Upload folder using huggingface_hub

checkpoint-6615/config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-6615/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3912425710c26ef9e7db531c461704f7e7656c98237274fbc97503f130bbb878
+size 2239647372

checkpoint-6615/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8850d44312cc901270a13ebce4719c8e1e722360ffe866665f81c40b264c3047
+size 4479530129

checkpoint-6615/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be5dda880f013a9e7bce1b3bd88b2a67ddfc352c01d2b2048b15dd905db3302
+size 14244

checkpoint-6615/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1634720f4cb1c92190a049362353c9c8ca2e9c3231f77e44837e95a06679f4b
+size 1064

checkpoint-6615/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 1.2596017122268677,
+  "best_model_checkpoint": "model/checkpoint-6615",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 6615,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 37.24568557739258,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.482,
+      "step": 2205
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5065759637188209,
+      "eval_f1": 0.5016373346532207,
+      "eval_loss": 1.3115675449371338,
+      "eval_precision": 0.5224665615391555,
+      "eval_recall": 0.5065759637188209,
+      "eval_runtime": 59.0262,
+      "eval_samples_per_second": 74.713,
+      "eval_steps_per_second": 4.676,
+      "step": 2205
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 29.510208129882812,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.225,
+      "step": 4410
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5340136054421769,
+      "eval_f1": 0.5207496781913654,
+      "eval_loss": 1.262213945388794,
+      "eval_precision": 0.5372608560773618,
+      "eval_recall": 0.5340136054421769,
+      "eval_runtime": 58.9744,
+      "eval_samples_per_second": 74.778,
+      "eval_steps_per_second": 4.68,
+      "step": 4410
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.824317932128906,
+      "learning_rate": 5e-06,
+      "loss": 1.1182,
+      "step": 6615
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5394557823129251,
+      "eval_f1": 0.5357869320793935,
+      "eval_loss": 1.2596017122268677,
+      "eval_precision": 0.5369446417328734,
+      "eval_recall": 0.5394557823129251,
+      "eval_runtime": 58.9757,
+      "eval_samples_per_second": 74.777,
+      "eval_steps_per_second": 4.68,
+      "step": 6615
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 13230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 4.931897418878976e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6615/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
+size 5240

events.out.tfevents.1734305996.15565a6fdb0d.14799.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60026a51a67f1cd87355d4a35d74e7f092d77e110549e5808328478f692f45f4
+size 9164

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bff3c3206e752f2a4247168df34eee1719863889ad6b645d17c3acc45d58cf0
+oid sha256:3912425710c26ef9e7db531c461704f7e7656c98237274fbc97503f130bbb878
 size 2239647372