Hugging Face's logo

kokovova
/
62ba96d0-4158-4eda-9230-adf88ff6bc37

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
62ba96d0-4158-4eda-9230-adf88ff6bc37
File size: 2,418 Bytes 
f5a430d
 
 
f1f4dfc
f5a430d
f1f4dfc
f5a430d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f1f4dfc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f5a430d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f1f4dfc
f5a430d
 
 
 
 
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": 0.0008128098837681866,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.064049418840933e-05,
      "eval_loss": 11.762539863586426,
      "eval_runtime": 48.8482,
      "eval_samples_per_second": 212.106,
      "eval_steps_per_second": 106.063,
      "step": 1
    },
    {
      "epoch": 0.000121921482565228,
      "grad_norm": 0.0339069738984108,
      "learning_rate": 6e-05,
      "loss": 11.7631,
      "step": 3
    },
    {
      "epoch": 0.000243842965130456,
      "grad_norm": 0.041261523962020874,
      "learning_rate": 0.00012,
      "loss": 11.7618,
      "step": 6
    },
    {
      "epoch": 0.0003251239535072746,
      "eval_loss": 11.761956214904785,
      "eval_runtime": 49.0627,
      "eval_samples_per_second": 211.179,
      "eval_steps_per_second": 105.6,
      "step": 8
    },
    {
      "epoch": 0.000365764447695684,
      "grad_norm": 0.03510475158691406,
      "learning_rate": 0.00018,
      "loss": 11.7622,
      "step": 9
    },
    {
      "epoch": 0.000487685930260912,
      "grad_norm": 0.046722933650016785,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.7637,
      "step": 12
    },
    {
      "epoch": 0.00060960741282614,
      "grad_norm": 0.04540090635418892,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.7614,
      "step": 15
    },
    {
      "epoch": 0.0006502479070145493,
      "eval_loss": 11.760395050048828,
      "eval_runtime": 49.1458,
      "eval_samples_per_second": 210.822,
      "eval_steps_per_second": 105.421,
      "step": 16
    },
    {
      "epoch": 0.000731528895391368,
      "grad_norm": 0.0367448627948761,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.7622,
      "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": 2037000437760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}