Update README.md
Browse files
README.md
CHANGED
@@ -65,44 +65,45 @@ model = AutoModelForCausalLM.from_pretrained("supermy/couplet")
|
|
65 |
|
66 |
bpe分词:"vocab_size"=50000
|
67 |
```
|
68 |
-
[INFO|trainer.py:1608] 2022-11-
|
69 |
-
[INFO|trainer.py:1609] 2022-11-
|
70 |
-
[INFO|trainer.py:1610] 2022-11-
|
71 |
-
[INFO|trainer.py:1611] 2022-11-
|
72 |
-
[INFO|trainer.py:1612] 2022-11-
|
73 |
-
[INFO|trainer.py:1613] 2022-11-
|
74 |
-
[INFO|trainer.py:1614] 2022-11-
|
75 |
-
[INFO|trainer.py:1616] 2022-11-
|
76 |
-
|
77 |
-
{'loss': 6.
|
78 |
-
{'loss': 5.
|
|
|
79 |
......
|
80 |
......
|
81 |
......
|
82 |
-
{'loss':
|
83 |
-
{'train_runtime':
|
84 |
***** train metrics *****
|
85 |
-
epoch =
|
86 |
-
train_loss =
|
87 |
-
train_runtime =
|
88 |
-
train_samples =
|
89 |
-
train_samples_per_second =
|
90 |
-
train_steps_per_second =
|
91 |
-
|
92 |
-
[INFO|trainer.py:2929] 2022-
|
93 |
-
[INFO|trainer.py:2931] 2022-
|
94 |
-
[INFO|trainer.py:2934] 2022-
|
95 |
-
100%|██████████|
|
96 |
-
[INFO|modelcard.py:449] 2022-
|
97 |
-
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'metrics': [{'name': 'Accuracy', 'type': 'accuracy', 'value': 0.
|
98 |
***** eval metrics *****
|
99 |
-
epoch =
|
100 |
-
eval_accuracy = 0.
|
101 |
-
eval_loss =
|
102 |
-
eval_runtime = 0:00:03.
|
103 |
-
eval_samples =
|
104 |
-
eval_samples_per_second =
|
105 |
-
eval_steps_per_second = 3.
|
106 |
-
perplexity =
|
107 |
|
108 |
```
|
|
|
65 |
|
66 |
bpe分词:"vocab_size"=50000
|
67 |
```
|
68 |
+
[INFO|trainer.py:1608] 2022-11-30 12:51:36,357 >> ***** Running training *****
|
69 |
+
[INFO|trainer.py:1609] 2022-11-30 12:51:36,357 >> Num examples = 260926
|
70 |
+
[INFO|trainer.py:1610] 2022-11-30 12:51:36,357 >> Num Epochs = 81
|
71 |
+
[INFO|trainer.py:1611] 2022-11-30 12:51:36,357 >> Instantaneous batch size per device = 96
|
72 |
+
[INFO|trainer.py:1612] 2022-11-30 12:51:36,357 >> Total train batch size (w. parallel, distributed & accumulation) = 96
|
73 |
+
[INFO|trainer.py:1613] 2022-11-30 12:51:36,357 >> Gradient Accumulation steps = 1
|
74 |
+
[INFO|trainer.py:1614] 2022-11-30 12:51:36,357 >> Total optimization steps = 220158
|
75 |
+
[INFO|trainer.py:1616] 2022-11-30 12:51:36,358 >> Number of trainable parameters = 124439808
|
76 |
+
|
77 |
+
{'loss': 6.1104, 'learning_rate': 4.9888034956712906e-05, 'epoch': 0.18}
|
78 |
+
{'loss': 5.5855, 'learning_rate': 4.977448014607691e-05, 'epoch': 0.37}
|
79 |
+
{'loss': 5.3264, 'learning_rate': 4.966092533544091e-05, 'epoch': 0.55}
|
80 |
......
|
81 |
......
|
82 |
......
|
83 |
+
{'loss': 2.8539, 'learning_rate': 5.677740531799889e-08, 'epoch': 80.94}
|
84 |
+
{'train_runtime': 146835.0563, 'train_samples_per_second': 143.937, 'train_steps_per_second': 1.499, 'train_loss': 3.1762605669072217, 'epoch': 81.0}
|
85 |
***** train metrics *****
|
86 |
+
epoch = 81.0
|
87 |
+
train_loss = 3.1763
|
88 |
+
train_runtime = 1 day, 16:47:15.05
|
89 |
+
train_samples = 260926
|
90 |
+
train_samples_per_second = 143.937
|
91 |
+
train_steps_per_second = 1.499
|
92 |
+
12/02/2022 05:38:54 - INFO - __main__ - *** Evaluate ***
|
93 |
+
[INFO|trainer.py:2929] 2022-12-02 05:38:54,688 >> ***** Running Evaluation *****
|
94 |
+
[INFO|trainer.py:2931] 2022-12-02 05:38:54,688 >> Num examples = 1350
|
95 |
+
[INFO|trainer.py:2934] 2022-12-02 05:38:54,688 >> Batch size = 96
|
96 |
+
100%|██████████| 15/15 [00:03<00:00, 4.20it/s]
|
97 |
+
[INFO|modelcard.py:449] 2022-12-02 05:38:59,875 >> Dropping the following result as it does not have all the necessary fields:
|
98 |
+
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'metrics': [{'name': 'Accuracy', 'type': 'accuracy', 'value': 0.4447501469723692}]}
|
99 |
***** eval metrics *****
|
100 |
+
epoch = 81.0
|
101 |
+
eval_accuracy = 0.4448
|
102 |
+
eval_loss = 3.2813
|
103 |
+
eval_runtime = 0:00:03.86
|
104 |
+
eval_samples = 1350
|
105 |
+
eval_samples_per_second = 349.505
|
106 |
+
eval_steps_per_second = 3.883
|
107 |
+
perplexity = 26.6108
|
108 |
|
109 |
```
|