End of training

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+base_model: sangjeedondrub/tibetan-roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: dzoQAmodel
+  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. -->
+
+# dzoQAmodel
+
+This model is a fine-tuned version of [sangjeedondrub/tibetan-roberta-base](https://huggingface.co/sangjeedondrub/tibetan-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.1991
+
+## 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: 16
+- eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 1    | 6.1538          |
+| No log        | 2.0   | 2    | 6.1843          |
+| No log        | 3.0   | 3    | 6.1991          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "sangjeedondrub/tibetan-roberta-base",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "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-12,
+  "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": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f00ced42ff4fdcf9c81f9d308c78fbf3dd5357a0cf198ef64a4de5441be5f8e
+size 331459608

runs/May09_15-21-29_d90a564c5046/events.out.tfevents.1715268119.d90a564c5046.8273.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07717cd7752ab8ac739a610cb0fd752935fc79537026ef7350400172f4d6fe71
+size 4704

runs/May09_15-27-24_d90a564c5046/events.out.tfevents.1715268452.d90a564c5046.8273.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887976447afce444be70e5606c90cabeac9f1d45fd0f2322fc5879608d590a74
+size 4704

runs/May09_15-27-24_d90a564c5046/events.out.tfevents.1715268528.d90a564c5046.8273.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faba4493675174ebe37f5a019d1dea0e10c93adae92ac284af3670186f68c7d
+size 4704

runs/May09_15-27-24_d90a564c5046/events.out.tfevents.1715268934.d90a564c5046.8273.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975f0ab58d820875fd12267d638ac23f524700ae2ba1592f1b53475cc60dfa32
+size 4704

runs/May09_15-27-24_d90a564c5046/events.out.tfevents.1715269021.d90a564c5046.8273.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95279cc5a93afbda8fe2d0656a37bc7885da4a24be6b7ddbe2e874d2608a7e51
+size 4704

runs/May09_15-27-24_d90a564c5046/events.out.tfevents.1715269249.d90a564c5046.8273.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2dff601d919534d9d1ece78d112b49f850a452e8fd3551a234b218cf22082f
+size 4704

runs/May09_15-27-24_d90a564c5046/events.out.tfevents.1715269277.d90a564c5046.8273.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde71fbb3a43eb88d85c44ee6790f7f39ebbde943547a5c2f4ebfcbe8fb14cc3
+size 5850

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1ef3d494651c389daa7309593b9ce2c7c968241d3aa13418c0be1964b70696
+size 4984