Hugging Face's logo

leixa
/
10a3e06d-5f7f-4f40-bae4-9b76eb4d292a

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
10a3e06d-5f7f-4f40-bae4-9b76eb4d292a
File size: 4,013 Bytes 
515714d
 
 
7dfb5f0
515714d
7dfb5f0
515714d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a1fa56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65fed76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e6a1bae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71e1115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79eb70b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7dfb5f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
515714d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7dfb5f0
515714d
 
 
 
 
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
170
171
172
173
174
175
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012264564169951819,
  "eval_steps": 5,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003504161191414805,
      "eval_loss": NaN,
      "eval_runtime": 518.3461,
      "eval_samples_per_second": 9.272,
      "eval_steps_per_second": 1.159,
      "step": 1
    },
    {
      "epoch": 0.0010512483574244415,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0017520805957074025,
      "eval_loss": NaN,
      "eval_runtime": 518.7288,
      "eval_samples_per_second": 9.265,
      "eval_steps_per_second": 1.159,
      "step": 5
    },
    {
      "epoch": 0.002102496714848883,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0031537450722733244,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.003504161191414805,
      "eval_loss": NaN,
      "eval_runtime": 518.5802,
      "eval_samples_per_second": 9.268,
      "eval_steps_per_second": 1.159,
      "step": 10
    },
    {
      "epoch": 0.004204993429697766,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.005256241787122208,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.005256241787122208,
      "eval_loss": NaN,
      "eval_runtime": 518.8609,
      "eval_samples_per_second": 9.263,
      "eval_steps_per_second": 1.158,
      "step": 15
    },
    {
      "epoch": 0.006307490144546649,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00700832238282961,
      "eval_loss": NaN,
      "eval_runtime": 518.8327,
      "eval_samples_per_second": 9.263,
      "eval_steps_per_second": 1.158,
      "step": 20
    },
    {
      "epoch": 0.007358738501971091,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.008409986859395532,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.008760402978537012,
      "eval_loss": NaN,
      "eval_runtime": 518.7316,
      "eval_samples_per_second": 9.265,
      "eval_steps_per_second": 1.159,
      "step": 25
    },
    {
      "epoch": 0.009461235216819974,
      "grad_norm": NaN,
      "learning_rate": 6.167226819279528e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.010512483574244415,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.010512483574244415,
      "eval_loss": NaN,
      "eval_runtime": 518.7787,
      "eval_samples_per_second": 9.264,
      "eval_steps_per_second": 1.158,
      "step": 30
    },
    {
      "epoch": 0.011563731931668857,
      "grad_norm": NaN,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.012264564169951819,
      "eval_loss": NaN,
      "eval_runtime": 518.5102,
      "eval_samples_per_second": 9.269,
      "eval_steps_per_second": 1.159,
      "step": 35
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.298089845837005e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}