Initial upload (auto-create if missing)

config.json

@@ -0,0 +1,51 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "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
+  },
+  "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": "multi_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e130578137cdfd9c78b1b0d07c248770c3233a1b7c9291ada946ae76f71f641
+size 1112223440

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11a8cbfc80e92a7d61892f3f029bc485181e2ea2d1b90a3143f98b99dee49ae
+size 2224569739

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8442066dd32c5fa083dff7be8149d4e86b522c35735f4d8deb4857134218be
+size 14709

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e442c261bc5b6ce5ea227e3938bfaea8bd8bad0740e825bb47c708db1da267cb
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ceebe97b4c8ae58240ea469d358c99af23273b2567d63272003748f87225d6c
+size 1465

trainer_state.json

@@ -0,0 +1,224 @@
+{
+  "best_global_step": 3580,
+  "best_metric": 0.9048878669310181,
+  "best_model_checkpoint": "../models/checkpoint-3580",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 3580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 13.927672386169434,
+      "learning_rate": 1.8005586592178773e-05,
+      "loss": 0.4010912506274005,
+      "step": 358
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1_macro": 0.6710618348718376,
+      "eval_f1_micro": 0.6837422485845241,
+      "eval_loss": 0.2920529246330261,
+      "eval_precision": 0.7507400828892836,
+      "eval_recall": 0.6277227722772277,
+      "eval_runtime": 10.5624,
+      "eval_samples_per_second": 131.882,
+      "eval_steps_per_second": 8.331,
+      "step": 358
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.783374309539795,
+      "learning_rate": 1.600558659217877e-05,
+      "loss": 0.2375833735119697,
+      "step": 716
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1_macro": 0.7938948225039975,
+      "eval_f1_micro": 0.7958968963703315,
+      "eval_loss": 0.1952921748161316,
+      "eval_precision": 0.8490460157126823,
+      "eval_recall": 0.749009900990099,
+      "eval_runtime": 10.5904,
+      "eval_samples_per_second": 131.534,
+      "eval_steps_per_second": 8.309,
+      "step": 716
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.0740878582000732,
+      "learning_rate": 1.4005586592178772e-05,
+      "loss": 0.16542356906656447,
+      "step": 1074
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1_macro": 0.8565937431886845,
+      "eval_f1_micro": 0.8570709612481128,
+      "eval_loss": 0.15338946878910065,
+      "eval_precision": 0.8715455475946776,
+      "eval_recall": 0.843069306930693,
+      "eval_runtime": 10.5905,
+      "eval_samples_per_second": 131.533,
+      "eval_steps_per_second": 8.309,
+      "step": 1074
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.07139253616333,
+      "learning_rate": 1.2005586592178773e-05,
+      "loss": 0.12163071659024201,
+      "step": 1432
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1_macro": 0.8791528524021864,
+      "eval_f1_micro": 0.8796576032225579,
+      "eval_loss": 0.13414326310157776,
+      "eval_precision": 0.8949795081967213,
+      "eval_recall": 0.8648514851485148,
+      "eval_runtime": 10.5851,
+      "eval_samples_per_second": 131.601,
+      "eval_steps_per_second": 8.314,
+      "step": 1432
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.252202987670898,
+      "learning_rate": 1.0005586592178771e-05,
+      "loss": 0.09038887876372098,
+      "step": 1790
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1_macro": 0.8942549448597952,
+      "eval_f1_micro": 0.8939018344075359,
+      "eval_loss": 0.12078466266393661,
+      "eval_precision": 0.8952333664349553,
+      "eval_recall": 0.8925742574257426,
+      "eval_runtime": 10.5971,
+      "eval_samples_per_second": 131.451,
+      "eval_steps_per_second": 8.304,
+      "step": 1790
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.7471844553947449,
+      "learning_rate": 8.005586592178772e-06,
+      "loss": 0.07169087905457566,
+      "step": 2148
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1_macro": 0.89416078614729,
+      "eval_f1_micro": 0.8939319190922546,
+      "eval_loss": 0.12150303274393082,
+      "eval_precision": 0.8908554572271387,
+      "eval_recall": 0.897029702970297,
+      "eval_runtime": 10.5789,
+      "eval_samples_per_second": 131.677,
+      "eval_steps_per_second": 8.318,
+      "step": 2148
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 10.221022605895996,
+      "learning_rate": 6.005586592178772e-06,
+      "loss": 0.0587206899120821,
+      "step": 2506
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1_macro": 0.8976220026825383,
+      "eval_f1_micro": 0.8966528218910335,
+      "eval_loss": 0.12085035443305969,
+      "eval_precision": 0.8851905451037144,
+      "eval_recall": 0.9084158415841584,
+      "eval_runtime": 10.5927,
+      "eval_samples_per_second": 131.506,
+      "eval_steps_per_second": 8.308,
+      "step": 2506
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.19410130381584167,
+      "learning_rate": 4.005586592178771e-06,
+      "loss": 0.048420543777210084,
+      "step": 2864
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1_macro": 0.9033916836789936,
+      "eval_f1_micro": 0.902893575282001,
+      "eval_loss": 0.11863750964403152,
+      "eval_precision": 0.8945578231292517,
+      "eval_recall": 0.9113861386138614,
+      "eval_runtime": 10.5889,
+      "eval_samples_per_second": 131.553,
+      "eval_steps_per_second": 8.311,
+      "step": 2864
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.716332197189331,
+      "learning_rate": 2.0055865921787714e-06,
+      "loss": 0.041742356795838424,
+      "step": 3222
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1_macro": 0.8996560535399232,
+      "eval_f1_micro": 0.8987775061124694,
+      "eval_loss": 0.1197083443403244,
+      "eval_precision": 0.8879227053140096,
+      "eval_recall": 0.9099009900990099,
+      "eval_runtime": 10.5879,
+      "eval_samples_per_second": 131.565,
+      "eval_steps_per_second": 8.311,
+      "step": 3222
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.6163859367370605,
+      "learning_rate": 5.5865921787709494e-09,
+      "loss": 0.03748961933498276,
+      "step": 3580
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1_macro": 0.9048878669310181,
+      "eval_f1_micro": 0.9043775984348251,
+      "eval_loss": 0.11842884868383408,
+      "eval_precision": 0.8936684388593523,
+      "eval_recall": 0.9153465346534654,
+      "eval_runtime": 10.5754,
+      "eval_samples_per_second": 131.72,
+      "eval_steps_per_second": 8.321,
+      "step": 3580
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3580,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1.503497561751552e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86879ae6379dd533799d5eab4de7008e22ef8b7eba1b79e73c59f549589653ff
+size 5201