Hugging Face's logo

nadejdatarabukina
/
c25ab343-2ada-4208-9bc4-5b086e29fc46

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c25ab343-2ada-4208-9bc4-5b086e29fc46
File size: 3,038 Bytes 
277d9a2
 
 
a9dccbe
277d9a2
a9dccbe
277d9a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b80b0b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a9dccbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
277d9a2
 
 
 
 
 
 
 
 
 
 
 
 
 
a9dccbe
277d9a2
 
 
 
a9dccbe
277d9a2
 
 
 
 
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": 0.13186813186813187,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004395604395604396,
      "eval_loss": NaN,
      "eval_runtime": 8.1385,
      "eval_samples_per_second": 11.796,
      "eval_steps_per_second": 5.898,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.035164835164835165,
      "eval_loss": NaN,
      "eval_runtime": 7.6519,
      "eval_samples_per_second": 12.546,
      "eval_steps_per_second": 6.273,
      "step": 8
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.07032967032967033,
      "eval_loss": NaN,
      "eval_runtime": 7.7067,
      "eval_samples_per_second": 12.457,
      "eval_steps_per_second": 6.228,
      "step": 16
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1054945054945055,
      "eval_loss": NaN,
      "eval_runtime": 7.7308,
      "eval_samples_per_second": 12.418,
      "eval_steps_per_second": 6.209,
      "step": 24
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.13186813186813187,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}