Hugging Face's logo

jssky
/
8d04d9ea-e0f3-4c6e-961f-a0a74f997d39

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
File size: 3,118 Bytes 
e25da1c
 
 
9862811
e25da1c
9862811
e25da1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85010db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32bf94b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9862811
 
 
 
 
 
 
e25da1c
 
 
 
 
 
 
 
 
 
 
 
 
 
9862811
e25da1c
 
 
 
9862811
e25da1c
 
 
 
 
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": 0.0015222437873425429,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015222437873425428,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.8275,
      "step": 1
    },
    {
      "epoch": 0.00015222437873425428,
      "eval_loss": 7.669393062591553,
      "eval_runtime": 93.5786,
      "eval_samples_per_second": 118.232,
      "eval_steps_per_second": 14.779,
      "step": 1
    },
    {
      "epoch": 0.00030444875746850857,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.9338,
      "step": 2
    },
    {
      "epoch": 0.0004566731362027629,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.5511,
      "step": 3
    },
    {
      "epoch": 0.0004566731362027629,
      "eval_loss": 7.669393062591553,
      "eval_runtime": 93.1619,
      "eval_samples_per_second": 118.761,
      "eval_steps_per_second": 14.845,
      "step": 3
    },
    {
      "epoch": 0.0006088975149370171,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 8.226,
      "step": 4
    },
    {
      "epoch": 0.0007611218936712714,
      "grad_norm": 26.795257568359375,
      "learning_rate": 2e-05,
      "loss": 7.7784,
      "step": 5
    },
    {
      "epoch": 0.0009133462724055258,
      "grad_norm": 26.446081161499023,
      "learning_rate": 4e-05,
      "loss": 7.7508,
      "step": 6
    },
    {
      "epoch": 0.0009133462724055258,
      "eval_loss": 7.27972412109375,
      "eval_runtime": 90.9362,
      "eval_samples_per_second": 121.668,
      "eval_steps_per_second": 15.208,
      "step": 6
    },
    {
      "epoch": 0.00106557065113978,
      "grad_norm": 25.43058204650879,
      "learning_rate": 6e-05,
      "loss": 7.1342,
      "step": 7
    },
    {
      "epoch": 0.0012177950298740343,
      "grad_norm": 20.734403610229492,
      "learning_rate": 8e-05,
      "loss": 6.4785,
      "step": 8
    },
    {
      "epoch": 0.0013700194086082886,
      "grad_norm": 19.443437576293945,
      "learning_rate": 0.0001,
      "loss": 5.6144,
      "step": 9
    },
    {
      "epoch": 0.0013700194086082886,
      "eval_loss": 4.204019069671631,
      "eval_runtime": 91.0755,
      "eval_samples_per_second": 121.482,
      "eval_steps_per_second": 15.185,
      "step": 9
    },
    {
      "epoch": 0.0015222437873425429,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 4.1238,
      "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": 2883817203302400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}