Fine-tuned model update

checkpoint-6/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "arithmetic",
+    "1": "multiplication",
+    "2": "division",
+    "3": "algebra",
+    "4": "geometry",
+    "5": "exponents"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "algebra": 3,
+    "arithmetic": 0,
+    "division": 2,
+    "exponents": 5,
+    "geometry": 4,
+    "multiplication": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-6/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00622e8cdee09bc9c52000c3ea057bfbb3b38ec90338e57a081ae179be6cc3cf
+size 1112217312

checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800bc7bb32cd75dca077ef971f3dcf5e5dc584fc870a87448aab2989020f5571
+size 2224548602

checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ae460aee1d885b276b898f4f8b9dee77c8b6c7941b7009c1d7d14dd5d118c4
+size 13990

checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a507d9cafa2419d0ab9d8bfd3d73565df3d210c7e1a2b8ba116f25efdab63f1
+size 1064

checkpoint-6/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.7609878778457642,
+      "eval_runtime": 0.4696,
+      "eval_samples_per_second": 8.517,
+      "eval_steps_per_second": 2.129,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.7294942140579224,
+      "eval_runtime": 0.2479,
+      "eval_samples_per_second": 16.136,
+      "eval_steps_per_second": 4.034,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.7482409477233887,
+      "eval_runtime": 0.279,
+      "eval_samples_per_second": 14.335,
+      "eval_steps_per_second": 3.584,
+      "step": 6
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 6,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2170744164864.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598e7344eec6698068461bff781155d74bd9440d68eab071e2ac9d361da8c62d
+size 5240

config.json

@@ -1,45 +1,45 @@
-{
-  "_name_or_path": "D:/sangapac-math-model",
-  "architectures": [
-    "XLMRobertaForSequenceClassification"
-  ],
-  "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,
-  "id2label": {
-    "0": "arithmetic",
-    "1": "multiplication",
-    "2": "division",
-    "3": "algebra",
-    "4": "geometry",
-    "5": "exponents"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "algebra": 3,
-    "arithmetic": 0,
-    "division": 2,
-    "exponents": 5,
-    "geometry": 4,
-    "multiplication": 1
-  },
-  "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",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "arithmetic",
+    "1": "multiplication",
+    "2": "division",
+    "3": "algebra",
+    "4": "geometry",
+    "5": "exponents"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "algebra": 3,
+    "arithmetic": 0,
+    "division": 2,
+    "exponents": 5,
+    "geometry": 4,
+    "multiplication": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e036f125b577ef815ac4dc06a77a1b679cefd365c599e80c6ee3e823c67bb9
+oid sha256:00622e8cdee09bc9c52000c3ea057bfbb3b38ec90338e57a081ae179be6cc3cf
 size 1112217312