Hugging Face's logo

VERSIL91
/
e42a57b5-baa1-4c5e-ac30-4199934a0511

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
e42a57b5-baa1-4c5e-ac30-4199934a0511
File size: 2,136 Bytes 
b2cb796
 
 
5b6f07b
b2cb796
5b6f07b
b2cb796
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e3b6b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b6f07b
 
 
 
 
 
 
b2cb796
 
 
 
 
 
 
 
 
 
 
 
 
 
5b6f07b
b2cb796
 
 
 
5b6f07b
b2cb796
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018626309662398137,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037252619324796275,
      "grad_norm": 67.76799774169922,
      "learning_rate": 1e-05,
      "loss": 128.9905,
      "step": 1
    },
    {
      "epoch": 0.0037252619324796275,
      "eval_loss": NaN,
      "eval_runtime": 200.5957,
      "eval_samples_per_second": 2.258,
      "eval_steps_per_second": 1.132,
      "step": 1
    },
    {
      "epoch": 0.007450523864959255,
      "grad_norm": 70.9619140625,
      "learning_rate": 2e-05,
      "loss": 149.4326,
      "step": 2
    },
    {
      "epoch": 0.007450523864959255,
      "eval_loss": NaN,
      "eval_runtime": 41.7188,
      "eval_samples_per_second": 10.858,
      "eval_steps_per_second": 5.441,
      "step": 2
    },
    {
      "epoch": 0.011175785797438883,
      "grad_norm": 61.16599655151367,
      "learning_rate": 3e-05,
      "loss": 136.7895,
      "step": 3
    },
    {
      "epoch": 0.01490104772991851,
      "grad_norm": 58.64887237548828,
      "learning_rate": 4e-05,
      "loss": 125.9775,
      "step": 4
    },
    {
      "epoch": 0.01490104772991851,
      "eval_loss": NaN,
      "eval_runtime": 19.5158,
      "eval_samples_per_second": 23.212,
      "eval_steps_per_second": 11.632,
      "step": 4
    },
    {
      "epoch": 0.018626309662398137,
      "grad_norm": 71.09612274169922,
      "learning_rate": 5e-05,
      "loss": 136.0768,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6270684581855232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}