Hugging Face's logo

ImNotTam
/
finetuned_7__2

Safetensors
Vietnamese
English
llm-judge
training-checkpoint
lora
unsloth
Model card Files
xet
 Community
finetuned_7__2
File size: 3,330 Bytes
93cb107
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": 60,
  "best_metric": 0.0092080757021904,
  "best_model_checkpoint": "/teamspace/studios/this_studio/DATN/output/medgemma_finetuned/checkpoint-60",
  "epoch": 5.36036036036036,
  "eval_steps": 15,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.6498702168464661,
      "learning_rate": 0.00018,
      "loss": 0.2477,
      "step": 10
    },
    {
      "epoch": 1.072072072072072,
      "eval_loss": 0.021378077566623688,
      "eval_runtime": 66.1391,
      "eval_samples_per_second": 0.242,
      "eval_steps_per_second": 0.121,
      "step": 15
    },
    {
      "epoch": 1.4324324324324325,
      "grad_norm": 2.6276116371154785,
      "learning_rate": 0.00019488259168373197,
      "loss": 0.0165,
      "step": 20
    },
    {
      "epoch": 2.144144144144144,
      "grad_norm": 0.3735731244087219,
      "learning_rate": 0.00017786415380497553,
      "loss": 0.0418,
      "step": 30
    },
    {
      "epoch": 2.144144144144144,
      "eval_loss": 0.019194122403860092,
      "eval_runtime": 23.7384,
      "eval_samples_per_second": 0.674,
      "eval_steps_per_second": 0.337,
      "step": 30
    },
    {
      "epoch": 2.864864864864865,
      "grad_norm": 0.07709665596485138,
      "learning_rate": 0.00015102700330609,
      "loss": 0.01,
      "step": 40
    },
    {
      "epoch": 3.2162162162162162,
      "eval_loss": 0.009275071322917938,
      "eval_runtime": 23.8923,
      "eval_samples_per_second": 0.67,
      "eval_steps_per_second": 0.335,
      "step": 45
    },
    {
      "epoch": 3.5765765765765765,
      "grad_norm": 0.09296473115682602,
      "learning_rate": 0.00011775531962543036,
      "loss": 0.0089,
      "step": 50
    },
    {
      "epoch": 4.288288288288288,
      "grad_norm": 0.06089961528778076,
      "learning_rate": 8.224468037456969e-05,
      "loss": 0.0088,
      "step": 60
    },
    {
      "epoch": 4.288288288288288,
      "eval_loss": 0.0092080757021904,
      "eval_runtime": 23.6439,
      "eval_samples_per_second": 0.677,
      "eval_steps_per_second": 0.338,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.04466509446501732,
      "learning_rate": 4.8972996693910054e-05,
      "loss": 0.0084,
      "step": 70
    },
    {
      "epoch": 5.36036036036036,
      "eval_loss": 0.009462282992899418,
      "eval_runtime": 23.7549,
      "eval_samples_per_second": 0.674,
      "eval_steps_per_second": 0.337,
      "step": 75
    }
  ],
  "logging_steps": 10,
  "max_steps": 98,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 15,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 45,
        "early_stopping_threshold": 0.0001
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.066878161809609e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}