Hugging Face's logo

nblinh63
/
d7dec48d-6963-4941-a666-82afe3a01311

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
d7dec48d-6963-4941-a666-82afe3a01311
File size: 3,201 Bytes 
0545f56
 
 
7cd935d
0545f56
7cd935d
0545f56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b94374a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1d2cf88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7cd935d
 
 
 
 
 
 
0545f56
 
 
 
 
 
 
 
 
 
 
 
 
 
7cd935d
0545f56
 
 
 
7cd935d
0545f56
 
 
 
 
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
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001453646836501072,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014536468365010721,
      "grad_norm": 11.293152809143066,
      "learning_rate": 2e-05,
      "loss": 5.4024,
      "step": 1
    },
    {
      "epoch": 0.00014536468365010721,
      "eval_loss": 4.953571796417236,
      "eval_runtime": 1311.2116,
      "eval_samples_per_second": 2.209,
      "eval_steps_per_second": 1.105,
      "step": 1
    },
    {
      "epoch": 0.00029072936730021443,
      "grad_norm": 10.99425983428955,
      "learning_rate": 4e-05,
      "loss": 4.8248,
      "step": 2
    },
    {
      "epoch": 0.00043609405095032164,
      "grad_norm": 11.894266128540039,
      "learning_rate": 6e-05,
      "loss": 3.6072,
      "step": 3
    },
    {
      "epoch": 0.00043609405095032164,
      "eval_loss": 4.856856822967529,
      "eval_runtime": 1306.8243,
      "eval_samples_per_second": 2.217,
      "eval_steps_per_second": 1.109,
      "step": 3
    },
    {
      "epoch": 0.0005814587346004289,
      "grad_norm": 9.180171012878418,
      "learning_rate": 8e-05,
      "loss": 3.6817,
      "step": 4
    },
    {
      "epoch": 0.000726823418250536,
      "grad_norm": 12.513172149658203,
      "learning_rate": 0.0001,
      "loss": 5.2037,
      "step": 5
    },
    {
      "epoch": 0.0008721881019006433,
      "grad_norm": 6.623383045196533,
      "learning_rate": 0.00012,
      "loss": 2.7651,
      "step": 6
    },
    {
      "epoch": 0.0008721881019006433,
      "eval_loss": 3.960355758666992,
      "eval_runtime": 1307.1519,
      "eval_samples_per_second": 2.216,
      "eval_steps_per_second": 1.109,
      "step": 6
    },
    {
      "epoch": 0.0010175527855507504,
      "grad_norm": 6.6997294425964355,
      "learning_rate": 0.00014,
      "loss": 2.3049,
      "step": 7
    },
    {
      "epoch": 0.0011629174692008577,
      "grad_norm": 16.76756477355957,
      "learning_rate": 0.00016,
      "loss": 4.7391,
      "step": 8
    },
    {
      "epoch": 0.0013082821528509648,
      "grad_norm": 9.461111068725586,
      "learning_rate": 0.00018,
      "loss": 3.1305,
      "step": 9
    },
    {
      "epoch": 0.0013082821528509648,
      "eval_loss": 2.8077025413513184,
      "eval_runtime": 1305.1255,
      "eval_samples_per_second": 2.22,
      "eval_steps_per_second": 1.11,
      "step": 9
    },
    {
      "epoch": 0.001453646836501072,
      "grad_norm": 7.420252799987793,
      "learning_rate": 0.0002,
      "loss": 2.4734,
      "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": 621231451668480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}