Hugging Face's logo

jssky
/
ebb7f595-e80f-4d33-9bb8-2d193ea0f113

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
ebb7f595-e80f-4d33-9bb8-2d193ea0f113
File size: 3,193 Bytes 
f83c8c7
 
 
d58e14d
f83c8c7
d58e14d
f83c8c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a04b6ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
936a571
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d58e14d
 
 
 
 
 
 
f83c8c7
 
 
 
 
 
 
 
 
 
 
 
 
 
d58e14d
f83c8c7
 
 
 
d58e14d
f83c8c7
 
 
 
 
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": 0.006126512482769184,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006126512482769183,
      "grad_norm": 1.3412106037139893,
      "learning_rate": 2e-05,
      "loss": 1.2605,
      "step": 1
    },
    {
      "epoch": 0.0006126512482769183,
      "eval_loss": 1.2916122674942017,
      "eval_runtime": 31.9584,
      "eval_samples_per_second": 10.764,
      "eval_steps_per_second": 10.764,
      "step": 1
    },
    {
      "epoch": 0.0012253024965538366,
      "grad_norm": 0.9073652029037476,
      "learning_rate": 4e-05,
      "loss": 0.9145,
      "step": 2
    },
    {
      "epoch": 0.001837953744830755,
      "grad_norm": 1.8176641464233398,
      "learning_rate": 6e-05,
      "loss": 1.5518,
      "step": 3
    },
    {
      "epoch": 0.001837953744830755,
      "eval_loss": 1.2262399196624756,
      "eval_runtime": 31.294,
      "eval_samples_per_second": 10.993,
      "eval_steps_per_second": 10.993,
      "step": 3
    },
    {
      "epoch": 0.0024506049931076732,
      "grad_norm": 1.203653335571289,
      "learning_rate": 8e-05,
      "loss": 0.9995,
      "step": 4
    },
    {
      "epoch": 0.003063256241384592,
      "grad_norm": 0.8254466652870178,
      "learning_rate": 0.0001,
      "loss": 0.7087,
      "step": 5
    },
    {
      "epoch": 0.00367590748966151,
      "grad_norm": 1.2285630702972412,
      "learning_rate": 0.00012,
      "loss": 0.9726,
      "step": 6
    },
    {
      "epoch": 0.00367590748966151,
      "eval_loss": 1.025619387626648,
      "eval_runtime": 31.2768,
      "eval_samples_per_second": 10.999,
      "eval_steps_per_second": 10.999,
      "step": 6
    },
    {
      "epoch": 0.004288558737938429,
      "grad_norm": 1.058066964149475,
      "learning_rate": 0.00014,
      "loss": 0.8224,
      "step": 7
    },
    {
      "epoch": 0.0049012099862153465,
      "grad_norm": 1.0622285604476929,
      "learning_rate": 0.00016,
      "loss": 0.9098,
      "step": 8
    },
    {
      "epoch": 0.005513861234492265,
      "grad_norm": 1.496508240699768,
      "learning_rate": 0.00018,
      "loss": 0.8408,
      "step": 9
    },
    {
      "epoch": 0.005513861234492265,
      "eval_loss": 0.7476592659950256,
      "eval_runtime": 31.2832,
      "eval_samples_per_second": 10.996,
      "eval_steps_per_second": 10.996,
      "step": 9
    },
    {
      "epoch": 0.006126512482769184,
      "grad_norm": 1.366001009941101,
      "learning_rate": 0.0002,
      "loss": 0.8999,
      "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": 1306268836823040.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}