Hugging Face's logo

VERSIL91
/
37562dc6-d1ef-4d3a-b67f-e5fff6562d50

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
37562dc6-d1ef-4d3a-b67f-e5fff6562d50
File size: 2,333 Bytes 
7392693
 
 
ddca97b
7392693
ddca97b
7392693
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ddca97b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7392693
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ddca97b
7392693
 
 
 
 
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": 0.07174887892376682,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01195814648729447,
      "grad_norm": 14.490328788757324,
      "learning_rate": 1e-05,
      "loss": 35.7522,
      "step": 1
    },
    {
      "epoch": 0.01195814648729447,
      "eval_loss": 2.004462242126465,
      "eval_runtime": 28.4736,
      "eval_samples_per_second": 4.952,
      "eval_steps_per_second": 2.494,
      "step": 1
    },
    {
      "epoch": 0.02391629297458894,
      "grad_norm": 11.366060256958008,
      "learning_rate": 2e-05,
      "loss": 30.9888,
      "step": 2
    },
    {
      "epoch": 0.03587443946188341,
      "grad_norm": 11.150002479553223,
      "learning_rate": 3e-05,
      "loss": 26.9533,
      "step": 3
    },
    {
      "epoch": 0.03587443946188341,
      "eval_loss": 1.9517086744308472,
      "eval_runtime": 6.5209,
      "eval_samples_per_second": 21.623,
      "eval_steps_per_second": 10.888,
      "step": 3
    },
    {
      "epoch": 0.04783258594917788,
      "grad_norm": 12.718278884887695,
      "learning_rate": 4e-05,
      "loss": 33.9918,
      "step": 4
    },
    {
      "epoch": 0.059790732436472344,
      "grad_norm": 12.853529930114746,
      "learning_rate": 5e-05,
      "loss": 32.5199,
      "step": 5
    },
    {
      "epoch": 0.07174887892376682,
      "grad_norm": 13.096259117126465,
      "learning_rate": 6e-05,
      "loss": 32.7244,
      "step": 6
    },
    {
      "epoch": 0.07174887892376682,
      "eval_loss": 1.8910431861877441,
      "eval_runtime": 6.5162,
      "eval_samples_per_second": 21.638,
      "eval_steps_per_second": 10.896,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7614327410393088.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}