Hugging Face's logo

nathanialhunt
/
f9aae621-ff3f-46e8-9fbc-0c9388f225de

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f9aae621-ff3f-46e8-9fbc-0c9388f225de
File size: 3,207 Bytes 
52ff093
 
 
51ec3a4
52ff093
51ec3a4
52ff093
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae4c7c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36dc997
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51ec3a4
 
 
 
 
 
 
52ff093
 
 
 
 
 
 
 
 
 
 
 
 
 
51ec3a4
52ff093
 
 
 
51ec3a4
52ff093
 
 
 
 
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": 0.0008520246235116195,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.520246235116194e-05,
      "grad_norm": 11.390654563903809,
      "learning_rate": 2e-05,
      "loss": 1.5967,
      "step": 1
    },
    {
      "epoch": 8.520246235116194e-05,
      "eval_loss": 1.6326349973678589,
      "eval_runtime": 97.9639,
      "eval_samples_per_second": 50.447,
      "eval_steps_per_second": 25.224,
      "step": 1
    },
    {
      "epoch": 0.00017040492470232388,
      "grad_norm": 16.750507354736328,
      "learning_rate": 4e-05,
      "loss": 1.9276,
      "step": 2
    },
    {
      "epoch": 0.00025560738705348587,
      "grad_norm": 13.093873023986816,
      "learning_rate": 6e-05,
      "loss": 1.2497,
      "step": 3
    },
    {
      "epoch": 0.00025560738705348587,
      "eval_loss": 1.5361175537109375,
      "eval_runtime": 96.3426,
      "eval_samples_per_second": 51.296,
      "eval_steps_per_second": 25.648,
      "step": 3
    },
    {
      "epoch": 0.00034080984940464777,
      "grad_norm": 8.885797500610352,
      "learning_rate": 8e-05,
      "loss": 1.0354,
      "step": 4
    },
    {
      "epoch": 0.0004260123117558097,
      "grad_norm": 7.249693393707275,
      "learning_rate": 0.0001,
      "loss": 0.9423,
      "step": 5
    },
    {
      "epoch": 0.0005112147741069717,
      "grad_norm": 10.092117309570312,
      "learning_rate": 0.00012,
      "loss": 1.2452,
      "step": 6
    },
    {
      "epoch": 0.0005112147741069717,
      "eval_loss": 0.8979904055595398,
      "eval_runtime": 94.4489,
      "eval_samples_per_second": 52.325,
      "eval_steps_per_second": 26.162,
      "step": 6
    },
    {
      "epoch": 0.0005964172364581337,
      "grad_norm": 5.180422782897949,
      "learning_rate": 0.00014,
      "loss": 0.5217,
      "step": 7
    },
    {
      "epoch": 0.0006816196988092955,
      "grad_norm": 9.183744430541992,
      "learning_rate": 0.00016,
      "loss": 0.654,
      "step": 8
    },
    {
      "epoch": 0.0007668221611604575,
      "grad_norm": 6.878085613250732,
      "learning_rate": 0.00018,
      "loss": 0.3706,
      "step": 9
    },
    {
      "epoch": 0.0007668221611604575,
      "eval_loss": 0.32512030005455017,
      "eval_runtime": 95.6597,
      "eval_samples_per_second": 51.662,
      "eval_steps_per_second": 25.831,
      "step": 9
    },
    {
      "epoch": 0.0008520246235116195,
      "grad_norm": 3.814892053604126,
      "learning_rate": 0.0002,
      "loss": 0.4047,
      "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
}