Training in progress, epoch 5

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b46bd691d875396b025a92c675c94f30deac0146b06596b1cfa7ca72196b624
-size 6364
+oid sha256:2a4ee493419fb38105e2af16ebe63112fd5d657d35e1196ac41bda51811426cb
+size 6844

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcfbb6a469efab87eedd1dab11d0be6b631b57226a6e11894b92f41a1c26df7
+oid sha256:895d79e3b2fe73c63a4aba79ac07dbc3bd3f6f05fdab7bcef31f3b7c73fcb33a
 size 17549312

run-4/checkpoint-605/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-605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895d79e3b2fe73c63a4aba79ac07dbc3bd3f6f05fdab7bcef31f3b7c73fcb33a
+size 17549312

run-4/checkpoint-605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54864eb0ce9faaf92a75ebdec2d046c0b7b8798a33040e080c2b12040e5a54c9
+size 35123898

run-4/checkpoint-605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8118854752a1ec21f28c87a05813d1c425eb3cb9564cd451d69a2e71f89d6a84
+size 14308

run-4/checkpoint-605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78951a029617bebd56efe4a2bde6c3849beebe9690ef517f4c21c91e2e3f614
+size 1064

run-4/checkpoint-605/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-605/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-605/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.7580645161290323,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-4\\checkpoint-605",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 605,
+  "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
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.233492032525934e-05,
+      "loss": 0.304,
+      "step": 484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7554630593132154,
+      "eval_loss": 0.33476221561431885,
+      "eval_runtime": 5.3945,
+      "eval_samples_per_second": 356.288,
+      "eval_steps_per_second": 2.966,
+      "step": 484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.8223280216839555e-05,
+      "loss": 0.2946,
+      "step": 605
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7580645161290323,
+      "eval_loss": 0.33405163884162903,
+      "eval_runtime": 5.3765,
+      "eval_samples_per_second": 357.48,
+      "eval_steps_per_second": 2.976,
+      "step": 605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 13731632367600.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.543866580390613,
+    "learning_rate": 0.00016878148075893845,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-4/checkpoint-605/training_args.bin

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