Hugging Face's logo

dimasik1987
/
ffae54ac-48c3-4966-839c-9ea4accb440c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
ffae54ac-48c3-4966-839c-9ea4accb440c
File size: 2,404 Bytes 
e1d3058
 
 
bc29952
e1d3058
bc29952
e1d3058
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc29952
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e1d3058
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc29952
e1d3058
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0025548494235620987,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012774247117810494,
      "eval_loss": 4.265634536743164,
      "eval_runtime": 367.944,
      "eval_samples_per_second": 8.961,
      "eval_steps_per_second": 4.482,
      "step": 1
    },
    {
      "epoch": 0.00038322741353431485,
      "grad_norm": 8.026169776916504,
      "learning_rate": 6e-05,
      "loss": 14.7151,
      "step": 3
    },
    {
      "epoch": 0.0007664548270686297,
      "grad_norm": 14.828211784362793,
      "learning_rate": 0.00012,
      "loss": 22.9284,
      "step": 6
    },
    {
      "epoch": 0.0010219397694248395,
      "eval_loss": 2.717600107192993,
      "eval_runtime": 369.4354,
      "eval_samples_per_second": 8.924,
      "eval_steps_per_second": 4.464,
      "step": 8
    },
    {
      "epoch": 0.0011496822406029444,
      "grad_norm": 13.35394287109375,
      "learning_rate": 0.00018,
      "loss": 11.4639,
      "step": 9
    },
    {
      "epoch": 0.0015329096541372594,
      "grad_norm": 10.815381050109863,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.6564,
      "step": 12
    },
    {
      "epoch": 0.0019161370676715741,
      "grad_norm": 9.865994453430176,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.6544,
      "step": 15
    },
    {
      "epoch": 0.002043879538849679,
      "eval_loss": 1.126829743385315,
      "eval_runtime": 369.8831,
      "eval_samples_per_second": 8.914,
      "eval_steps_per_second": 4.458,
      "step": 16
    },
    {
      "epoch": 0.002299364481205889,
      "grad_norm": 7.193143367767334,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.3582,
      "step": 18
    }
  ],
  "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": 6534582019031040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}