Hugging Face's logo

KevinKibe
/
nllb-200-3.3B-finetuned

PyTorch
m2m_100
Generated from Trainer
Model card Files Community
nllb-200-3.3B-finetuned
File size: 3,470 Bytes 
3542237
f89bb15
 
562a00c
3542237
562a00c
3542237
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f89bb15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13a6685
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e353c26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae64e05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1028bed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
562a00c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3542237
 
 
 
 
 
 
562a00c
3542237
 
 
 
 
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
 
{
  "best_metric": 1.1881097555160522,
  "best_model_checkpoint": "../facebook/nllb-200-3.3B-finetuned/checkpoint-1000",
  "epoch": 3500.0,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 500.0,
      "grad_norm": 13.488256454467773,
      "learning_rate": 9.758186548415274e-06,
      "loss": 4.34,
      "step": 500
    },
    {
      "epoch": 500.0,
      "eval_gen_len": 26.0,
      "eval_loss": 2.901174306869507,
      "eval_rouge": 0.05,
      "eval_runtime": 7.0444,
      "eval_samples_per_second": 0.284,
      "eval_steps_per_second": 0.142,
      "step": 500
    },
    {
      "epoch": 1000.0,
      "grad_norm": 0.9894864559173584,
      "learning_rate": 9.050617527877911e-06,
      "loss": 0.609,
      "step": 1000
    },
    {
      "epoch": 1000.0,
      "eval_gen_len": 26.0,
      "eval_loss": 1.1881097555160522,
      "eval_rouge": 0.098,
      "eval_runtime": 1.1556,
      "eval_samples_per_second": 1.731,
      "eval_steps_per_second": 0.865,
      "step": 1000
    },
    {
      "epoch": 1500.0,
      "grad_norm": 0.1642373949289322,
      "learning_rate": 7.946545841400035e-06,
      "loss": 0.0196,
      "step": 1500
    },
    {
      "epoch": 1500.0,
      "eval_gen_len": 30.5,
      "eval_loss": 1.5324629545211792,
      "eval_rouge": 0.1493,
      "eval_runtime": 6.9442,
      "eval_samples_per_second": 0.288,
      "eval_steps_per_second": 0.144,
      "step": 1500
    },
    {
      "epoch": 2000.0,
      "grad_norm": 0.08364015817642212,
      "learning_rate": 6.554045718173867e-06,
      "loss": 0.0061,
      "step": 2000
    },
    {
      "epoch": 2000.0,
      "eval_gen_len": 33.5,
      "eval_loss": 1.5447587966918945,
      "eval_rouge": 0.125,
      "eval_runtime": 6.9455,
      "eval_samples_per_second": 0.288,
      "eval_steps_per_second": 0.144,
      "step": 2000
    },
    {
      "epoch": 2500.0,
      "grad_norm": 0.05517512932419777,
      "learning_rate": 5.0094247723796405e-06,
      "loss": 0.0036,
      "step": 2500
    },
    {
      "epoch": 2500.0,
      "eval_gen_len": 33.5,
      "eval_loss": 1.5625241994857788,
      "eval_rouge": 0.125,
      "eval_runtime": 6.9319,
      "eval_samples_per_second": 0.289,
      "eval_steps_per_second": 0.144,
      "step": 2500
    },
    {
      "epoch": 3000.0,
      "grad_norm": 0.04180261120200157,
      "learning_rate": 3.463881264198645e-06,
      "loss": 0.0025,
      "step": 3000
    },
    {
      "epoch": 3000.0,
      "eval_gen_len": 33.5,
      "eval_loss": 1.5641270875930786,
      "eval_rouge": 0.125,
      "eval_runtime": 6.9474,
      "eval_samples_per_second": 0.288,
      "eval_steps_per_second": 0.144,
      "step": 3000
    },
    {
      "epoch": 3500.0,
      "grad_norm": 0.03480682149529457,
      "learning_rate": 2.0687037606464554e-06,
      "loss": 0.002,
      "step": 3500
    },
    {
      "epoch": 3500.0,
      "eval_gen_len": 33.5,
      "eval_loss": 1.5625765323638916,
      "eval_rouge": 0.125,
      "eval_runtime": 6.9229,
      "eval_samples_per_second": 0.289,
      "eval_steps_per_second": 0.144,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5000,
  "save_steps": 500,
  "total_flos": 2.2267930804224e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}