Hugging Face's logo

Paladiso
/
bb558fe8-9262-4aef-9da8-8c8ad8a19526

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
bb558fe8-9262-4aef-9da8-8c8ad8a19526
File size: 2,964 Bytes 
78891ee
 
 
28dd978
78891ee
28dd978
78891ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bb0076d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0705e10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28dd978
 
 
 
 
 
 
78891ee
 
 
 
 
 
 
 
 
 
 
 
 
 
28dd978
78891ee
 
 
 
28dd978
78891ee
 
 
 
 
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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.036596523330283626,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "grad_norm": 16.431114196777344,
      "learning_rate": 2e-05,
      "loss": 6.7731,
      "step": 1
    },
    {
      "epoch": 0.007319304666056725,
      "grad_norm": 13.973880767822266,
      "learning_rate": 4e-05,
      "loss": 6.7965,
      "step": 2
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 16.485984802246094,
      "learning_rate": 6e-05,
      "loss": 6.9483,
      "step": 3
    },
    {
      "epoch": 0.010978956999085087,
      "eval_loss": 6.581966876983643,
      "eval_runtime": 6.0089,
      "eval_samples_per_second": 19.138,
      "eval_steps_per_second": 9.652,
      "step": 3
    },
    {
      "epoch": 0.01463860933211345,
      "grad_norm": 16.0874080657959,
      "learning_rate": 8e-05,
      "loss": 6.7443,
      "step": 4
    },
    {
      "epoch": 0.018298261665141813,
      "grad_norm": 20.540544509887695,
      "learning_rate": 0.0001,
      "loss": 6.0838,
      "step": 5
    },
    {
      "epoch": 0.021957913998170174,
      "grad_norm": 22.555376052856445,
      "learning_rate": 0.00012,
      "loss": 4.8242,
      "step": 6
    },
    {
      "epoch": 0.021957913998170174,
      "eval_loss": 3.0552265644073486,
      "eval_runtime": 5.3044,
      "eval_samples_per_second": 21.68,
      "eval_steps_per_second": 10.934,
      "step": 6
    },
    {
      "epoch": 0.025617566331198535,
      "grad_norm": 12.365771293640137,
      "learning_rate": 0.00014,
      "loss": 3.0256,
      "step": 7
    },
    {
      "epoch": 0.0292772186642269,
      "grad_norm": 7.180561065673828,
      "learning_rate": 0.00016,
      "loss": 1.7685,
      "step": 8
    },
    {
      "epoch": 0.03293687099725526,
      "grad_norm": 4.194366931915283,
      "learning_rate": 0.00018,
      "loss": 1.0649,
      "step": 9
    },
    {
      "epoch": 0.03293687099725526,
      "eval_loss": 0.7600207924842834,
      "eval_runtime": 8.1062,
      "eval_samples_per_second": 14.187,
      "eval_steps_per_second": 7.155,
      "step": 9
    },
    {
      "epoch": 0.036596523330283626,
      "grad_norm": 2.806422472000122,
      "learning_rate": 0.0002,
      "loss": 0.6251,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1647822923366400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}