Upload 6 files

text_model/checkpoint-3390/config.json

@@ -0,0 +1,40 @@
+{
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

text_model/checkpoint-3390/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f24f5364acfc5d87ebb0a3c5fcc469d28c484c7e83d040bcd06128d0806f2c
+size 14645

text_model/checkpoint-3390/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620f6518a6822e6069d190f7216c1c8d8395eaf4764f38a30b7e7b53a9b0178a
+size 1383

text_model/checkpoint-3390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f984e843285daed226a34f377b0bb79290e7781134bd15d3520e9312df6d19
+size 1465

text_model/checkpoint-3390/trainer_state.json

@@ -0,0 +1,266 @@
+{
+  "best_global_step": 2712,
+  "best_metric": 0.8775633088032715,
+  "best_model_checkpoint": "/content/drive/MyDrive/pbl_6/text_violation/output_phobert_final/checkpoint-2712",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 3390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5908419497784343,
+      "grad_norm": 8.066655158996582,
+      "learning_rate": 1.88259587020649e-05,
+      "loss": 1.0146,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7455686853766618,
+      "eval_f1": 0.7480569004890223,
+      "eval_loss": 0.6535171866416931,
+      "eval_precision": 0.7438951273666146,
+      "eval_recall": 0.7635212365766714,
+      "eval_runtime": 4.1402,
+      "eval_samples_per_second": 654.079,
+      "eval_steps_per_second": 10.386,
+      "step": 339
+    },
+    {
+      "epoch": 1.1802067946824224,
+      "grad_norm": 8.033791542053223,
+      "learning_rate": 1.7646017699115045e-05,
+      "loss": 0.7183,
+      "step": 400
+    },
+    {
+      "epoch": 1.7710487444608567,
+      "grad_norm": 7.553318500518799,
+      "learning_rate": 1.6466076696165194e-05,
+      "loss": 0.5841,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7961595273264401,
+      "eval_f1": 0.8004633351993021,
+      "eval_loss": 0.5103763341903687,
+      "eval_precision": 0.7954926941267795,
+      "eval_recall": 0.8145635466866111,
+      "eval_runtime": 4.2164,
+      "eval_samples_per_second": 642.252,
+      "eval_steps_per_second": 10.198,
+      "step": 678
+    },
+    {
+      "epoch": 2.360413589364845,
+      "grad_norm": 11.982539176940918,
+      "learning_rate": 1.528613569321534e-05,
+      "loss": 0.4924,
+      "step": 800
+    },
+    {
+      "epoch": 2.951255539143279,
+      "grad_norm": 10.420658111572266,
+      "learning_rate": 1.410619469026549e-05,
+      "loss": 0.4396,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8319793205317577,
+      "eval_f1": 0.839237623407653,
+      "eval_loss": 0.43686869740486145,
+      "eval_precision": 0.8322550154197035,
+      "eval_recall": 0.8486163782995474,
+      "eval_runtime": 4.2136,
+      "eval_samples_per_second": 642.679,
+      "eval_steps_per_second": 10.205,
+      "step": 1017
+    },
+    {
+      "epoch": 3.5406203840472674,
+      "grad_norm": 13.99537181854248,
+      "learning_rate": 1.2926253687315635e-05,
+      "loss": 0.3559,
+      "step": 1200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8545051698670606,
+      "eval_f1": 0.8630242724646225,
+      "eval_loss": 0.40422186255455017,
+      "eval_precision": 0.8628044809228071,
+      "eval_recall": 0.8634142412515072,
+      "eval_runtime": 4.206,
+      "eval_samples_per_second": 643.836,
+      "eval_steps_per_second": 10.223,
+      "step": 1356
+    },
+    {
+      "epoch": 4.129985228951256,
+      "grad_norm": 14.122424125671387,
+      "learning_rate": 1.1746312684365783e-05,
+      "loss": 0.3394,
+      "step": 1400
+    },
+    {
+      "epoch": 4.72082717872969,
+      "grad_norm": 10.866605758666992,
+      "learning_rate": 1.056637168141593e-05,
+      "loss": 0.2889,
+      "step": 1600
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8441654357459379,
