Upload folder using huggingface_hub

checkpoint-1446/config.json

@@ -0,0 +1,28 @@
+{
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-1446/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b57f8dc201dbaf66b2fdde409c5767e708c9de901321079a93f7769e293409
+size 2239618672

checkpoint-1446/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc76461b84da41cd5b92e0e2c65d50adad78ada568aed4b322d0cc37e3f4cb4
+size 4479472785

checkpoint-1446/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5386d4e9581c88162595d562aa5edcda8532a891a4b8e6347bbc40188e0d7f1b
+size 14244

checkpoint-1446/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a019bdd016d1c7db514c3f8a96aeb0c1c2668e4eadbc201284604ce5fafc9783
+size 1064

checkpoint-1446/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_global_step": 1446,
+  "best_metric": 0.5801101922988892,
+  "best_model_checkpoint": "/content/drive/MyDrive/modeling/checkpoint-1446",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 1446,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 17.5683536529541,
+      "learning_rate": 4.501037344398341e-06,
+      "loss": 0.694,
+      "step": 482
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.569055036344756,
+      "eval_f1": 0.6687948922585794,
+      "eval_loss": 0.6698787808418274,
+      "eval_precision": 0.5491480996068152,
+      "eval_recall": 0.8551020408163266,
+      "eval_runtime": 20.8749,
+      "eval_samples_per_second": 46.132,
+      "eval_steps_per_second": 2.922,
+      "step": 482
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 17.880165100097656,
+      "learning_rate": 4.001037344398341e-06,
+      "loss": 0.6326,
+      "step": 964
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6656282450674974,
+      "eval_f1": 0.7238421955403087,
+      "eval_loss": 0.6021382808685303,
+      "eval_precision": 0.6242603550295858,
+      "eval_recall": 0.8612244897959184,
+      "eval_runtime": 20.6115,
+      "eval_samples_per_second": 46.722,
+      "eval_steps_per_second": 2.96,
+      "step": 964
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 16.805747985839844,
+      "learning_rate": 3.5010373443983405e-06,
+      "loss": 0.5468,
+      "step": 1446
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6998961578400831,
+      "eval_f1": 0.7336405529953917,
+      "eval_loss": 0.5801101922988892,
+      "eval_precision": 0.66890756302521,
+      "eval_recall": 0.8122448979591836,
+      "eval_runtime": 20.6212,
+      "eval_samples_per_second": 46.699,
+      "eval_steps_per_second": 2.958,
+      "step": 1446
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4820,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.153600187514675e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1446/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b218aed1063e5eeb248859642ce46dc3690005cfad8237930658fa19f80c47d6
+size 5240

config.json

@@ -0,0 +1,28 @@
+{
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

events.out.tfevents.1750251155.25e773d0c2b3.1041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771c647ede9c4e68eea0917c0faa9070e113a0d0529304073d55a112f4e0d2ac
+size 4966

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b57f8dc201dbaf66b2fdde409c5767e708c9de901321079a93f7769e293409
+size 2239618672

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b218aed1063e5eeb248859642ce46dc3690005cfad8237930658fa19f80c47d6
+size 5240