Hugging Face's logo

EricPeter
/
active-learning

PEFT
Safetensors
Model card Files Community
active-learning
File size: 3,838 Bytes 
d8a22ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
 
{
  "best_metric": 2.8250861167907715,
  "best_model_checkpoint": "en-to-lg-ufal-al/checkpoint-160",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 12.3779,
      "eval_gen_len": 42.6083,
      "eval_loss": 2.9468307495117188,
      "eval_runtime": 1501.8811,
      "eval_samples_per_second": 10.334,
      "eval_steps_per_second": 0.323,
      "step": 16
    },
    {
      "epoch": 2.0,
      "eval_bleu": 12.5162,
      "eval_gen_len": 42.7061,
      "eval_loss": 2.9221065044403076,
      "eval_runtime": 1525.1235,
      "eval_samples_per_second": 10.176,
      "eval_steps_per_second": 0.318,
      "step": 32
    },
    {
      "epoch": 3.0,
      "eval_bleu": 12.6486,
      "eval_gen_len": 42.7809,
      "eval_loss": 2.8996763229370117,
      "eval_runtime": 1520.5333,
      "eval_samples_per_second": 10.207,
      "eval_steps_per_second": 0.319,
      "step": 48
    },
    {
      "epoch": 3.125,
      "grad_norm": 1.846739411354065,
      "learning_rate": 1.3875e-05,
      "loss": 3.2685,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_bleu": 12.7887,
      "eval_gen_len": 42.9278,
      "eval_loss": 2.8806185722351074,
      "eval_runtime": 1541.7574,
      "eval_samples_per_second": 10.066,
      "eval_steps_per_second": 0.315,
      "step": 64
    },
    {
      "epoch": 5.0,
      "eval_bleu": 12.8971,
      "eval_gen_len": 42.9779,
      "eval_loss": 2.863759994506836,
      "eval_runtime": 1538.3478,
      "eval_samples_per_second": 10.089,
      "eval_steps_per_second": 0.315,
      "step": 80
    },
    {
      "epoch": 6.0,
      "eval_bleu": 12.9175,
      "eval_gen_len": 42.9273,
      "eval_loss": 2.8501696586608887,
      "eval_runtime": 1540.1728,
      "eval_samples_per_second": 10.077,
      "eval_steps_per_second": 0.315,
      "step": 96
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.854383111000061,
      "learning_rate": 7.625e-06,
      "loss": 3.1513,
      "step": 100
    },
    {
      "epoch": 7.0,
      "eval_bleu": 12.9938,
      "eval_gen_len": 43.0523,
      "eval_loss": 2.839545249938965,
      "eval_runtime": 1546.6529,
      "eval_samples_per_second": 10.035,
      "eval_steps_per_second": 0.314,
      "step": 112
    },
    {
      "epoch": 8.0,
      "eval_bleu": 13.0635,
      "eval_gen_len": 43.0526,
      "eval_loss": 2.831665277481079,
      "eval_runtime": 1543.1426,
      "eval_samples_per_second": 10.057,
      "eval_steps_per_second": 0.314,
      "step": 128
    },
    {
      "epoch": 9.0,
      "eval_bleu": 13.1002,
      "eval_gen_len": 43.099,
      "eval_loss": 2.8269288539886475,
      "eval_runtime": 1549.5221,
      "eval_samples_per_second": 10.016,
      "eval_steps_per_second": 0.313,
      "step": 144
    },
    {
      "epoch": 9.375,
      "grad_norm": 0.8836955428123474,
      "learning_rate": 1.3750000000000002e-06,
      "loss": 3.1409,
      "step": 150
    },
    {
      "epoch": 10.0,
      "eval_bleu": 13.0773,
      "eval_gen_len": 43.1512,
      "eval_loss": 2.8250861167907715,
      "eval_runtime": 1562.623,
      "eval_samples_per_second": 9.932,
      "eval_steps_per_second": 0.31,
      "step": 160
    }
  ],
  "logging_steps": 50,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 327971658792960.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}