Hugging Face's logo

nmthien
/
vietnamese-gpt2

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
nmthien commited on
Commit
c122bea
·
verified ·
1 Parent(s): a62271a

Training in progress, step 1000, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +82 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6747c1dbb236ae8a8e2c013fd20695930a27f3e043e98d3527a043f6bad52d5c
3
  size 441688704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91623e2083a021d2a847f58e433bf6b162a7981b87d91d848b5225bca3958c6
3
  size 441688704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026c3a76931f69dfdbd218c11b08b8fe784a3ce60d1a6856a39cf4887f7973d1
3
  size 883473803
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47bdf519d96aa74e9c715546ec1a1288bd59b6143e44665732ac5391e10312c3
3
  size 883473803
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98e3012d71403a9a3da3536a0effa208f6c6bc60b40847bfead1201cbc3aaf4e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd87c7bd588cc407326020fcfa893af0bcddb350137a0abab09d5d4b782eb66
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d38247c8593a99c0071e308445b15a90a6a76bcfcf3d08cc7a2fcecc343f64
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada16671df03ce2c4c7b2196578593f96e5a9638c91cc68f984858ec0e816498
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.5,
6
  "eval_steps": 500,
7
- "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -86,6 +86,84 @@
86
  "eval_samples_per_second": 43.697,
87
  "eval_steps_per_second": 1.37,
88
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  }
90
  ],
91
  "logging_steps": 50,
@@ -100,12 +178,12 @@
100
  "should_evaluate": false,
101
  "should_log": false,
102
  "should_save": true,
103
- "should_training_stop": false
104
  },
105
  "attributes": {}
106
  }
107
  },
108
- "total_flos": 8361345024000000.0,
109
  "train_batch_size": 32,
110
  "trial_name": null,
111
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
  "eval_steps": 500,
7
+ "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
86
  "eval_samples_per_second": 43.697,
87
  "eval_steps_per_second": 1.37,
88
  "step": 500
89
+ },
90
+ {
91
+ "epoch": 0.55,
92
+ "grad_norm": 0.3327743709087372,
93
+ "learning_rate": 9.020000000000001e-05,
94
+ "loss": 3.3641653442382813,
95
+ "step": 550
96
+ },
97
+ {
98
+ "epoch": 0.6,
99
+ "grad_norm": 0.3543381094932556,
100
+ "learning_rate": 8.020000000000001e-05,
101
+ "loss": 3.343744812011719,
102
+ "step": 600
103
+ },
104
+ {
105
+ "epoch": 0.65,
106
+ "grad_norm": 0.3211086094379425,
107
+ "learning_rate": 7.02e-05,
108
+ "loss": 3.1690444946289062,
109
+ "step": 650
110
+ },
111
+ {
112
+ "epoch": 0.7,
113
+ "grad_norm": 0.3273960053920746,
114
+ "learning_rate": 6.02e-05,
115
+ "loss": 3.1066433715820314,
116
+ "step": 700
117
+ },
118
+ {
119
+ "epoch": 0.75,
120
+ "grad_norm": 0.3205295503139496,
121
+ "learning_rate": 5.02e-05,
122
+ "loss": 3.2476007080078126,
123
+ "step": 750
124
+ },
125
+ {
126
+ "epoch": 0.8,
127
+ "grad_norm": 0.3276917338371277,
128
+ "learning_rate": 4.02e-05,
129
+ "loss": 3.3101565551757814,
130
+ "step": 800
131
+ },
132
+ {
133
+ "epoch": 0.85,
134
+ "grad_norm": 0.3194756805896759,
135
+ "learning_rate": 3.02e-05,
136
+ "loss": 3.332541198730469,
137
+ "step": 850
138
+ },
139
+ {
140
+ "epoch": 0.9,
141
+ "grad_norm": 0.3311285674571991,
142
+ "learning_rate": 2.0200000000000003e-05,
143
+ "loss": 3.340621032714844,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 0.95,
148
+ "grad_norm": 0.32693082094192505,
149
+ "learning_rate": 1.02e-05,
150
+ "loss": 3.3452032470703124,
151
+ "step": 950
152
+ },
153
+ {
154
+ "epoch": 1.0,
155
+ "grad_norm": 0.32115134596824646,
156
+ "learning_rate": 2.0000000000000002e-07,
157
+ "loss": 3.334386901855469,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 1.0,
162
+ "eval_loss": 3.17313551902771,
163
+ "eval_runtime": 192.0422,
164
+ "eval_samples_per_second": 45.188,
165
+ "eval_steps_per_second": 1.416,
166
+ "step": 1000
167
  }
168
  ],
169
  "logging_steps": 50,
 
178
  "should_evaluate": false,
179
  "should_log": false,
180
  "should_save": true,
181
+ "should_training_stop": true
182
  },
183
  "attributes": {}
184
  }
185
  },
186
+ "total_flos": 1.6722690048e+16,
187
  "train_batch_size": 32,
188
  "trial_name": null,
189
  "trial_params": null