AmalNlal/Aryman_test

README.md

@@ -1,57 +1,59 @@
----
-license: apache-2.0
-base_model: distilbert/distilroberta-base
-tags:
-- generated_from_trainer
-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 [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.7764
-
-## 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: 7e-06
-- train_batch_size: 4
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 1
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.8608        | 1.0   | 6504 | 0.7782          |
-
-
-### Framework versions
-
-- Transformers 4.36.2
-- Pytorch 2.1.2+cu118
-- Datasets 2.16.0
-- Tokenizers 0.15.0
+---
+license: apache-2.0
+base_model: distilbert/distilroberta-base
+tags:
+- generated_from_trainer
+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 [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7455
+
+## 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: 10
+- 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
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9681        | 1.0   | 1037 | 0.8161          |
+| 0.8887        | 2.0   | 2074 | 0.7667          |
+| 0.8486        | 3.0   | 3111 | 0.7455          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -1,27 +1,27 @@
-{
-  "_name_or_path": "distilbert/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": "4.36.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}
+{
+  "_name_or_path": "distilbert/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": "4.40.1",
+  "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 sha256:7ab1d0c022ada85974a76c833812b627f152cb9c2ab277b70f2ee2839482772b
+oid sha256:4494be2805523b1172e1ed3be2e770d76ed05b9fcb5e59b9adae5edc03118150
 size 328693404

runs/May01_17-10-58_a92de6680e74/events.out.tfevents.1714583459.a92de6680e74.3495.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67d41cbe11b2163e98ddfa0cab491856033d914656d001a3deeffa686dbcd2b
+size 4715

runs/May01_17-11-18_a92de6680e74/events.out.tfevents.1714583479.a92de6680e74.3495.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771486e0826022ce1d2791e4de34a908578ea1d0733f43d44a5100c805d757d9
+size 4715

runs/May01_17-11-51_a92de6680e74/events.out.tfevents.1714583511.a92de6680e74.3495.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb57733967c740b7c96a9c7705d674fcfcbe3404437f6aa353d33351fabfb90
+size 4715

runs/May01_17-13-51_a92de6680e74/events.out.tfevents.1714583632.a92de6680e74.3495.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe9e548a5f6084c4b149a7f06b0dc8b3a42246640b41bbb75a93cefeb326b17
+size 4714

runs/May01_17-14-15_a92de6680e74/events.out.tfevents.1714583655.a92de6680e74.3495.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386dad65718acd94d95cd59736384ece90d496cfc92387626e0f474892b03b4a
+size 4714

runs/May01_17-14-40_a92de6680e74/events.out.tfevents.1714583680.a92de6680e74.3495.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1dfa949b66155f698598341a0372432551d542a893f37910c6c682242519460
+size 4714

runs/May01_17-16-10_a92de6680e74/events.out.tfevents.1714583770.a92de6680e74.3495.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea591ee89b442b14d790ccf2bba4a8e4c89ccdd675ec170e09fc216eb7206d42
+size 4714

runs/May01_17-16-54_a92de6680e74/events.out.tfevents.1714583814.a92de6680e74.3495.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb4acb8426972db6ac575972241dc8e905b4606be58f39fb0e79b00c72b2a72
+size 4714

runs/May01_17-18-12_a92de6680e74/events.out.tfevents.1714583892.a92de6680e74.3495.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3332e7bc129ea713b028c7f6d3d18dc71c030e8260099d23c755f018ff5cdd23
+size 7147

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e02d5965902ba53c65fcdb18750eba193415f203be009fae744f8e118f9772
-size 4728
+oid sha256:07c24c669013195c60a5d3068de8c7778b1e2b4e0ee002356bbd82d1d23df8bc
+size 4984