Hugging Face's logo

fedovtt
/
3f82edc5-9c41-420c-a757-9aeafdec662b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3f82edc5-9c41-420c-a757-9aeafdec662b
File size: 3,077 Bytes 
30e7528
 
 
418f39e
30e7528
418f39e
30e7528
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d627c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
418f39e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30e7528
 
 
 
 
 
 
 
 
 
 
 
 
 
418f39e
30e7528
 
 
 
418f39e
30e7528
 
 
 
 
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": 0.0011315844067668747,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.771948022556249e-05,
      "eval_loss": NaN,
      "eval_runtime": 969.1518,
      "eval_samples_per_second": 11.518,
      "eval_steps_per_second": 5.76,
      "step": 1
    },
    {
      "epoch": 0.00011315844067668747,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00022631688135337495,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0003017558418044999,
      "eval_loss": NaN,
      "eval_runtime": 968.0156,
      "eval_samples_per_second": 11.532,
      "eval_steps_per_second": 5.766,
      "step": 8
    },
    {
      "epoch": 0.00033947532203006245,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0004526337627067499,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0005657922033834373,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0006035116836089999,
      "eval_loss": NaN,
      "eval_runtime": 968.5076,
      "eval_samples_per_second": 11.526,
      "eval_steps_per_second": 5.764,
      "step": 16
    },
    {
      "epoch": 0.0006789506440601249,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0007921090847368123,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0009052675254134998,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0009052675254134998,
      "eval_loss": NaN,
      "eval_runtime": 968.7702,
      "eval_samples_per_second": 11.523,
      "eval_steps_per_second": 5.762,
      "step": 24
    },
    {
      "epoch": 0.0010184259660901873,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0011315844067668747,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1.0945431626317824e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}