Hugging Face's logo

filipesantoscv11
/
f8a073c0-d3ed-4c99-8a44-d111d6fc700b

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
f8a073c0-d3ed-4c99-8a44-d111d6fc700b
File size: 3,874 Bytes 
2459d15
 
 
fe04be1
2459d15
fe04be1
2459d15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c913a6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fe04be1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2459d15
 
 
 
 
 
 
 
 
 
 
 
 
 
fe04be1
2459d15
 
 
 
fe04be1
2459d15
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0033685156074556477,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011228385358185493,
      "eval_loss": 11.5,
      "eval_runtime": 24.0004,
      "eval_samples_per_second": 156.247,
      "eval_steps_per_second": 78.124,
      "step": 1
    },
    {
      "epoch": 0.00033685156074556477,
      "grad_norm": 1.953316132130567e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0005614192679092747,
      "eval_loss": 11.5,
      "eval_runtime": 24.2609,
      "eval_samples_per_second": 154.57,
      "eval_steps_per_second": 77.285,
      "step": 5
    },
    {
      "epoch": 0.0006737031214911295,
      "grad_norm": 1.4230739907361567e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0010105546822366943,
      "grad_norm": 1.824189348553773e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0011228385358185494,
      "eval_loss": 11.5,
      "eval_runtime": 24.2682,
      "eval_samples_per_second": 154.523,
      "eval_steps_per_second": 77.262,
      "step": 10
    },
    {
      "epoch": 0.001347406242982259,
      "grad_norm": 1.678512489888817e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0016842578037278239,
      "grad_norm": 1.1590057511057239e-05,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0016842578037278239,
      "eval_loss": 11.5,
      "eval_runtime": 24.371,
      "eval_samples_per_second": 153.871,
      "eval_steps_per_second": 76.936,
      "step": 15
    },
    {
      "epoch": 0.0020211093644733886,
      "grad_norm": 1.3804982700094115e-05,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0022456770716370988,
      "eval_loss": 11.5,
      "eval_runtime": 24.0385,
      "eval_samples_per_second": 156.0,
      "eval_steps_per_second": 78.0,
      "step": 20
    },
    {
      "epoch": 0.0023579609252189536,
      "grad_norm": 1.6708543626009487e-05,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 1.7559348634677008e-05,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.002807096339546373,
      "eval_loss": 11.5,
      "eval_runtime": 24.4035,
      "eval_samples_per_second": 153.667,
      "eval_steps_per_second": 76.833,
      "step": 25
    },
    {
      "epoch": 0.003031664046710083,
      "grad_norm": 2.3784989025443792e-05,
      "learning_rate": 5.449673790581611e-06,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.0033685156074556477,
      "grad_norm": 1.8421775166643783e-05,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.0033685156074556477,
      "eval_loss": 11.5,
      "eval_runtime": 24.2838,
      "eval_samples_per_second": 154.424,
      "eval_steps_per_second": 77.212,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1206856679424.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}