Hugging Face's logo

jssky
/
ab88c701-ac81-4fdf-b808-21d9a7afbd7a

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
ab88c701-ac81-4fdf-b808-21d9a7afbd7a
File size: 3,215 Bytes 
291f9e9
 
 
2bbe42d
291f9e9
2bbe42d
291f9e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d6b090a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad465fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2bbe42d
 
 
 
 
 
 
291f9e9
 
 
 
 
 
 
 
 
 
 
 
 
 
2bbe42d
291f9e9
 
 
 
2bbe42d
291f9e9
 
 
 
 
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": 0.00034919554077294433,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.491955407729443e-05,
      "grad_norm": 1.5854488611221313,
      "learning_rate": 2e-05,
      "loss": 2.0741,
      "step": 1
    },
    {
      "epoch": 3.491955407729443e-05,
      "eval_loss": 2.1542773246765137,
      "eval_runtime": 357.8677,
      "eval_samples_per_second": 16.847,
      "eval_steps_per_second": 16.847,
      "step": 1
    },
    {
      "epoch": 6.983910815458886e-05,
      "grad_norm": 1.4733368158340454,
      "learning_rate": 4e-05,
      "loss": 1.5595,
      "step": 2
    },
    {
      "epoch": 0.00010475866223188329,
      "grad_norm": 2.865410804748535,
      "learning_rate": 6e-05,
      "loss": 1.7822,
      "step": 3
    },
    {
      "epoch": 0.00010475866223188329,
      "eval_loss": 2.1372852325439453,
      "eval_runtime": 356.9492,
      "eval_samples_per_second": 16.89,
      "eval_steps_per_second": 16.89,
      "step": 3
    },
    {
      "epoch": 0.00013967821630917772,
      "grad_norm": 2.658249616622925,
      "learning_rate": 8e-05,
      "loss": 2.1342,
      "step": 4
    },
    {
      "epoch": 0.00017459777038647217,
      "grad_norm": 2.390005111694336,
      "learning_rate": 0.0001,
      "loss": 1.829,
      "step": 5
    },
    {
      "epoch": 0.00020951732446376658,
      "grad_norm": 1.4543702602386475,
      "learning_rate": 0.00012,
      "loss": 1.679,
      "step": 6
    },
    {
      "epoch": 0.00020951732446376658,
      "eval_loss": 2.071124315261841,
      "eval_runtime": 357.0228,
      "eval_samples_per_second": 16.887,
      "eval_steps_per_second": 16.887,
      "step": 6
    },
    {
      "epoch": 0.00024443687854106103,
      "grad_norm": 1.8792164325714111,
      "learning_rate": 0.00014,
      "loss": 2.4839,
      "step": 7
    },
    {
      "epoch": 0.00027935643261835545,
      "grad_norm": 2.3412582874298096,
      "learning_rate": 0.00016,
      "loss": 1.5353,
      "step": 8
    },
    {
      "epoch": 0.0003142759866956499,
      "grad_norm": 1.6153055429458618,
      "learning_rate": 0.00018,
      "loss": 1.6283,
      "step": 9
    },
    {
      "epoch": 0.0003142759866956499,
      "eval_loss": 2.0233631134033203,
      "eval_runtime": 358.2408,
      "eval_samples_per_second": 16.829,
      "eval_steps_per_second": 16.829,
      "step": 9
    },
    {
      "epoch": 0.00034919554077294433,
      "grad_norm": 2.771148443222046,
      "learning_rate": 0.0002,
      "loss": 1.4844,
      "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": 360477150412800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}