Training in progress epoch 0

README.md

@@ -1,18 +1,22 @@
 ---
 license: apache-2.0
 tags:
-- generated_from_trainer
+- generated_from_keras_callback
 model-index:
-- name: my_awesome_eli5_mlm_model
+- name: zdaniar/my_awesome_eli5_mlm_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_mlm_model
+# zdaniar/my_awesome_eli5_mlm_model
 
-This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.0455
+- Validation Loss: 1.8457
+- Epoch: 0
 
 ## Model description
 
@@ -31,17 +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
+- 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
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 2.0455     | 1.8457          | 0     |
+
 
 ### Framework versions
 
 - Transformers 4.26.1
-- Pytorch 1.13.1+cu116
+- TensorFlow 2.11.0
 - Datasets 2.10.1
 - Tokenizers 0.13.2

config.json

@@ -19,7 +19,6 @@
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "type_vocab_size": 1,
   "use_cache": true,

runs/Mar09_10-26-04_84cc66ed7119/events.out.tfevents.1678357570.84cc66ed7119.125.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb173a36a72e09224223a4eebe9b9270afc9fbe58352b331391a9c584762c59e
-size 40
+oid sha256:436b20e3cab687e527c9f3d5b7865763e6b177ecf2f8391312b4f157d9025f56
+size 3840

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc86138eaa01945922003b5fbcee1fe0f900da151fed1775fc627a0992969d6
+size 484838716

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "distilroberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}