": 1
    },
    {
      "epoch": 5.850775959161584e-05,
      "grad_norm": 11.912729263305664,
      "learning_rate": 6e-05,
      "loss": 19.6102,
      "step": 3
    },
    {
      "epoch": 9.751293265269307e-05,
      "eval_loss": 4.3603668212890625,
      "eval_runtime": 740.5036,
      "eval_samples_per_second": 29.156,
      "eval_steps_per_second": 14.578,
      "step": 5
    },
    {
      "epoch": 0.00011701551918323167,
      "grad_norm": 8.767396926879883,
      "learning_rate": 0.00012,
      "loss": 16.5732,
      "step": 6
    },
    {
      "epoch": 0.00017552327877484752,
      "grad_norm": 8.869946479797363,
      "learning_rate": 0.00018,
      "loss": 17.0351,
      "step": 9
    },
    {
      "epoch": 0.00019502586530538614,
      "eval_loss": 4.058638095855713,
      "eval_runtime": 736.3032,
      "eval_samples_per_second": 29.322,
      "eval_steps_per_second": 14.661,
      "step": 10
    },
    {
      "epoch": 0.00023403103836646335,
      "grad_norm": 9.496614456176758,
      "learning_rate": 0.00019510565162951537,
      "loss": 16.2777,
      "step": 12
    },
    {
      "epoch": 0.0002925387979580792,
      "grad_norm": 9.867759704589844,
      "learning_rate": 0.00017071067811865476,
      "loss": 15.7824,
      "step": 15
    },
    {
      "epoch": 0.0002925387979580792,
      "eval_loss": 3.9371206760406494,
      "eval_runtime": 734.2275,
      "eval_samples_per_second": 29.405,
      "eval_steps_per_second": 14.703,
      "step": 15
    },
    {
      "epoch": 0.00035104655754969504,
      "grad_norm": 9.290112495422363,
      "learning_rate": 0.00013090169943749476,
      "loss": 15.3766,
      "step": 18
    },
    {
      "epoch": 0.0003900517306107723,
      "eval_loss": 3.88244366645813,
      "eval_runtime": 735.9882,
      "eval_samples_per_second": 29.335,
      "eval_steps_per_second": 14.667,
      "step": 20
    },
    {
      "epoch": 0.00040955431714131084,
      "grad_norm": 22.563886642456055,
      "learning_rate": 8.435655349597689e-05,
      "loss": 15.521,
      "step": 21
    },
    {
      "epoch": 0.0004680620767329267,
      "grad_norm": 8.729718208312988,
      "learning_rate": 4.12214747707527e-05,
      "loss": 15.695,
      "step": 24
    },
    {
      "epoch": 0.0004875646632634653,
      "eval_loss": 3.8451759815216064,
      "eval_runtime": 737.0999,
      "eval_samples_per_second": 29.29,
      "eval_steps_per_second": 14.645,
      "step": 25
    },
    {
      "epoch": 0.0005265698363245426,
      "grad_norm": 10.4032564163208,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 15.0216,
      "step": 27
    },
    {
      "epoch": 0.0005850775959161584,
      "grad_norm": 8.15900993347168,
      "learning_rate": 0.0,
      "loss": 15.2282,
      "step": 30
    },
    {
      "epoch": 0.0005850775959161584,
      "eval_loss": 3.839513063430786,
      "eval_runtime": 735.1733,
      "eval_samples_per_second": 29.367,
      "eval_steps_per_second": 14.684,
      "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": 455056482631680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}