Training in progress, epoch 4

logs/events.out.tfevents.1702113073.joseph_legion.21152.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26248bf8b9f026f4cd1123a75e36708d721a0d3b36488cf5fc2a645b420eacb4
-size 5883
+oid sha256:2224e63f51997c0f61e84e9614023e42b54e0ff61917893a2f1897e61e18f2de
+size 6717

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd04757f2bcd2959a1fd8dc75d30a254d3c5347f48cb32f59163d3b8e5a8d9c
+oid sha256:5bfc0ef4b11eb782cb2c54385c7a92c139847ccbefac8d0e95f5930c03f3af5e
 size 17549312

run-3/checkpoint-484/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-3/checkpoint-484/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bfc0ef4b11eb782cb2c54385c7a92c139847ccbefac8d0e95f5930c03f3af5e
+size 17549312

run-3/checkpoint-484/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa591ec556e1453a40955d3b382fb604b811ac9d39fb2274fdf38d9b51926296
+size 35123898

run-3/checkpoint-484/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8a3330c813834e4c485b34be4f2caec2b74c220dd9549f784aeeae29566825
+size 14308

run-3/checkpoint-484/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c288db9b97ca78ee4e9891fb0b34490063875a04f536752587413882bb659503
+size 1064

run-3/checkpoint-484/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-3/checkpoint-484/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-3/checkpoint-484/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.7221644120707597,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-3\\checkpoint-484",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 484,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.432859087215925e-05,
+      "loss": 0.6101,
+      "step": 121
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6696149843912591,
+      "eval_loss": 0.5727917551994324,
+      "eval_runtime": 5.4304,
+      "eval_samples_per_second": 353.931,
+      "eval_steps_per_second": 2.946,
+      "step": 121
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.288572724810617e-05,
+      "loss": 0.5466,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7096774193548387,
+      "eval_loss": 0.5379418134689331,
+      "eval_runtime": 5.3325,
+      "eval_samples_per_second": 360.429,
+      "eval_steps_per_second": 3.0,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.1442863624053085e-05,
+      "loss": 0.5163,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7185223725286161,
+      "eval_loss": 0.5288857817649841,
+      "eval_runtime": 5.421,
+      "eval_samples_per_second": 354.547,
+      "eval_steps_per_second": 2.951,
+      "step": 363
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.5044,
+      "step": 484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7221644120707597,
+      "eval_loss": 0.5248228907585144,
+      "eval_runtime": 5.5066,
+      "eval_samples_per_second": 349.037,
+      "eval_steps_per_second": 2.906,
+      "step": 484
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 484,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 10998668340780.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9476011981470215,
+    "learning_rate": 4.577145449621234e-05,
+    "num_train_epochs": 4,
+    "temperature": 6
+  }
+}

run-3/checkpoint-484/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf80e9c40d7bc767c4249778d2a4e70661bde8a0da7851900e67f34e7531f9d2
+size 4792