Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,31 @@
+{
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad84c604f1620aef0066b162dd85d8b9a2a69fd10bca6536e2723d7d599aa940
+size 2239618624

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6854b5a821c2812919f5dc7910d081b526f092aebeae861b37c3ceddffde5e7
+size 4479483838

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0be487492a6440856b5e229a4ec6d31eff276a33e1de3ac4e598078aaf4157
+size 14581

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c019e3dc1041ffb9baf39ee4a983e94d339838d5cc0ed6a72ad2ce59f20f7b
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9effc98ff47019959605df1fecacb39fa887f5bd43f67bd93220ad9e150412
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5451f31fe3f899dcd75ec2ad93f415528c9b5f58bb7a5a1c6dd5884fb56257
+size 16781486

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_global_step": 84,
+  "best_metric": 0.7058823529411765,
+  "best_model_checkpoint": "./models/checkpoint-84",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 84,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.581439197063446,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.9031,
+      "eval_samples_per_second": 44.291,
+      "eval_steps_per_second": 2.215,
+      "step": 12
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5537109375,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.5021,
+      "eval_samples_per_second": 79.667,
+      "eval_steps_per_second": 3.983,
+      "step": 24
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5029891729354858,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.2048,
+      "eval_samples_per_second": 195.356,
+      "eval_steps_per_second": 9.768,
+      "step": 36
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6923076923076923,
+      "eval_loss": 0.4609321653842926,
+      "eval_precision": 0.5625,
+      "eval_recall": 0.9,
+      "eval_runtime": 0.2105,
+      "eval_samples_per_second": 190.068,
+      "eval_steps_per_second": 9.503,
+      "step": 48
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.5555555555555556,
+      "eval_loss": 0.39023980498313904,
+      "eval_precision": 0.625,
+      "eval_recall": 0.5,
+      "eval_runtime": 0.1635,
+      "eval_samples_per_second": 244.71,
+      "eval_steps_per_second": 12.236,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.4278203547000885,
+      "eval_precision": 0.75,
+      "eval_recall": 0.6,
+      "eval_runtime": 0.1645,
+      "eval_samples_per_second": 243.13,
+      "eval_steps_per_second": 12.157,
+      "step": 72
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.7058823529411765,
+      "eval_loss": 0.47510337829589844,
+      "eval_precision": 0.8571428571428571,
+      "eval_recall": 0.6,
+      "eval_runtime": 0.1737,
+      "eval_samples_per_second": 230.298,
+      "eval_steps_per_second": 11.515,
+      "step": 84
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 309328405487136.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241ca46dcccdfa2e042590495c1b8d7ec263d8bf58712d16655c63fa466e0209
+size 5201