Training in progress, epoch 4

logs/events.out.tfevents.1702224982.joseph_legion.22340.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c182f26053497b3287cb7eb2fef2bb7a9805320c8b85cf69a73ec134932973
-size 5942
+oid sha256:e487b439ab5bd58e914f6aa4f46d3c67c3747ec3af4f6cc36d632d1c44ed6589
+size 6422

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ddb4dac676ca7abc74a297c1c2e8f6d223af192785606581093d70ae682008
+oid sha256:20cbc361f9ac382188d6ce581f98ff8662502e31387cc65209e98a9995f11a37
 size 17549312

run-0/checkpoint-220/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-0/checkpoint-220/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cbc361f9ac382188d6ce581f98ff8662502e31387cc65209e98a9995f11a37
+size 17549312

run-0/checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20863023e63d8b801cb37bf420b707f80f0483ce63be4ca10470a62fab9dad04
+size 35123898

run-0/checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7490a59add9b8bbe4259dbc0adb9870a059024eef767fd9d1db3db4b03e7ff2
+size 14308

run-0/checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf16e94ae0a2a86b5008801bcb0c3647d3228f684d3a3a16f60ca922c5fce5a6
+size 1064

run-0/checkpoint-220/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-0/checkpoint-220/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-0/checkpoint-220/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.6984848484848485,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-0\\checkpoint-165",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.1639231036686423e-05,
+      "loss": 0.3688,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6378787878787879,
+      "eval_loss": 0.3670942187309265,
+      "eval_runtime": 3.2946,
+      "eval_samples_per_second": 600.98,
+      "eval_steps_per_second": 4.856,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6229423277514814e-05,
+      "loss": 0.3633,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6782828282828283,
+      "eval_loss": 0.3586779534816742,
+      "eval_runtime": 3.2782,
+      "eval_samples_per_second": 603.989,
+      "eval_steps_per_second": 4.881,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.0819615518343211e-05,
+      "loss": 0.3544,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6984848484848485,
+      "eval_loss": 0.3513254225254059,
+      "eval_runtime": 3.3521,
+      "eval_samples_per_second": 590.677,
+      "eval_steps_per_second": 4.773,
+      "step": 165
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.409807759171606e-06,
+      "loss": 0.3484,
+      "step": 220
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.696969696969697,
+      "eval_loss": 0.3481346070766449,
+      "eval_runtime": 3.354,
+      "eval_samples_per_second": 590.334,
+      "eval_steps_per_second": 4.77,
+      "step": 220
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 275,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3368572315560.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5339855376932713,
+    "learning_rate": 2.7049038795858027e-05,
+    "num_train_epochs": 5,
+    "temperature": 24
+  }
+}

run-0/checkpoint-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4b5d2e8689e8402348a8a7f0484dd982845d1acc2eb0c6b3b9db93248be3f5
+size 4792