Training in progress epoch 0

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.8951
-- Train Accuracy: 0.0451
-- Validation Loss: 4.3546
-- Validation Accuracy: 0.0447
-- Epoch: 9
+- Train Loss: 7.1912
+- Train Accuracy: 0.0424
+- Validation Loss: 5.8111
+- Validation Accuracy: 0.0344
+- Epoch: 0
 
 ## Model description
 
@@ -37,23 +37,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 125, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, '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}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 125, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, '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 | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 4.1322     | 0.0446         | 4.3546          | 0.0447              | 0     |
-| 3.8960     | 0.0449         | 4.3546          | 0.0447              | 1     |
-| 3.8963     | 0.0451         | 4.3546          | 0.0447              | 2     |
-| 3.8952     | 0.0451         | 4.3546          | 0.0447              | 3     |
-| 3.8945     | 0.0451         | 4.3546          | 0.0447              | 4     |
-| 3.8949     | 0.0451         | 4.3546          | 0.0447              | 5     |
-| 3.8939     | 0.0451         | 4.3546          | 0.0447              | 6     |
-| 3.8947     | 0.0449         | 4.3546          | 0.0447              | 7     |
-| 3.8942     | 0.0449         | 4.3546          | 0.0447              | 8     |
-| 3.8951     | 0.0451         | 4.3546          | 0.0447              | 9     |
+| 7.1912     | 0.0424         | 5.8111          | 0.0344              | 0     |
 
 
 ### Framework versions

config.json

@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
+  "n_ctx": 40,
   "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 sha256:2eeb06cda5e9aece2b9c9129d27bb8e18beb65471d89224d480ceb1e61345134
+oid sha256:6c8c55918c00a2537479d975a796b3a9f3f16d75c340275277e7780e327e9d47
 size 497935464