Hugging Face's logo

kunjcr2
/
stackoverflow-flan-finetune

Transformers
TensorBoard
Safetensors
PEFT
English
Stackoverflow
flan-t5
lora
seq2seq
Model card Files
xet
Metrics Community
stackoverflow-flan-finetune
File size: 2,958 Bytes 
d7fafc8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": 500,
  "best_metric": 2.775390625,
  "best_model_checkpoint": "./stackoverflow_flan_finetune/checkpoint-500",
  "epoch": 0.14819205690574985,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02963841138114997,
      "grad_norm": 0.5776488780975342,
      "learning_rate": 0.0004853289863663308,
      "loss": 9.4912,
      "step": 100
    },
    {
      "epoch": 0.02963841138114997,
      "eval_loss": 3.810546875,
      "eval_runtime": 26.2211,
      "eval_samples_per_second": 57.168,
      "eval_steps_per_second": 7.17,
      "step": 100
    },
    {
      "epoch": 0.05927682276229994,
      "grad_norm": 0.5113403797149658,
      "learning_rate": 0.0004705097806757558,
      "loss": 3.9372,
      "step": 200
    },
    {
      "epoch": 0.05927682276229994,
      "eval_loss": 3.38671875,
      "eval_runtime": 26.0016,
      "eval_samples_per_second": 57.65,
      "eval_steps_per_second": 7.23,
      "step": 200
    },
    {
      "epoch": 0.08891523414344991,
      "grad_norm": 1.3626296520233154,
      "learning_rate": 0.0004556905749851808,
      "loss": 3.5486,
      "step": 300
    },
    {
      "epoch": 0.08891523414344991,
      "eval_loss": 3.048828125,
      "eval_runtime": 27.2076,
      "eval_samples_per_second": 55.095,
      "eval_steps_per_second": 6.91,
      "step": 300
    },
    {
      "epoch": 0.11855364552459988,
      "grad_norm": 0.4870101511478424,
      "learning_rate": 0.0004408713692946058,
      "loss": 3.2785,
      "step": 400
    },
    {
      "epoch": 0.11855364552459988,
      "eval_loss": 2.828125,
      "eval_runtime": 26.0791,
      "eval_samples_per_second": 57.479,
      "eval_steps_per_second": 7.209,
      "step": 400
    },
    {
      "epoch": 0.14819205690574985,
      "grad_norm": 1.628702163696289,
      "learning_rate": 0.00042605216360403083,
      "loss": 3.1755,
      "step": 500
    },
    {
      "epoch": 0.14819205690574985,
      "eval_loss": 2.775390625,
      "eval_runtime": 26.1328,
      "eval_samples_per_second": 57.361,
      "eval_steps_per_second": 7.194,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 3374,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 373894938624000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}