Hugging Face's logo

SungJoo
/
qwen3-14b-full-ft-crisis-2epoch-2models-AGREE-FIXED

Safetensors
qwen3
Model card Files
xet
Community
qwen3-14b-full-ft-crisis-2epoch-2models-AGREE-FIXED
File size: 2,857 Bytes 
14896f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": 66,
  "best_metric": 0.20703822374343872,
  "best_model_checkpoint": "./2OR3models_AGREE_qwen_14b_FIXED/checkpoint-66",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.30614685481942117,
      "grad_norm": 2.296875,
      "learning_rate": 7.272727272727272e-06,
      "loss": 0.1684,
      "mean_token_accuracy": 0.9445589079055935,
      "num_tokens": 706980.0,
      "step": 10
    },
    {
      "epoch": 0.6122937096388423,
      "grad_norm": 1.796875,
      "learning_rate": 6.464646464646464e-06,
      "loss": 0.0674,
      "mean_token_accuracy": 0.9480227190069854,
      "num_tokens": 1419620.0,
      "step": 20
    },
    {
      "epoch": 0.9184405644582636,
      "grad_norm": 1.765625,
      "learning_rate": 5.656565656565656e-06,
      "loss": 0.0548,
      "mean_token_accuracy": 0.945695337234065,
      "num_tokens": 2128225.0,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.2109527587890625,
      "eval_mean_token_accuracy": 0.958704282652657,
      "eval_num_tokens": 2316871.0,
      "eval_runtime": 21.1385,
      "eval_samples_per_second": 19.869,
      "eval_steps_per_second": 2.507,
      "step": 33
    },
    {
      "epoch": 1.2143027983735948,
      "grad_norm": 1.2890625,
      "learning_rate": 4.848484848484849e-06,
      "loss": 0.044,
      "mean_token_accuracy": 0.9486577720919634,
      "num_tokens": 2810729.0,
      "step": 40
    },
    {
      "epoch": 1.520449653193016,
      "grad_norm": 1.765625,
      "learning_rate": 4.04040404040404e-06,
      "loss": 0.0406,
      "mean_token_accuracy": 0.9642394744325429,
      "num_tokens": 3524030.0,
      "step": 50
    },
    {
      "epoch": 1.8265965080124373,
      "grad_norm": 1.5078125,
      "learning_rate": 3.232323232323232e-06,
      "loss": 0.0416,
      "mean_token_accuracy": 0.9507318206131459,
      "num_tokens": 4231645.0,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.20703822374343872,
      "eval_mean_token_accuracy": 0.9592590725646829,
      "eval_num_tokens": 4633742.0,
      "eval_runtime": 21.1128,
      "eval_samples_per_second": 19.893,
      "eval_steps_per_second": 2.51,
      "step": 66
    }
  ],
  "logging_steps": 10,
  "max_steps": 99,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8896728211224576e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}