Hugging Face's logo

philip-hightech
/
e1693b23-e59d-449d-a002-a5eca4fc41f0

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
e1693b23-e59d-449d-a002-a5eca4fc41f0
File size: 2,439 Bytes 
7b74a0e
 
 
ee726d2
7b74a0e
ee726d2
7b74a0e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f395ac4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
023ca99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee726d2
 
 
 
 
 
 
 
 
 
 
 
 
 
7b74a0e
 
 
 
 
 
 
 
 
 
 
 
 
 
ee726d2
7b74a0e
 
 
 
ee726d2
7b74a0e
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18248175182481752,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036496350364963502,
      "eval_loss": 11.937646865844727,
      "eval_runtime": 0.3936,
      "eval_samples_per_second": 294.683,
      "eval_steps_per_second": 147.341,
      "step": 1
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 0.01586594060063362,
      "learning_rate": 5e-05,
      "loss": 11.9381,
      "step": 10
    },
    {
      "epoch": 0.04744525547445255,
      "eval_loss": 11.937573432922363,
      "eval_runtime": 0.3983,
      "eval_samples_per_second": 291.228,
      "eval_steps_per_second": 145.614,
      "step": 13
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 0.02235872857272625,
      "learning_rate": 4.267766952966369e-05,
      "loss": 11.9375,
      "step": 20
    },
    {
      "epoch": 0.0948905109489051,
      "eval_loss": 11.937477111816406,
      "eval_runtime": 0.4003,
      "eval_samples_per_second": 289.758,
      "eval_steps_per_second": 144.879,
      "step": 26
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 0.010235522873699665,
      "learning_rate": 2.5e-05,
      "loss": 11.937,
      "step": 30
    },
    {
      "epoch": 0.14233576642335766,
      "eval_loss": 11.937421798706055,
      "eval_runtime": 0.395,
      "eval_samples_per_second": 293.694,
      "eval_steps_per_second": 146.847,
      "step": 39
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 0.008573858067393303,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 11.9364,
      "step": 40
    },
    {
      "epoch": 0.18248175182481752,
      "grad_norm": 0.011130424216389656,
      "learning_rate": 0.0,
      "loss": 11.9372,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5908070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}