Hugging Face's logo

fedovtt
/
fbaf892b-f6c9-425f-a67f-e99b607aedfe

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
fbaf892b-f6c9-425f-a67f-e99b607aedfe
File size: 3,297 Bytes 
736a8c0
 
 
feb07fa
736a8c0
feb07fa
736a8c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a8d8b95
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
feb07fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
736a8c0
 
 
 
 
 
 
 
 
 
 
 
 
 
feb07fa
736a8c0
 
 
 
feb07fa
736a8c0
 
 
 
 
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": 0.005567928730512249,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001855976243504083,
      "eval_loss": 1.2906131744384766,
      "eval_runtime": 234.3041,
      "eval_samples_per_second": 9.684,
      "eval_steps_per_second": 4.844,
      "step": 1
    },
    {
      "epoch": 0.0005567928730512249,
      "grad_norm": 1.4204806089401245,
      "learning_rate": 6e-05,
      "loss": 3.8724,
      "step": 3
    },
    {
      "epoch": 0.0011135857461024498,
      "grad_norm": 2.304058313369751,
      "learning_rate": 0.00012,
      "loss": 4.5803,
      "step": 6
    },
    {
      "epoch": 0.0014847809948032665,
      "eval_loss": 1.2551518678665161,
      "eval_runtime": 235.9886,
      "eval_samples_per_second": 9.615,
      "eval_steps_per_second": 4.81,
      "step": 8
    },
    {
      "epoch": 0.0016703786191536749,
      "grad_norm": 5.708734512329102,
      "learning_rate": 0.00018,
      "loss": 5.9305,
      "step": 9
    },
    {
      "epoch": 0.0022271714922048997,
      "grad_norm": 3.761167287826538,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.884,
      "step": 12
    },
    {
      "epoch": 0.0027839643652561247,
      "grad_norm": 3.1222829818725586,
      "learning_rate": 0.00017071067811865476,
      "loss": 5.1134,
      "step": 15
    },
    {
      "epoch": 0.002969561989606533,
      "eval_loss": 1.2209032773971558,
      "eval_runtime": 236.0548,
      "eval_samples_per_second": 9.612,
      "eval_steps_per_second": 4.808,
      "step": 16
    },
    {
      "epoch": 0.0033407572383073497,
      "grad_norm": 3.7993876934051514,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.0935,
      "step": 18
    },
    {
      "epoch": 0.0038975501113585748,
      "grad_norm": 4.368784427642822,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.6337,
      "step": 21
    },
    {
      "epoch": 0.004454342984409799,
      "grad_norm": 3.697722911834717,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.247,
      "step": 24
    },
    {
      "epoch": 0.004454342984409799,
      "eval_loss": 1.2021467685699463,
      "eval_runtime": 235.9349,
      "eval_samples_per_second": 9.617,
      "eval_steps_per_second": 4.811,
      "step": 24
    },
    {
      "epoch": 0.005011135857461025,
      "grad_norm": 1.3606876134872437,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 5.4003,
      "step": 27
    },
    {
      "epoch": 0.005567928730512249,
      "grad_norm": 1.3388198614120483,
      "learning_rate": 0.0,
      "loss": 3.6189,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4621127267581952e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}