Hugging Face's logo

brixeus
/
383a443e-274f-47fc-865b-06cf581189db

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
383a443e-274f-47fc-865b-06cf581189db
File size: 3,097 Bytes 
3950c09
 
 
addfb7b
3950c09
addfb7b
3950c09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1806fff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
addfb7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3950c09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
addfb7b
3950c09
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7105263157894737,
  "eval_steps": 9,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02631578947368421,
      "eval_loss": 1.6184024810791016,
      "eval_runtime": 4.4294,
      "eval_samples_per_second": 14.449,
      "eval_steps_per_second": 1.806,
      "step": 1
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 26.1455020904541,
      "learning_rate": 3e-05,
      "loss": 6.2533,
      "step": 3
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 20.71628761291504,
      "learning_rate": 6e-05,
      "loss": 6.0813,
      "step": 6
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 17.294282913208008,
      "learning_rate": 9e-05,
      "loss": 4.9981,
      "step": 9
    },
    {
      "epoch": 0.23684210526315788,
      "eval_loss": 1.035604476928711,
      "eval_runtime": 4.5385,
      "eval_samples_per_second": 14.102,
      "eval_steps_per_second": 1.763,
      "step": 9
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 11.629775047302246,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.0086,
      "step": 12
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 10.649725914001465,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.8607,
      "step": 15
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 9.19792366027832,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.954,
      "step": 18
    },
    {
      "epoch": 0.47368421052631576,
      "eval_loss": 0.8341699838638306,
      "eval_runtime": 4.56,
      "eval_samples_per_second": 14.035,
      "eval_steps_per_second": 1.754,
      "step": 18
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 8.501199722290039,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.2274,
      "step": 21
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 10.514701843261719,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.3657,
      "step": 24
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 8.145644187927246,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.5328,
      "step": 27
    },
    {
      "epoch": 0.7105263157894737,
      "eval_loss": 0.7960277199745178,
      "eval_runtime": 4.5667,
      "eval_samples_per_second": 14.015,
      "eval_steps_per_second": 1.752,
      "step": 27
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.796903641533645e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}