Hugging Face's logo

jeqcho
/
mdcl_7b_to_3b-qwen25-3b-cat-random_10k-seed44

Transformers
Safetensors
unsloth
Model card Files
xet
 Community
mdcl_7b_to_3b-qwen25-3b-cat-random_10k-seed44
File size: 3,284 Bytes
d94c2e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0989010989010989,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6525499820709229,
      "learning_rate": 0.0,
      "loss": 2.4309,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.59049391746521,
      "learning_rate": 4e-05,
      "loss": 3.2935,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.4867584705352783,
      "learning_rate": 8e-05,
      "loss": 2.4426,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.8229094743728638,
      "learning_rate": 0.00012,
      "loss": 2.9208,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.2393176555633545,
      "learning_rate": 0.00016,
      "loss": 2.5664,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6051244735717773,
      "learning_rate": 0.0002,
      "loss": 2.4695,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1993753910064697,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6291,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.116241693496704,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3491,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8124693632125854,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3178,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4746452569961548,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3747,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0956214666366577,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2291,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5584886074066162,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2929,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8778825402259827,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0355,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5020594596862793,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1668,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4985601305961609,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1048,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2471665486135296.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}