Hugging Face's logo

lesso08
/
c092a1af-e68e-4e2e-ac19-e0cf603b060c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c092a1af-e68e-4e2e-ac19-e0cf603b060c
File size: 3,185 Bytes 
861a249
 
 
4d8fd8a
861a249
4d8fd8a
861a249
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
162ff94
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0231850
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4d8fd8a
 
 
 
 
 
 
861a249
 
 
 
 
 
 
 
 
 
 
 
 
 
4d8fd8a
861a249
 
 
 
4d8fd8a
861a249
 
 
 
 
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": 0.017152658662092625,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017152658662092624,
      "grad_norm": 10.20623779296875,
      "learning_rate": 2e-05,
      "loss": 10.0968,
      "step": 1
    },
    {
      "epoch": 0.0017152658662092624,
      "eval_loss": 10.568317413330078,
      "eval_runtime": 16.8116,
      "eval_samples_per_second": 14.633,
      "eval_steps_per_second": 7.316,
      "step": 1
    },
    {
      "epoch": 0.003430531732418525,
      "grad_norm": 8.958074569702148,
      "learning_rate": 4e-05,
      "loss": 10.1851,
      "step": 2
    },
    {
      "epoch": 0.005145797598627788,
      "grad_norm": 18.63714599609375,
      "learning_rate": 6e-05,
      "loss": 11.9602,
      "step": 3
    },
    {
      "epoch": 0.005145797598627788,
      "eval_loss": 10.42160701751709,
      "eval_runtime": 16.0368,
      "eval_samples_per_second": 15.34,
      "eval_steps_per_second": 7.67,
      "step": 3
    },
    {
      "epoch": 0.00686106346483705,
      "grad_norm": 15.487518310546875,
      "learning_rate": 8e-05,
      "loss": 10.6799,
      "step": 4
    },
    {
      "epoch": 0.008576329331046312,
      "grad_norm": 12.911466598510742,
      "learning_rate": 0.0001,
      "loss": 9.0754,
      "step": 5
    },
    {
      "epoch": 0.010291595197255575,
      "grad_norm": 14.155526161193848,
      "learning_rate": 0.00012,
      "loss": 8.8563,
      "step": 6
    },
    {
      "epoch": 0.010291595197255575,
      "eval_loss": 7.425621509552002,
      "eval_runtime": 16.0849,
      "eval_samples_per_second": 15.294,
      "eval_steps_per_second": 7.647,
      "step": 6
    },
    {
      "epoch": 0.012006861063464836,
      "grad_norm": 18.84572982788086,
      "learning_rate": 0.00014,
      "loss": 7.9854,
      "step": 7
    },
    {
      "epoch": 0.0137221269296741,
      "grad_norm": 16.23927116394043,
      "learning_rate": 0.00016,
      "loss": 5.275,
      "step": 8
    },
    {
      "epoch": 0.015437392795883362,
      "grad_norm": 21.072099685668945,
      "learning_rate": 0.00018,
      "loss": 4.0998,
      "step": 9
    },
    {
      "epoch": 0.015437392795883362,
      "eval_loss": 3.4490346908569336,
      "eval_runtime": 16.0797,
      "eval_samples_per_second": 15.299,
      "eval_steps_per_second": 7.649,
      "step": 9
    },
    {
      "epoch": 0.017152658662092625,
      "grad_norm": 20.780302047729492,
      "learning_rate": 0.0002,
      "loss": 4.6252,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}