Training in progress epoch 0

README.md

@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.6842
-- Validation Loss: 6.0821
-- Epoch: 4
+- Train Loss: 7.3561
+- Validation Loss: 6.5449
+- Epoch: 0
 
 ## Model description
 
@@ -34,18 +34,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0006, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0006, 'decay_steps': 33845, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 700, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 35810, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 700, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 6.9373     | 6.3278          | 0     |
-| 6.1036     | 6.0726          | 1     |
-| 5.8224     | 6.0130          | 2     |
-| 5.6876     | 5.9888          | 3     |
-| 5.6842     | 6.0821          | 4     |
+| 7.3561     | 6.5449          | 0     |
 
 
 ### Framework versions

config.json

@@ -10,7 +10,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 512,
+  "n_ctx": 256,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b5439034e568252566a81598810f99ed11dfca25896bd418ced8bb7d0c942a
+oid sha256:f279d4712d076f33fb9881e3f7fa5de1d76d23c8e951d315b0cd58294f538cc6
 size 451065960

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -18,7 +18,7 @@
     "single_word": false
   },
   "errors": "replace",
-  "max_len": 512,
+  "max_len": 256,
   "name_or_path": "./GPT-2-puisi",
   "pad_token": null,
   "special_tokens_map_file": null,