Hugging Face's logo

sergioalves
/
0e7f026a-4059-4dd5-9c54-26049a2fe884

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0e7f026a-4059-4dd5-9c54-26049a2fe884
File size: 1,666 Bytes 
5eb8ea9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003745283283864383,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.7452832838643834e-05,
      "eval_loss": 1.7370612621307373,
      "eval_runtime": 474.9951,
      "eval_samples_per_second": 23.67,
      "eval_steps_per_second": 11.836,
      "step": 1
    },
    {
      "epoch": 0.0001123584985159315,
      "grad_norm": 0.28893381357192993,
      "learning_rate": 3e-05,
      "loss": 1.5635,
      "step": 3
    },
    {
      "epoch": 0.000224716997031863,
      "grad_norm": 0.2005578577518463,
      "learning_rate": 6e-05,
      "loss": 1.6927,
      "step": 6
    },
    {
      "epoch": 0.00029962266270915067,
      "eval_loss": 1.7258363962173462,
      "eval_runtime": 473.4423,
      "eval_samples_per_second": 23.747,
      "eval_steps_per_second": 11.875,
      "step": 8
    },
    {
      "epoch": 0.00033707549554779447,
      "grad_norm": 0.25112399458885193,
      "learning_rate": 9e-05,
      "loss": 1.9006,
      "step": 9
    }
  ],
  "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": 579019934269440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}