Hugging Face's logo

duyphu
/
8a221955-e48e-4037-bfba-4a9585b4bf4f

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
8a221955-e48e-4037-bfba-4a9585b4bf4f
File size: 3,694 Bytes 
9223d98
 
 
e77fcec
1b85b2e
e77fcec
9223d98
 
 
 
 
 
 
1b85b2e
 
 
9223d98
1b85b2e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9e7ceb2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
232c8b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e77fcec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9223d98
 
 
1b85b2e
9223d98
 
1b85b2e
9223d98
 
 
 
 
 
 
e77fcec
9223d98
 
 
 
e77fcec
9223d98
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13183915622940012,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026367831245880024,
      "eval_loss": 9.952766418457031,
      "eval_runtime": 19.7234,
      "eval_samples_per_second": 8.112,
      "eval_steps_per_second": 4.056,
      "step": 1
    },
    {
      "epoch": 0.013183915622940013,
      "grad_norm": 7.932442665100098,
      "learning_rate": 5e-05,
      "loss": 9.1812,
      "step": 5
    },
    {
      "epoch": 0.026367831245880026,
      "grad_norm": 8.679454803466797,
      "learning_rate": 0.0001,
      "loss": 8.8656,
      "step": 10
    },
    {
      "epoch": 0.026367831245880026,
      "eval_loss": 7.980339050292969,
      "eval_runtime": 19.8797,
      "eval_samples_per_second": 8.048,
      "eval_steps_per_second": 4.024,
      "step": 10
    },
    {
      "epoch": 0.03955174686882004,
      "grad_norm": 11.740812301635742,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.7582,
      "step": 15
    },
    {
      "epoch": 0.05273566249176005,
      "grad_norm": 12.778048515319824,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9227,
      "step": 20
    },
    {
      "epoch": 0.05273566249176005,
      "eval_loss": 0.8312085866928101,
      "eval_runtime": 19.9694,
      "eval_samples_per_second": 8.012,
      "eval_steps_per_second": 4.006,
      "step": 20
    },
    {
      "epoch": 0.06591957811470006,
      "grad_norm": 3.4786934852600098,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4806,
      "step": 25
    },
    {
      "epoch": 0.07910349373764008,
      "grad_norm": 19.870271682739258,
      "learning_rate": 5e-05,
      "loss": 0.3225,
      "step": 30
    },
    {
      "epoch": 0.07910349373764008,
      "eval_loss": 0.1717974841594696,
      "eval_runtime": 20.0121,
      "eval_samples_per_second": 7.995,
      "eval_steps_per_second": 3.998,
      "step": 30
    },
    {
      "epoch": 0.0922874093605801,
      "grad_norm": 4.610195636749268,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1221,
      "step": 35
    },
    {
      "epoch": 0.1054713249835201,
      "grad_norm": 8.429944038391113,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1087,
      "step": 40
    },
    {
      "epoch": 0.1054713249835201,
      "eval_loss": 0.09574756771326065,
      "eval_runtime": 20.1599,
      "eval_samples_per_second": 7.937,
      "eval_steps_per_second": 3.968,
      "step": 40
    },
    {
      "epoch": 0.11865524060646011,
      "grad_norm": 20.386011123657227,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1,
      "step": 45
    },
    {
      "epoch": 0.13183915622940012,
      "grad_norm": 8.91682243347168,
      "learning_rate": 0.0,
      "loss": 0.2509,
      "step": 50
    },
    {
      "epoch": 0.13183915622940012,
      "eval_loss": 0.0755360797047615,
      "eval_runtime": 19.9856,
      "eval_samples_per_second": 8.006,
      "eval_steps_per_second": 4.003,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.61937503551488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}