Hugging Face's logo

filipesantoscv11
/
c24d74d7-ab7e-48fd-ba58-8de7130c1c06

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
c24d74d7-ab7e-48fd-ba58-8de7130c1c06
File size: 4,248 Bytes 
3ce35a0
6ba0876
 
 
3ce35a0
6ba0876
3ce35a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6e05570
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0876
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ce35a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0876
3ce35a0
 
 
 
6ba0876
3ce35a0
 
 
 
 
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": 1.7774372100830078,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0007216135278482687,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4053784261608958e-05,
      "eval_loss": 3.604696750640869,
      "eval_runtime": 2235.6462,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 1
    },
    {
      "epoch": 7.216135278482687e-05,
      "grad_norm": 21.76235580444336,
      "learning_rate": 0.00012,
      "loss": 10.3252,
      "step": 3
    },
    {
      "epoch": 0.00012026892130804478,
      "eval_loss": 3.373138666152954,
      "eval_runtime": 2235.6131,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 5
    },
    {
      "epoch": 0.00014432270556965373,
      "grad_norm": 12.278535842895508,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.0076,
      "step": 6
    },
    {
      "epoch": 0.0002164840583544806,
      "grad_norm": 6.428678512573242,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.4451,
      "step": 9
    },
    {
      "epoch": 0.00024053784261608956,
      "eval_loss": 2.6429617404937744,
      "eval_runtime": 2235.5851,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 10
    },
    {
      "epoch": 0.00028864541113930747,
      "grad_norm": 6.507843971252441,
      "learning_rate": 0.000163742398974869,
      "loss": 8.2763,
      "step": 12
    },
    {
      "epoch": 0.0003608067639241344,
      "grad_norm": 16.41105079650879,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.6064,
      "step": 15
    },
    {
      "epoch": 0.0003608067639241344,
      "eval_loss": 2.160693407058716,
      "eval_runtime": 2235.7553,
      "eval_samples_per_second": 15.659,
      "eval_steps_per_second": 3.915,
      "step": 15
    },
    {
      "epoch": 0.0004329681167089612,
      "grad_norm": 5.645549297332764,
      "learning_rate": 9.372094804706867e-05,
      "loss": 7.2956,
      "step": 18
    },
    {
      "epoch": 0.00048107568523217913,
      "eval_loss": 1.9027982950210571,
      "eval_runtime": 2235.6324,
      "eval_samples_per_second": 15.66,
      "eval_steps_per_second": 3.915,
      "step": 20
    },
    {
      "epoch": 0.0005051294694937881,
      "grad_norm": 5.871511459350586,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.5545,
      "step": 21
    },
    {
      "epoch": 0.0005772908222786149,
      "grad_norm": 5.881715774536133,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 6.5465,
      "step": 24
    },
    {
      "epoch": 0.0006013446065402239,
      "eval_loss": 1.795774221420288,
      "eval_runtime": 2235.8074,
      "eval_samples_per_second": 15.659,
      "eval_steps_per_second": 3.915,
      "step": 25
    },
    {
      "epoch": 0.0006494521750634418,
      "grad_norm": 11.0554780960083,
      "learning_rate": 7.022351411174866e-06,
      "loss": 6.722,
      "step": 27
    },
    {
      "epoch": 0.0007216135278482687,
      "grad_norm": 13.766908645629883,
      "learning_rate": 0.0,
      "loss": 6.8375,
      "step": 30
    },
    {
      "epoch": 0.0007216135278482687,
      "eval_loss": 1.7774372100830078,
      "eval_runtime": 2235.4123,
      "eval_samples_per_second": 15.662,
      "eval_steps_per_second": 3.916,
      "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": 1.960393933062144e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}