+      "eval_f1": 0.8517152790349632,
+      "eval_loss": 0.4265260100364685,
+      "eval_precision": 0.8441186724361562,
+      "eval_recall": 0.8647582579749038,
+      "eval_runtime": 4.1986,
+      "eval_samples_per_second": 644.981,
+      "eval_steps_per_second": 10.242,
+      "step": 1695
+    },
+    {
+      "epoch": 5.310192023633678,
+      "grad_norm": 5.72359561920166,
+      "learning_rate": 9.386430678466077e-06,
+      "loss": 0.2514,
+      "step": 1800
+    },
+    {
+      "epoch": 5.901033973412112,
+      "grad_norm": 9.600533485412598,
+      "learning_rate": 8.206489675516224e-06,
+      "loss": 0.2464,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8626292466765141,
+      "eval_f1": 0.8702889928876043,
+      "eval_loss": 0.389065682888031,
+      "eval_precision": 0.8652231358736173,
+      "eval_recall": 0.8783380417030334,
+      "eval_runtime": 4.2127,
+      "eval_samples_per_second": 642.817,
+      "eval_steps_per_second": 10.207,
+      "step": 2034
+    },
+    {
+      "epoch": 6.4903988183161,
+      "grad_norm": 17.138826370239258,
+      "learning_rate": 7.026548672566372e-06,
+      "loss": 0.211,
+      "step": 2200
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8674298375184638,
+      "eval_f1": 0.8754706796586051,
+      "eval_loss": 0.39963972568511963,
+      "eval_precision": 0.8702205064128979,
+      "eval_recall": 0.8830179653015887,
+      "eval_runtime": 4.256,
+      "eval_samples_per_second": 636.271,
+      "eval_steps_per_second": 10.103,
+      "step": 2373
+    },
+    {
+      "epoch": 7.079763663220088,
+      "grad_norm": 6.464990615844727,
+      "learning_rate": 5.8466076696165195e-06,
+      "loss": 0.1979,
+      "step": 2400
+    },
+    {
+      "epoch": 7.670605612998523,
+      "grad_norm": 9.935137748718262,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1781,
+      "step": 2600
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8707533234859675,
+      "eval_f1": 0.8775633088032715,
+      "eval_loss": 0.4202274978160858,
+      "eval_precision": 0.8721032179023319,
+      "eval_recall": 0.8847283016982879,
+      "eval_runtime": 4.21,
+      "eval_samples_per_second": 643.232,
+      "eval_steps_per_second": 10.214,
+      "step": 2712
+    },
+    {
+      "epoch": 8.259970457902511,
+      "grad_norm": 9.050063133239746,
+      "learning_rate": 3.4867256637168144e-06,
+      "loss": 0.1651,
+      "step": 2800
+    },
+    {
+      "epoch": 8.850812407680944,
+      "grad_norm": 11.100234985351562,
+      "learning_rate": 2.306784660766962e-06,
+      "loss": 0.1541,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.869645494830133,
+      "eval_f1": 0.877165841562759,
+      "eval_loss": 0.4208575487136841,
+      "eval_precision": 0.8718772232277948,
+      "eval_recall": 0.8837444901736863,
+      "eval_runtime": 4.2122,
+      "eval_samples_per_second": 642.888,
+      "eval_steps_per_second": 10.208,
+      "step": 3051
+    },
+    {
+      "epoch": 9.440177252584933,
+      "grad_norm": 9.718356132507324,
+      "learning_rate": 1.1268436578171092e-06,
+      "loss": 0.1452,
+      "step": 3200
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8670605612998523,
+      "eval_f1": 0.8750774553354714,
+      "eval_loss": 0.4245568513870239,
+      "eval_precision": 0.8694463928962631,
+      "eval_recall": 0.8819628066777028,
+      "eval_runtime": 4.2399,
+      "eval_samples_per_second": 638.697,
+      "eval_steps_per_second": 10.142,
+      "step": 3390
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 3390,
+  "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": 1.42477194921984e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

text_model/checkpoint-3390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac51c57e06a52a75b974c3c2c4b8757518ef7f4880695f487451f5a439715840
+size 5841