Hugging Face's logo

Paladiso
/
721c72a9-ea56-4aa8-a850-589c974f12f1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
721c72a9-ea56-4aa8-a850-589c974f12f1
File size: 2,997 Bytes 
512933c
 
 
b4af477
512933c
b4af477
512933c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c160715
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6dadbf9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b4af477
 
 
 
 
 
 
512933c
 
 
 
 
 
 
 
 
 
 
 
 
 
b4af477
512933c
 
 
 
b4af477
512933c
 
 
 
 
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": 0.0001293259531322746,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2932595313227458e-05,
      "grad_norm": 1.3630019426345825,
      "learning_rate": 2e-05,
      "loss": 1.3488,
      "step": 1
    },
    {
      "epoch": 2.5865190626454916e-05,
      "grad_norm": 1.150367259979248,
      "learning_rate": 4e-05,
      "loss": 1.2877,
      "step": 2
    },
    {
      "epoch": 3.8797785939682375e-05,
      "grad_norm": 1.5213168859481812,
      "learning_rate": 6e-05,
      "loss": 1.5296,
      "step": 3
    },
    {
      "epoch": 3.8797785939682375e-05,
      "eval_loss": 1.4517000913619995,
      "eval_runtime": 1785.3318,
      "eval_samples_per_second": 18.236,
      "eval_steps_per_second": 9.118,
      "step": 3
    },
    {
      "epoch": 5.173038125290983e-05,
      "grad_norm": 1.284034013748169,
      "learning_rate": 8e-05,
      "loss": 1.4316,
      "step": 4
    },
    {
      "epoch": 6.46629765661373e-05,
      "grad_norm": 1.3621246814727783,
      "learning_rate": 0.0001,
      "loss": 1.2137,
      "step": 5
    },
    {
      "epoch": 7.759557187936475e-05,
      "grad_norm": 1.5063856840133667,
      "learning_rate": 0.00012,
      "loss": 1.3861,
      "step": 6
    },
    {
      "epoch": 7.759557187936475e-05,
      "eval_loss": 1.1301480531692505,
      "eval_runtime": 1801.8138,
      "eval_samples_per_second": 18.07,
      "eval_steps_per_second": 9.035,
      "step": 6
    },
    {
      "epoch": 9.052816719259221e-05,
      "grad_norm": 1.1399325132369995,
      "learning_rate": 0.00014,
      "loss": 0.7782,
      "step": 7
    },
    {
      "epoch": 0.00010346076250581966,
      "grad_norm": 1.6941022872924805,
      "learning_rate": 0.00016,
      "loss": 0.9016,
      "step": 8
    },
    {
      "epoch": 0.00011639335781904713,
      "grad_norm": 1.6896311044692993,
      "learning_rate": 0.00018,
      "loss": 0.809,
      "step": 9
    },
    {
      "epoch": 0.00011639335781904713,
      "eval_loss": 0.49266761541366577,
      "eval_runtime": 1811.7138,
      "eval_samples_per_second": 17.971,
      "eval_steps_per_second": 8.985,
      "step": 9
    },
    {
      "epoch": 0.0001293259531322746,
      "grad_norm": 1.1890869140625,
      "learning_rate": 0.0002,
      "loss": 0.4355,
      "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": 1628734142545920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}