End of training

README.md

@@ -1,56 +1,62 @@
----
-license: apache-2.0
-base_model: distilroberta-base
-tags:
-- generated_from_trainer
-datasets:
-- eli5_category
-model-index:
-- name: 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. -->
-
-# my_awesome_eli5_mlm_model
-
-This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the eli5_category dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.0195
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### 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
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.36.1
-- Pytorch 2.7.1+cu128
-- Datasets 3.2.0
-- Tokenizers 0.15.2
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilroberta-base
+tags:
+- generated_from_trainer
+datasets:
+- eli5_category
+model-index:
+- name: 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. -->
+
+# my_awesome_eli5_mlm_model
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the eli5_category dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9992
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.2552        | 1.0   | 1299 | 2.0395          |
+| 2.1823        | 2.0   | 2598 | 2.0380          |
+| 2.1545        | 3.0   | 3897 | 2.0091          |
+
+
+### Framework versions
+
+- Transformers 4.52.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -1,27 +1,26 @@
-{
-  "_name_or_path": "distilroberta-base",
-  "architectures": [
-    "RobertaForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5c880fe3cc8007307ec62e6b58152d74a9d543e30fcd76a8f3295a6c024b4b
+oid sha256:841344aa838454b0616a21cb798300a460dcbc625429d6ce6736e64589466038
 size 328693404

runs/Jun06_12-43-08_dc85121ec65a/events.out.tfevents.1749213797.dc85121ec65a.1802.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873fd4dbd57aa60f0a6c9ef97092aa10a35c78a2da483828d45a4cd70e8eb833
-size 6966
+oid sha256:19e7bb55523b37dd3ff13f76c9bde9ff6430f95698720bd2a74c7927e89a3471
+size 7591

runs/Jun06_12-43-08_dc85121ec65a/events.out.tfevents.1749215944.dc85121ec65a.1802.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1700b91561702a16138ada73d6cf1adf84f85bcce5dabe6804fee5aa342b7f81
+size 359

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>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0b3eec019a621f3eff1b01ddcab15df20289bbd20dd70205c6090ecacea17a
-size 5137
+oid sha256:fe083d9e6b74a2ae1f2b7a974d7801ea506eac008641c081c97b9cc4192d9a5e
+size 5304