Hugging Face's logo

adammandic87
/
032cbbb5-bf71-40df-bff5-a79fb44167c5

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
032cbbb5-bf71-40df-bff5-a79fb44167c5
File size: 2,430 Bytes 
bc51fad
 
 
8a2ec4e
bc51fad
8a2ec4e
bc51fad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6b985fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
caf6483
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a2ec4e
 
 
 
 
 
 
 
 
 
 
 
 
 
bc51fad
 
 
 
 
 
 
 
 
 
 
 
 
 
8a2ec4e
bc51fad
 
 
 
8a2ec4e
bc51fad
 
 
 
 
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
101
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1530221882172915,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00306044376434583,
      "eval_loss": 0.834145188331604,
      "eval_runtime": 6.2625,
      "eval_samples_per_second": 22.036,
      "eval_steps_per_second": 11.018,
      "step": 1
    },
    {
      "epoch": 0.030604437643458302,
      "grad_norm": 0.5659714341163635,
      "learning_rate": 0.0001,
      "loss": 0.7283,
      "step": 10
    },
    {
      "epoch": 0.03978576893649579,
      "eval_loss": 0.6105126142501831,
      "eval_runtime": 5.1744,
      "eval_samples_per_second": 26.67,
      "eval_steps_per_second": 13.335,
      "step": 13
    },
    {
      "epoch": 0.061208875286916604,
      "grad_norm": 0.6774999499320984,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5548,
      "step": 20
    },
    {
      "epoch": 0.07957153787299158,
      "eval_loss": 0.45831599831581116,
      "eval_runtime": 5.1833,
      "eval_samples_per_second": 26.624,
      "eval_steps_per_second": 13.312,
      "step": 26
    },
    {
      "epoch": 0.09181331293037491,
      "grad_norm": 0.5139346122741699,
      "learning_rate": 5e-05,
      "loss": 0.4389,
      "step": 30
    },
    {
      "epoch": 0.11935730680948738,
      "eval_loss": 0.43966734409332275,
      "eval_runtime": 5.1801,
      "eval_samples_per_second": 26.64,
      "eval_steps_per_second": 13.32,
      "step": 39
    },
    {
      "epoch": 0.12241775057383321,
      "grad_norm": 0.4938279986381531,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4451,
      "step": 40
    },
    {
      "epoch": 0.1530221882172915,
      "grad_norm": 0.5841078758239746,
      "learning_rate": 0.0,
      "loss": 0.452,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1282341913690112e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}