Training in progress, epoch 1, checkpoint

checkpoint-93/config.json

@@ -0,0 +1,37 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "valid",
+    "1": "fallacy"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "fallacy": 1,
+    "valid": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-93/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9417637f220f7d7e9131faaafe8afadfd176e605a3fae55f974c77abbe1006
+size 1421495416

checkpoint-93/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a127003bf1811532c61e82d4030d89bc637db5966a849fbbda333b248301e6ee
+size 2843229182

checkpoint-93/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b203ea65fc89cb813eab0e94850c884f421255fe06426c04648c2135dfa5385f
+size 14645

checkpoint-93/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924e9b9a07012819b7c3130d69619c81a2b4d9fc6a0af9970f7883eff3ed23f7
+size 1383

checkpoint-93/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1509f821eeec3d1883e4c8feb1c9a82904e7b01ad278fdb204cbc4aebc86cbb0
+size 1465

checkpoint-93/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-93/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_global_step": 93,
+  "best_metric": 0.7275834596900619,
+  "best_model_checkpoint": "models/roberta-large-touche-enhanced-binary/trainer/checkpoint-93",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 16.532739639282227,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 1.553863525390625,
+      "step": 10
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 24.55632209777832,
+      "learning_rate": 1.3571428571428574e-05,
+      "loss": 1.414971923828125,
+      "step": 20
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 7.70368766784668,
+      "learning_rate": 1.9920318725099602e-05,
+      "loss": 1.493170166015625,
+      "step": 30
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 9.611059188842773,
+      "learning_rate": 1.912350597609562e-05,
+      "loss": 1.4590301513671875,
+      "step": 40
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 12.690634727478027,
+      "learning_rate": 1.8326693227091633e-05,
+      "loss": 1.412310791015625,
+      "step": 50
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 13.649928092956543,
+      "learning_rate": 1.752988047808765e-05,
+      "loss": 1.3273170471191407,
+      "step": 60
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 22.00589942932129,
+      "learning_rate": 1.6733067729083667e-05,
+      "loss": 1.3404205322265625,
+      "step": 70
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 29.264972686767578,
+      "learning_rate": 1.593625498007968e-05,
+      "loss": 1.4568191528320313,
+      "step": 80
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 22.74860954284668,
+      "learning_rate": 1.5139442231075698e-05,
+      "loss": 1.1942962646484374,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.735,
+      "eval_fallacy_f1": 0.7725321888412017,
+      "eval_loss": 0.543099045753479,
+      "eval_macro_f1": 0.7275834596900619,
+      "eval_runtime": 2.291,
+      "eval_samples_per_second": 87.297,
+      "eval_steps_per_second": 5.674,
+      "step": 93
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 279,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 265021621803288.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-93/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289286e71a74df77914c3392f4d411e1b3deb53c0130d083ae87d9aa1cdd507f
+size 5457