Hugging Face's logo

nadejdatarabukina
/
3451c9c6-8bd9-440a-a458-013a07eafb5c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
3451c9c6-8bd9-440a-a458-013a07eafb5c
File size: 2,825 Bytes 
9bda509
 
 
0adcc62
9bda509
0adcc62
9bda509
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0adcc62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9bda509
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0adcc62
9bda509
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015479876160990712,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007739938080495357,
      "eval_loss": 1.6945956945419312,
      "eval_runtime": 110.0753,
      "eval_samples_per_second": 4.951,
      "eval_steps_per_second": 2.48,
      "step": 1
    },
    {
      "epoch": 0.0023219814241486067,
      "grad_norm": 4.82108736038208,
      "learning_rate": 6e-05,
      "loss": 6.8237,
      "step": 3
    },
    {
      "epoch": 0.003869969040247678,
      "eval_loss": 1.6913092136383057,
      "eval_runtime": 111.3468,
      "eval_samples_per_second": 4.895,
      "eval_steps_per_second": 2.452,
      "step": 5
    },
    {
      "epoch": 0.0046439628482972135,
      "grad_norm": 1.9441202878952026,
      "learning_rate": 0.00012,
      "loss": 6.141,
      "step": 6
    },
    {
      "epoch": 0.00696594427244582,
      "grad_norm": 1.3660614490509033,
      "learning_rate": 0.00018,
      "loss": 5.5771,
      "step": 9
    },
    {
      "epoch": 0.007739938080495356,
      "eval_loss": 1.6541721820831299,
      "eval_runtime": 111.3024,
      "eval_samples_per_second": 4.897,
      "eval_steps_per_second": 2.453,
      "step": 10
    },
    {
      "epoch": 0.009287925696594427,
      "grad_norm": 3.83369779586792,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.9687,
      "step": 12
    },
    {
      "epoch": 0.011609907120743035,
      "grad_norm": 1.0999690294265747,
      "learning_rate": 0.00017071067811865476,
      "loss": 7.028,
      "step": 15
    },
    {
      "epoch": 0.011609907120743035,
      "eval_loss": 1.5518581867218018,
      "eval_runtime": 111.3292,
      "eval_samples_per_second": 4.895,
      "eval_steps_per_second": 2.452,
      "step": 15
    },
    {
      "epoch": 0.01393188854489164,
      "grad_norm": 1.7612863779067993,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.8503,
      "step": 18
    },
    {
      "epoch": 0.015479876160990712,
      "eval_loss": 1.4609495401382446,
      "eval_runtime": 111.3426,
      "eval_samples_per_second": 4.895,
      "eval_steps_per_second": 2.452,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8576723457146880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}