Hugging Face's logo

Paladiso
/
369db93c-b0b2-4862-895e-e55b2f44da91

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
Community
369db93c-b0b2-4862-895e-e55b2f44da91
File size: 2,971 Bytes 
3025c08
 
 
28a63c9
3025c08
28a63c9
3025c08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a1bb36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cdc5e8c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28a63c9
 
 
 
 
 
 
3025c08
 
 
 
 
 
 
 
 
 
 
 
 
 
28a63c9
3025c08
 
 
 
28a63c9
3025c08
 
 
 
 
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": 0.009987515605493134,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009987515605493133,
      "grad_norm": 0.29484567046165466,
      "learning_rate": 2e-05,
      "loss": 0.9667,
      "step": 1
    },
    {
      "epoch": 0.0019975031210986267,
      "grad_norm": 0.4613470137119293,
      "learning_rate": 4e-05,
      "loss": 1.3396,
      "step": 2
    },
    {
      "epoch": 0.00299625468164794,
      "grad_norm": 0.32433879375457764,
      "learning_rate": 6e-05,
      "loss": 0.9502,
      "step": 3
    },
    {
      "epoch": 0.00299625468164794,
      "eval_loss": 1.0558395385742188,
      "eval_runtime": 24.2386,
      "eval_samples_per_second": 17.41,
      "eval_steps_per_second": 8.705,
      "step": 3
    },
    {
      "epoch": 0.003995006242197253,
      "grad_norm": 0.3317357003688812,
      "learning_rate": 8e-05,
      "loss": 0.9,
      "step": 4
    },
    {
      "epoch": 0.004993757802746567,
      "grad_norm": 0.3528467118740082,
      "learning_rate": 0.0001,
      "loss": 0.9682,
      "step": 5
    },
    {
      "epoch": 0.00599250936329588,
      "grad_norm": 0.45743900537490845,
      "learning_rate": 0.00012,
      "loss": 1.1032,
      "step": 6
    },
    {
      "epoch": 0.00599250936329588,
      "eval_loss": 1.039202094078064,
      "eval_runtime": 22.8981,
      "eval_samples_per_second": 18.429,
      "eval_steps_per_second": 9.215,
      "step": 6
    },
    {
      "epoch": 0.006991260923845194,
      "grad_norm": 0.3344796895980835,
      "learning_rate": 0.00014,
      "loss": 0.9604,
      "step": 7
    },
    {
      "epoch": 0.007990012484394507,
      "grad_norm": 0.36716145277023315,
      "learning_rate": 0.00016,
      "loss": 0.9254,
      "step": 8
    },
    {
      "epoch": 0.008988764044943821,
      "grad_norm": 0.5545617341995239,
      "learning_rate": 0.00018,
      "loss": 0.9992,
      "step": 9
    },
    {
      "epoch": 0.008988764044943821,
      "eval_loss": 0.9399694800376892,
      "eval_runtime": 22.0251,
      "eval_samples_per_second": 19.16,
      "eval_steps_per_second": 9.58,
      "step": 9
    },
    {
      "epoch": 0.009987515605493134,
      "grad_norm": 0.5323424339294434,
      "learning_rate": 0.0002,
      "loss": 0.7955,
      "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": 820048664985600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}