Hugging Face's logo

dimasik87
/
d77e41ee-8587-4461-bf28-27d3384386a6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d77e41ee-8587-4461-bf28-27d3384386a6
File size: 2,155 Bytes 
c303ed7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.6682432889938354,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.043149946062567425,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004314994606256742,
      "eval_loss": 2.547675371170044,
      "eval_runtime": 17.0287,
      "eval_samples_per_second": 11.451,
      "eval_steps_per_second": 2.877,
      "step": 1
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 0.3732893764972687,
      "learning_rate": 0.00012,
      "loss": 1.9139,
      "step": 3
    },
    {
      "epoch": 0.021574973031283712,
      "eval_loss": 2.419311285018921,
      "eval_runtime": 16.2521,
      "eval_samples_per_second": 11.998,
      "eval_steps_per_second": 3.015,
      "step": 5
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 0.6296373009681702,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.1198,
      "step": 6
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 0.834452748298645,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.844,
      "step": 9
    },
    {
      "epoch": 0.043149946062567425,
      "eval_loss": 1.6682432889938354,
      "eval_runtime": 16.2667,
      "eval_samples_per_second": 11.988,
      "eval_steps_per_second": 3.012,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2695579394048e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}