Upload 8 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/YoutubeTranscriptQADataset/code/models/xlmr_large/checkpoint/checkpoint-20326",
+  "_name_or_path": "xlm-roberta-large",
   "architectures": [
-    "XLMRobertaModel"
+    "XLMRobertaForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -21,7 +21,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.25.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5bab0d1b34214a258ec419ab0def16320b822b8268443632be9914ca5e11a4f
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20540e74f9acba2dfcb5c74ae55ae2230c9f009236818d0bf0dd673106316cea
+size 627

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": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2ffa7deefd76ec48ae60053f8130bb15760ad2aec71316e54c5865b3b2620a
+size 17082925

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_metric": 0.3207553029060364,
+  "best_model_checkpoint": "/content/drive/MyDrive/YoutubeTranscriptQADataset/code/models/xlmr_large/checkpoint/checkpoint-10163",
+  "epoch": 2.0,
+  "global_step": 20326,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.9508019285644e-06,
+      "loss": 1.2245,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.9016038571288e-06,
+      "loss": 0.6119,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.852405785693202e-06,
+      "loss": 0.5168,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.803207714257602e-06,
+      "loss": 0.4754,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.754009642822002e-06,
+      "loss": 0.4414,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.704811571386402e-06,
+      "loss": 0.4249,
+      "step": 3000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.655613499950802e-06,
+      "loss": 0.4322,
+      "step": 3500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.606415428515204e-06,
+      "loss": 0.4398,
+      "step": 4000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.557217357079604e-06,
+      "loss": 0.4151,
+      "step": 4500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.508019285644004e-06,
+      "loss": 0.4015,
+      "step": 5000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.458821214208404e-06,
+      "loss": 0.3581,
+      "step": 5500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.409623142772804e-06,
+      "loss": 0.407,
+      "step": 6000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.360425071337204e-06,
+      "loss": 0.4068,
+      "step": 6500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 9.311226999901604e-06,
+      "loss": 0.3947,
+      "step": 7000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.262028928466004e-06,
+      "loss": 0.3646,
+      "step": 7500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 9.212830857030404e-06,
+      "loss": 0.346,
+      "step": 8000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 9.163632785594806e-06,
+      "loss": 0.3644,
+      "step": 8500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.114434714159206e-06,
+      "loss": 0.3436,
+      "step": 9000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.065236642723606e-06,
+      "loss": 0.3528,
+      "step": 9500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.016038571288006e-06,
+      "loss": 0.3225,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3207553029060364,
+      "eval_runtime": 236.2565,
+      "eval_samples_per_second": 42.661,
+      "eval_steps_per_second": 5.333,
+      "step": 10163
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 8.966840499852406e-06,
+      "loss": 0.28,
+      "step": 10500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.917642428416807e-06,
+      "loss": 0.2658,
+      "step": 11000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.868444356981207e-06,
+      "loss": 0.2642,
+      "step": 11500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 8.819246285545607e-06,
+      "loss": 0.2493,
+      "step": 12000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.770048214110007e-06,
+      "loss": 0.2754,
+      "step": 12500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 8.720850142674407e-06,
+      "loss": 0.2482,
+      "step": 13000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 8.671652071238809e-06,
+      "loss": 0.2614,
+      "step": 13500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 8.622453999803209e-06,
+      "loss": 0.2638,
+      "step": 14000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 8.573255928367609e-06,
+      "loss": 0.2586,
+      "step": 14500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.524057856932009e-06,
+      "loss": 0.2842,
+      "step": 15000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 8.474859785496409e-06,
+      "loss": 0.246,
+      "step": 15500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.42566171406081e-06,
+      "loss": 0.2538,
+      "step": 16000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 8.37646364262521e-06,
+      "loss": 0.2609,
+      "step": 16500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.32726557118961e-06,
+      "loss": 0.2317,
+      "step": 17000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.27806749975401e-06,
+      "loss": 0.2855,
+      "step": 17500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 8.22886942831841e-06,
+      "loss": 0.2564,
+      "step": 18000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 8.17967135688281e-06,
+      "loss": 0.2693,
+      "step": 18500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.130473285447212e-06,
+      "loss": 0.2361,
+      "step": 19000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.081275214011612e-06,
+      "loss": 0.2829,
+      "step": 19500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 8.032077142576012e-06,
+      "loss": 0.2411,
+      "step": 20000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3713413178920746,
+      "eval_runtime": 236.2518,
+      "eval_samples_per_second": 42.662,
+      "eval_steps_per_second": 5.333,
+      "step": 20326
+    }
+  ],
+  "max_steps": 101630,
+  "num_train_epochs": 10,
+  "total_flos": 1.510077569200128e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8886e1a6c82f47a065b0f4835531e066ab90616621063e5695f0db0510ef6fcd
+size 3579