Hugging Face's logo

ClarenceDan
/
2dbd336e-a106-4107-98b1-b3f3d34eba0a

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
2dbd336e-a106-4107-98b1-b3f3d34eba0a
File size: 3,203 Bytes 
f28d197
 
 
9de91e8
f28d197
9de91e8
f28d197
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
255ca9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
805b7ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9de91e8
 
 
 
 
 
 
f28d197
 
 
 
 
 
 
 
 
 
 
 
 
 
9de91e8
f28d197
 
 
 
9de91e8
f28d197
 
 
 
 
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": 0.00015873645779594428,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.587364577959443e-05,
      "grad_norm": 1.7801799774169922,
      "learning_rate": 2e-05,
      "loss": 1.7349,
      "step": 1
    },
    {
      "epoch": 1.587364577959443e-05,
      "eval_loss": 2.8036000728607178,
      "eval_runtime": 587.2782,
      "eval_samples_per_second": 45.168,
      "eval_steps_per_second": 22.584,
      "step": 1
    },
    {
      "epoch": 3.174729155918886e-05,
      "grad_norm": 2.7413840293884277,
      "learning_rate": 4e-05,
      "loss": 2.3991,
      "step": 2
    },
    {
      "epoch": 4.762093733878329e-05,
      "grad_norm": 2.748443841934204,
      "learning_rate": 6e-05,
      "loss": 3.015,
      "step": 3
    },
    {
      "epoch": 4.762093733878329e-05,
      "eval_loss": 2.7955071926116943,
      "eval_runtime": 506.2626,
      "eval_samples_per_second": 52.396,
      "eval_steps_per_second": 26.198,
      "step": 3
    },
    {
      "epoch": 6.349458311837772e-05,
      "grad_norm": 1.9895458221435547,
      "learning_rate": 8e-05,
      "loss": 2.449,
      "step": 4
    },
    {
      "epoch": 7.936822889797214e-05,
      "grad_norm": 1.320906162261963,
      "learning_rate": 0.0001,
      "loss": 2.5093,
      "step": 5
    },
    {
      "epoch": 9.524187467756657e-05,
      "grad_norm": 2.114384889602661,
      "learning_rate": 0.00012,
      "loss": 2.451,
      "step": 6
    },
    {
      "epoch": 9.524187467756657e-05,
      "eval_loss": 2.7090823650360107,
      "eval_runtime": 520.5763,
      "eval_samples_per_second": 50.955,
      "eval_steps_per_second": 25.478,
      "step": 6
    },
    {
      "epoch": 0.000111115520457161,
      "grad_norm": 2.729943037033081,
      "learning_rate": 0.00014,
      "loss": 3.3698,
      "step": 7
    },
    {
      "epoch": 0.00012698916623675544,
      "grad_norm": 1.4825519323349,
      "learning_rate": 0.00016,
      "loss": 2.4287,
      "step": 8
    },
    {
      "epoch": 0.00014286281201634986,
      "grad_norm": 1.5584574937820435,
      "learning_rate": 0.00018,
      "loss": 2.221,
      "step": 9
    },
    {
      "epoch": 0.00014286281201634986,
      "eval_loss": 2.539081573486328,
      "eval_runtime": 431.5948,
      "eval_samples_per_second": 61.46,
      "eval_steps_per_second": 30.73,
      "step": 9
    },
    {
      "epoch": 0.00015873645779594428,
      "grad_norm": 1.7351861000061035,
      "learning_rate": 0.0002,
      "loss": 2.3476,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}