Hugging Face's logo

Paladiso
/
f7ff76c3-0b5c-4bcf-a7b7-b4c360b7e417

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
Community
1
f7ff76c3-0b5c-4bcf-a7b7-b4c360b7e417
File size: 3,047 Bytes 
2496a35
 
 
8ea8cb3
2496a35
8ea8cb3
2496a35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be547f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ea8cb3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2496a35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ea8cb3
2496a35
 
 
 
 
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
129
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019835803625544105,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022039781806160118,
      "grad_norm": 0.6059606075286865,
      "learning_rate": 2e-05,
      "loss": 0.6582,
      "step": 1
    },
    {
      "epoch": 0.00022039781806160118,
      "eval_loss": 0.6642674207687378,
      "eval_runtime": 56.6046,
      "eval_samples_per_second": 33.76,
      "eval_steps_per_second": 16.889,
      "step": 1
    },
    {
      "epoch": 0.00044079563612320236,
      "grad_norm": 0.5567238926887512,
      "learning_rate": 4e-05,
      "loss": 0.603,
      "step": 2
    },
    {
      "epoch": 0.0006611934541848036,
      "grad_norm": 0.622408926486969,
      "learning_rate": 6e-05,
      "loss": 0.694,
      "step": 3
    },
    {
      "epoch": 0.0006611934541848036,
      "eval_loss": 0.660050094127655,
      "eval_runtime": 55.3516,
      "eval_samples_per_second": 34.525,
      "eval_steps_per_second": 17.271,
      "step": 3
    },
    {
      "epoch": 0.0008815912722464047,
      "grad_norm": 0.6857208609580994,
      "learning_rate": 8e-05,
      "loss": 0.8926,
      "step": 4
    },
    {
      "epoch": 0.001101989090308006,
      "grad_norm": 0.7746605277061462,
      "learning_rate": 0.0001,
      "loss": 0.5486,
      "step": 5
    },
    {
      "epoch": 0.0013223869083696072,
      "grad_norm": 1.2170764207839966,
      "learning_rate": 0.00012,
      "loss": 0.7053,
      "step": 6
    },
    {
      "epoch": 0.0013223869083696072,
      "eval_loss": 0.5303690433502197,
      "eval_runtime": 55.4034,
      "eval_samples_per_second": 34.492,
      "eval_steps_per_second": 17.255,
      "step": 6
    },
    {
      "epoch": 0.0015427847264312083,
      "grad_norm": 0.7118781208992004,
      "learning_rate": 0.00014,
      "loss": 0.4517,
      "step": 7
    },
    {
      "epoch": 0.0017631825444928094,
      "grad_norm": 0.635513961315155,
      "learning_rate": 0.00016,
      "loss": 0.3173,
      "step": 8
    },
    {
      "epoch": 0.0019835803625544105,
      "grad_norm": 0.5836746096611023,
      "learning_rate": 0.00018,
      "loss": 0.3211,
      "step": 9
    },
    {
      "epoch": 0.0019835803625544105,
      "eval_loss": 0.3485614061355591,
      "eval_runtime": 55.5095,
      "eval_samples_per_second": 34.427,
      "eval_steps_per_second": 17.222,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1568372441481216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}