Hugging Face's logo

ClarenceDan
/
ad2a06b4-ddab-457d-86f4-a14c00550b5a

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
ad2a06b4-ddab-457d-86f4-a14c00550b5a
File size: 2,982 Bytes 
1a59a56
 
 
6456579
1a59a56
6456579
1a59a56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aa03a7a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd5cb14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6456579
 
 
 
 
 
 
1a59a56
 
 
 
 
 
 
 
 
 
 
 
 
 
6456579
1a59a56
 
 
 
6456579
1a59a56
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00021398956800855958,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139895680085596e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 2.139895680085596e-05,
      "eval_loss": NaN,
      "eval_runtime": 1064.2703,
      "eval_samples_per_second": 18.489,
      "eval_steps_per_second": 9.245,
      "step": 1
    },
    {
      "epoch": 4.279791360171192e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 6.419687040256787e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 6.419687040256787e-05,
      "eval_loss": NaN,
      "eval_runtime": 1062.7447,
      "eval_samples_per_second": 18.515,
      "eval_steps_per_second": 9.258,
      "step": 3
    },
    {
      "epoch": 8.559582720342384e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00010699478400427979,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00012839374080513574,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00012839374080513574,
      "eval_loss": NaN,
      "eval_runtime": 1127.196,
      "eval_samples_per_second": 17.457,
      "eval_steps_per_second": 8.729,
      "step": 6
    },
    {
      "epoch": 0.0001497926976059917,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00017119165440684768,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00019259061120770361,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00019259061120770361,
      "eval_loss": NaN,
      "eval_runtime": 1061.7706,
      "eval_samples_per_second": 18.532,
      "eval_steps_per_second": 9.267,
      "step": 9
    },
    {
      "epoch": 0.00021398956800855958,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3238750071029760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}