Training in progress, epoch 5

logs/events.out.tfevents.1702103173.joseph_legion.21824.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565c0703c93d7017c7ceb430fcefc1a23b1bed4550c4e04613459e19d45287e2
-size 6559
+oid sha256:30c40aef0e1d9abe3e4d7ae6572e2c5bdef34c2325333682ba628541b6069306
+size 7393

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e950a31644b89760b8ad73acda283992cd68ed43c325ac16db8e606a1364284
+oid sha256:e5038310bc3c44f46ae4134161415c7d50e4a0dc1161a7dac9e1ea233c0ba4ef
 size 17550344

run-8/checkpoint-600/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_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": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "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-8/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5038310bc3c44f46ae4134161415c7d50e4a0dc1161a7dac9e1ea233c0ba4ef
+size 17550344

run-8/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155db41ace90c35dcbf84c527a8c241ead1f5e8ab4e86ed7d7c03bafad21146e
+size 35125946

run-8/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f92f526003e4a114a738b5de8af3b2d3635f0249357026b2e9d009f7bfcf2b9
+size 14244

run-8/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da8a5ba1037d763a03808caeaeda91ddaba958be8d682616591bd3dd4c3cff5
+size 1064

run-8/checkpoint-600/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-8/checkpoint-600/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-8/checkpoint-600/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8697440585009141,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-8\\checkpoint-600",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.043236986060486e-05,
+      "loss": 0.5087,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.4896513521671295,
+      "eval_runtime": 10.857,
+      "eval_samples_per_second": 201.529,
+      "eval_steps_per_second": 1.658,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.782427739545364e-05,
+      "loss": 0.4749,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8619744058500914,
+      "eval_loss": 0.4745013117790222,
+      "eval_runtime": 10.9152,
+      "eval_samples_per_second": 200.455,
+      "eval_steps_per_second": 1.649,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.521618493030243e-05,
+      "loss": 0.4634,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8665447897623401,
+      "eval_loss": 0.47145363688468933,
+      "eval_runtime": 10.8657,
+      "eval_samples_per_second": 201.368,
+      "eval_steps_per_second": 1.657,
+      "step": 360
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2608092465151215e-05,
+      "loss": 0.4568,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8692870201096892,
+      "eval_loss": 0.46969375014305115,
+      "eval_runtime": 10.7546,
+      "eval_samples_per_second": 203.448,
+      "eval_steps_per_second": 1.674,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.454,
+      "step": 600
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8697440585009141,
+      "eval_loss": 0.46959272027015686,
+      "eval_runtime": 10.8689,
+      "eval_samples_per_second": 201.308,
+      "eval_steps_per_second": 1.656,
+      "step": 600
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 10042741487136.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.304046232575607e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 1
+  }
+}

run-8/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525ea9e0eca994e5213a281a2d3bcd4c40576157132541d1de8f3addcf3d6d58
+size 4792