Added code-switch Model

checkpoint-50/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-50/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8377ce3b2e2497d8353482904b50a140a2b8796d1f9e97bb5ad23ee7c61e6176
+size 1113205088

checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83bebab5fca41af8e6a4127fd4ee8743249d1f096facc09b358d98df453d84c
+size 2226530490

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b5ab3cb131ee60f9a31d7c40e56e8c52d5e2de7aeb488cc8af3978ff3dbb15
+size 14244

checkpoint-50/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fc8047d95fa1e65abe4f08c289db750f33d2cf801b0ece6e4674c2299a8266
+size 988

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06fe4625c3f9e00f3ef848a00bced3d204423e7990e7a9562e9bb5dc90a83062
+size 1064

checkpoint-50/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.571428571428571,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.9124679565429688,
+      "eval_runtime": 0.3353,
+      "eval_samples_per_second": 125.248,
+      "eval_steps_per_second": 17.893,
+      "step": 11
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.9891194105148315,
+      "eval_runtime": 0.3515,
+      "eval_samples_per_second": 119.495,
+      "eval_steps_per_second": 17.071,
+      "step": 22
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.025794506072998,
+      "eval_runtime": 0.3344,
+      "eval_samples_per_second": 125.594,
+      "eval_steps_per_second": 17.942,
+      "step": 33
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8432807922363281,
+      "eval_runtime": 0.3407,
+      "eval_samples_per_second": 123.271,
+      "eval_steps_per_second": 17.61,
+      "step": 44
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 15370954974720.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81acbe68459ce02ff1d513fb5799f18dc737d1e7d771d8c4ed675c380483501e
+size 5304