Training in progress, epoch 3

logs/events.out.tfevents.1702113279.joseph_legion.21152.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117f8137fe0d9dc61f338f6c6a862425bcfe688fc6ac685ac3cc05e97bf97331
-size 5404
+oid sha256:1e0f7367e7b235db69f47c32e9002507aa6884b2e66e8b9f6dcd2a3164675a44
+size 5884

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc8ac5b0a7f05307c65e11613f0fd1cdc8ec91f4140880345e719631a1e86d7
+oid sha256:19fbac7b44c0b00e171c766cc9543f71040b3aa10dd5b00dc0de71a5eef5d354
 size 17549312

run-4/checkpoint-363/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-363/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fbac7b44c0b00e171c766cc9543f71040b3aa10dd5b00dc0de71a5eef5d354
+size 17549312

run-4/checkpoint-363/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47d2817b954a8510c0c8a9fd0939d571bbc51c185b00e28d2c7bea1c4853d4f
+size 35123898

run-4/checkpoint-363/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7915dd38af4270aefc78e183c118c69b6f8d50285ff32709d8aff7d88a6ead2a
+size 14308

run-4/checkpoint-363/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc8a9f5c75c1f3ac850cfe4b897deb68153bfd0dfa084fb75ec43477f690c16
+size 1064

run-4/checkpoint-363/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-4/checkpoint-363/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-363/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7554630593132154,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-4\\checkpoint-363",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 363,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00014466984065051867,
+      "loss": 0.3523,
+      "step": 121
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7346514047866806,
+      "eval_loss": 0.3383758068084717,
+      "eval_runtime": 5.3759,
+      "eval_samples_per_second": 357.519,
+      "eval_steps_per_second": 2.976,
+      "step": 121
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001205582005420989,
+      "loss": 0.3282,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7544224765868887,
+      "eval_loss": 0.33105042576789856,
+      "eval_runtime": 5.4179,
+      "eval_samples_per_second": 354.751,
+      "eval_steps_per_second": 2.953,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.644656043367911e-05,
+      "loss": 0.3153,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7554630593132154,
+      "eval_loss": 0.33135876059532166,
+      "eval_runtime": 5.3821,
+      "eval_samples_per_second": 357.112,
+      "eval_steps_per_second": 2.973,
+      "step": 363
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 8247964642380.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.543866580390613,
+    "learning_rate": 0.00016878148075893845,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-4/checkpoint-363/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ff081b3a6ff2508f06d2f68c32f682d03896bb152914dd2b16bfe1092b0639
+size 4792