Hugging Face's logo

kokovova
/
7b687989-2b60-41ed-a5af-0fb6590b5de7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7b687989-2b60-41ed-a5af-0fb6590b5de7
File size: 2,400 Bytes 
7bb3418
 
 
e02ed89
7bb3418
e02ed89
7bb3418
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e02ed89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7bb3418
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e02ed89
7bb3418
 
 
 
 
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": 0.008457553652605984,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004228776826302992,
      "eval_loss": 1.7915385961532593,
      "eval_runtime": 87.7121,
      "eval_samples_per_second": 11.355,
      "eval_steps_per_second": 5.678,
      "step": 1
    },
    {
      "epoch": 0.0012686330478908975,
      "grad_norm": 0.7311314940452576,
      "learning_rate": 6e-05,
      "loss": 1.7856,
      "step": 3
    },
    {
      "epoch": 0.002537266095781795,
      "grad_norm": 0.8283582925796509,
      "learning_rate": 0.00012,
      "loss": 1.8386,
      "step": 6
    },
    {
      "epoch": 0.0033830214610423934,
      "eval_loss": 1.6457921266555786,
      "eval_runtime": 86.6816,
      "eval_samples_per_second": 11.49,
      "eval_steps_per_second": 5.745,
      "step": 8
    },
    {
      "epoch": 0.003805899143672693,
      "grad_norm": 0.7579265832901001,
      "learning_rate": 0.00018,
      "loss": 1.559,
      "step": 9
    },
    {
      "epoch": 0.00507453219156359,
      "grad_norm": 1.1918922662734985,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.7637,
      "step": 12
    },
    {
      "epoch": 0.006343165239454488,
      "grad_norm": 0.7861229777336121,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.458,
      "step": 15
    },
    {
      "epoch": 0.006766042922084787,
      "eval_loss": 1.489386796951294,
      "eval_runtime": 86.7212,
      "eval_samples_per_second": 11.485,
      "eval_steps_per_second": 5.743,
      "step": 16
    },
    {
      "epoch": 0.007611798287345386,
      "grad_norm": 0.9497506022453308,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5591,
      "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": 1.066014263476224e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}