Training in progress epoch 0

README.md

@@ -1,20 +1,22 @@
 ---
 license: apache-2.0
 tags:
-- generated_from_trainer
+- generated_from_keras_callback
 model-index:
-- name: my_awesome_eli5_clm-model
+- name: frogwang2000/my_awesome_eli5_clm-model
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
 
-# my_awesome_eli5_clm-model
+# frogwang2000/my_awesome_eli5_clm-model
 
-This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.7368
+- Train Loss: 3.9097
+- Validation Loss: 3.7588
+- Epoch: 0
 
 ## Model description
 
@@ -33,26 +35,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3.0
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.8739        | 1.0   | 1130 | 3.7567          |
-| 3.7727        | 2.0   | 2260 | 3.7388          |
-| 3.7302        | 3.0   | 3390 | 3.7368          |
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.9097     | 3.7588          | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.28.1
-- Pytorch 2.0.0+cpu
+- TensorFlow 2.12.0
 - Datasets 2.11.0
 - Tokenizers 0.13.3

config.json

@@ -39,7 +39,6 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float32",
   "transformers_version": "4.28.1",
   "use_cache": true,
   "vocab_size": 50257

runs/May29_18-02-00_centos8.hardware/events.out.tfevents.1685354525.centos8.hardware.2496361.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5241c2be1dcd0a38c05345444804fad34a151b1ae336fc442144db68953873b2
-size 5872
+oid sha256:bab8eec76c55eeba6543d9f4da75489fcc41dd6ca6c42fa7fd03f1d8986ba7e7
+size 6497

runs/May29_18-02-00_centos8.hardware/events.out.tfevents.1685357525.centos8.hardware.2496361.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2c8344489cbe09ba9d787159f6a04cb05262096910d5751dfa0b3d8c2c1c0b
+size 359

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93336ac93f1e55867bf864c29888dc50c0ec6cc1cf8b61bd37501cc97b553ab
+size 327745496

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}