Hugging Face's logo

Hugging-GK
/
stack_exc_multilabel_instr_lm_head

Text Generation
PEFT
Safetensors
Transformers
lora
sft
trl
conversational
Model card Files
xet
Community
stack_exc_multilabel_instr_lm_head
File size: 3,993 Bytes
665fd51
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 100,
  "best_metric": 0.0856408029794693,
  "best_model_checkpoint": "/content/models/gemma_qlora_lmh_inst/checkpoint-100",
  "epoch": 1.7008547008547008,
  "eval_steps": 20,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.185229367017746,
      "epoch": 0.3418803418803419,
      "grad_norm": 5.452565670013428,
      "learning_rate": 8.389830508474577e-06,
      "loss": 0.527,
      "mean_token_accuracy": 0.8931800335645675,
      "num_tokens": 118924.0,
      "step": 20
    },
    {
      "epoch": 0.3418803418803419,
      "eval_entropy": 2.111573049145886,
      "eval_loss": 0.13321338593959808,
      "eval_mean_token_accuracy": 0.9574781697020571,
      "eval_num_tokens": 118924.0,
      "eval_runtime": 47.1766,
      "eval_samples_per_second": 39.448,
      "eval_steps_per_second": 2.48,
      "step": 20
    },
    {
      "entropy": 2.087030777335167,
      "epoch": 0.6837606837606838,
      "grad_norm": 2.0593972206115723,
      "learning_rate": 6.694915254237288e-06,
      "loss": 0.1209,
      "mean_token_accuracy": 0.9594760566949845,
      "num_tokens": 236856.0,
      "step": 40
    },
    {
      "epoch": 0.6837606837606838,
      "eval_entropy": 2.0892730227902403,
      "eval_loss": 0.09804344922304153,
      "eval_mean_token_accuracy": 0.9691366318963531,
      "eval_num_tokens": 236856.0,
      "eval_runtime": 46.3719,
      "eval_samples_per_second": 40.132,
      "eval_steps_per_second": 2.523,
      "step": 40
    },
    {
      "entropy": 2.0854212504166822,
      "epoch": 1.017094017094017,
      "grad_norm": 2.2971627712249756,
      "learning_rate": 5e-06,
      "loss": 0.1049,
      "mean_token_accuracy": 0.9694300477321331,
      "num_tokens": 347411.0,
      "step": 60
    },
    {
      "epoch": 1.017094017094017,
      "eval_entropy": 2.0886059316814456,
      "eval_loss": 0.09312945604324341,
      "eval_mean_token_accuracy": 0.9695246902286497,
      "eval_num_tokens": 347411.0,
      "eval_runtime": 46.3826,
      "eval_samples_per_second": 40.123,
      "eval_steps_per_second": 2.522,
      "step": 60
    },
    {
      "entropy": 2.0619985163211823,
      "epoch": 1.358974358974359,
      "grad_norm": 1.8603676557540894,
      "learning_rate": 3.305084745762712e-06,
      "loss": 0.0752,
      "mean_token_accuracy": 0.9758038982748986,
      "num_tokens": 463138.0,
      "step": 80
    },
    {
      "epoch": 1.358974358974359,
      "eval_entropy": 2.0556565125783286,
      "eval_loss": 0.09433301538228989,
      "eval_mean_token_accuracy": 0.9687594807046092,
      "eval_num_tokens": 463138.0,
      "eval_runtime": 46.4215,
      "eval_samples_per_second": 40.089,
      "eval_steps_per_second": 2.52,
      "step": 80
    },
    {
      "entropy": 2.0492735713720323,
      "epoch": 1.7008547008547008,
      "grad_norm": 1.3368176221847534,
      "learning_rate": 1.6101694915254237e-06,
      "loss": 0.0619,
      "mean_token_accuracy": 0.9785473644733429,
      "num_tokens": 581349.0,
      "step": 100
    },
    {
      "epoch": 1.7008547008547008,
      "eval_entropy": 2.024941165223081,
      "eval_loss": 0.0856408029794693,
      "eval_mean_token_accuracy": 0.9721253937126225,
      "eval_num_tokens": 581349.0,
      "eval_runtime": 46.4267,
      "eval_samples_per_second": 40.085,
      "eval_steps_per_second": 2.52,
      "step": 100
    }
  ],
  "logging_steps": 20,
  "max_steps": 118,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6519515681526272e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}