Training in progress, epoch 3

logs/events.out.tfevents.1702225275.joseph_legion.22340.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665818eaf235f85626d8cd943bc07527c0c7efb5ec8b3ccc8029cb83644d91e4
-size 5462
+oid sha256:21cad359e3e2c68b5fa15e53c5e74d8f2a2f83d298cc0932ab57d4431282b01d
+size 5942

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc8325677378c849d6d96f98eacb9c718f817890655be5a3cbc51f50fc9046d
+oid sha256:ddd9c9832834fd214e70b612128b86a84aa92f382acea991d15894d68e19b2a6
 size 17549312

run-3/checkpoint-165/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "agvidit1/TinyBert-Berttoken-Toxigen-pretrain",
+  "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-165/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd9c9832834fd214e70b612128b86a84aa92f382acea991d15894d68e19b2a6
+size 17549312

run-3/checkpoint-165/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3446e45e8228fad2342e768d04a48265e0b8e44bab1cc71cdcbf6032cfe081bf
+size 35123898

run-3/checkpoint-165/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ef8354889bdc155d6655d573b67a207c3fe92e6c8c8a589ed2558c3ca5645e
+size 14308

run-3/checkpoint-165/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c223484b5d208f09c778631646d5ac25681c93c707913c99b91b0d18c4404ac9
+size 1064

run-3/checkpoint-165/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-165/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-165/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.6792929292929293,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-3\\checkpoint-165",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 165,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4720964669022145e-05,
+      "loss": 0.3636,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6378787878787879,
+      "eval_loss": 0.3626602292060852,
+      "eval_runtime": 3.3658,
+      "eval_samples_per_second": 588.264,
+      "eval_steps_per_second": 4.754,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2267470557518455e-05,
+      "loss": 0.3604,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6393939393939394,
+      "eval_loss": 0.35877418518066406,
+      "eval_runtime": 3.34,
+      "eval_samples_per_second": 592.817,
+      "eval_steps_per_second": 4.79,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.813976446014764e-06,
+      "loss": 0.356,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6792929292929293,
+      "eval_loss": 0.3534165918827057,
+      "eval_runtime": 3.437,
+      "eval_samples_per_second": 576.084,
+      "eval_steps_per_second": 4.655,
+      "step": 165
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 385,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 2524547079600.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.524441928071262,
+    "learning_rate": 1.7174458780525836e-05,
+    "num_train_epochs": 7,
+    "temperature": 11
+  }
+}

run-3/checkpoint-165/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beba1d8158ddcd8ff24d11a4333407e6a3952372b86d4bccb40918afb846f7c7
+size 4792