Hugging Face's logo

Paladiso
/
e2729802-dde6-43c2-bb4a-4d0a4beac90e

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
e2729802-dde6-43c2-bb4a-4d0a4beac90e
File size: 2,984 Bytes 
4015c0f
 
 
40bfd20
4015c0f
40bfd20
4015c0f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fabe877
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9e7076
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40bfd20
 
 
 
 
 
 
4015c0f
 
 
 
 
 
 
 
 
 
 
 
 
 
40bfd20
4015c0f
 
 
 
40bfd20
4015c0f
 
 
 
 
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": 0.0012396566151176124,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012396566151176124,
      "grad_norm": 1.4749228954315186,
      "learning_rate": 2e-05,
      "loss": 2.3448,
      "step": 1
    },
    {
      "epoch": 0.0002479313230235225,
      "grad_norm": 1.1061748266220093,
      "learning_rate": 4e-05,
      "loss": 2.3491,
      "step": 2
    },
    {
      "epoch": 0.00037189698453528373,
      "grad_norm": 1.2379366159439087,
      "learning_rate": 6e-05,
      "loss": 2.327,
      "step": 3
    },
    {
      "epoch": 0.00037189698453528373,
      "eval_loss": 2.8299930095672607,
      "eval_runtime": 231.6956,
      "eval_samples_per_second": 14.661,
      "eval_steps_per_second": 7.333,
      "step": 3
    },
    {
      "epoch": 0.000495862646047045,
      "grad_norm": 1.9947458505630493,
      "learning_rate": 8e-05,
      "loss": 3.0068,
      "step": 4
    },
    {
      "epoch": 0.0006198283075588062,
      "grad_norm": 1.231313705444336,
      "learning_rate": 0.0001,
      "loss": 2.5538,
      "step": 5
    },
    {
      "epoch": 0.0007437939690705675,
      "grad_norm": 1.4085564613342285,
      "learning_rate": 0.00012,
      "loss": 2.4,
      "step": 6
    },
    {
      "epoch": 0.0007437939690705675,
      "eval_loss": 2.711785078048706,
      "eval_runtime": 234.2588,
      "eval_samples_per_second": 14.501,
      "eval_steps_per_second": 7.253,
      "step": 6
    },
    {
      "epoch": 0.0008677596305823287,
      "grad_norm": 1.1774617433547974,
      "learning_rate": 0.00014,
      "loss": 2.1749,
      "step": 7
    },
    {
      "epoch": 0.00099172529209409,
      "grad_norm": 1.5084151029586792,
      "learning_rate": 0.00016,
      "loss": 2.7707,
      "step": 8
    },
    {
      "epoch": 0.001115690953605851,
      "grad_norm": 1.7904571294784546,
      "learning_rate": 0.00018,
      "loss": 2.8662,
      "step": 9
    },
    {
      "epoch": 0.001115690953605851,
      "eval_loss": 2.3707175254821777,
      "eval_runtime": 237.4543,
      "eval_samples_per_second": 14.306,
      "eval_steps_per_second": 7.155,
      "step": 9
    },
    {
      "epoch": 0.0012396566151176124,
      "grad_norm": 1.475090503692627,
      "learning_rate": 0.0002,
      "loss": 2.0393,
      "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": 397265366679552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}