Hugging Face's logo

VERSIL91
/
d0f82559-dd90-405b-b328-f7d2c4f8737f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
Community
d0f82559-dd90-405b-b328-f7d2c4f8737f
File size: 2,181 Bytes 
d1bf3f3
 
 
d530f42
d1bf3f3
d530f42
d1bf3f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2853678
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d530f42
 
 
 
 
 
 
d1bf3f3
 
 
 
 
 
 
 
 
 
 
 
 
 
d530f42
d1bf3f3
 
 
 
d530f42
d1bf3f3
 
 
 
 
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": 0.010182003309151075,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002036400661830215,
      "grad_norm": 0.3946382403373718,
      "learning_rate": 1e-05,
      "loss": 2.1342,
      "step": 1
    },
    {
      "epoch": 0.002036400661830215,
      "eval_loss": 2.5031049251556396,
      "eval_runtime": 163.8416,
      "eval_samples_per_second": 5.048,
      "eval_steps_per_second": 2.527,
      "step": 1
    },
    {
      "epoch": 0.00407280132366043,
      "grad_norm": 0.32853010296821594,
      "learning_rate": 2e-05,
      "loss": 1.9424,
      "step": 2
    },
    {
      "epoch": 0.00407280132366043,
      "eval_loss": 2.4755871295928955,
      "eval_runtime": 16.4429,
      "eval_samples_per_second": 50.295,
      "eval_steps_per_second": 25.178,
      "step": 2
    },
    {
      "epoch": 0.0061092019854906456,
      "grad_norm": 0.35577061772346497,
      "learning_rate": 3e-05,
      "loss": 2.0014,
      "step": 3
    },
    {
      "epoch": 0.00814560264732086,
      "grad_norm": 0.36109641194343567,
      "learning_rate": 4e-05,
      "loss": 1.9657,
      "step": 4
    },
    {
      "epoch": 0.00814560264732086,
      "eval_loss": 2.4512460231781006,
      "eval_runtime": 16.3794,
      "eval_samples_per_second": 50.49,
      "eval_steps_per_second": 25.276,
      "step": 4
    },
    {
      "epoch": 0.010182003309151075,
      "grad_norm": 0.39837709069252014,
      "learning_rate": 5e-05,
      "loss": 2.0879,
      "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": 1681099763220480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}