Training in progress, epoch 1

logs/events.out.tfevents.1702112366.joseph_legion.21152.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3dd3246593b7b8461fb7b79a2282bd194c92d3d00de5aa3c1a271fecf3b8620
-size 7324
+oid sha256:2e95cfadb8e161b3b09d5b7a6064da321647bf4999566f8a0ec62ac175873f6e
+size 8158

logs/events.out.tfevents.1702112719.joseph_legion.21152.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe2b38536aef071e5232e6c7703253e3afe8aa5b1d1522370a3a741e60f332e
+size 4923

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f74f1aa42c05fbf66ac212bb2eb6606261e607f51d2229901245ea728807b8
+oid sha256:02be72d67ba340cb865cd422613b3778066941df3ae9356c2f7b5cee49557151
 size 17549312

run-1/checkpoint-847/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-1/checkpoint-847/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b03dcab5d674ccd5221379f3deb1cb32d1427969060b776e8de2515b8b93db7
+size 17549312

run-1/checkpoint-847/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc157d2af3731cb5191b0af88aa43a09a8788df65452ca65d6a7c85287a9626b
+size 35123898

run-1/checkpoint-847/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa47f1b51be8b4f259ede72e5207674b89dcb4200a08ed0dedcba82e0d62d39
+size 14308

run-1/checkpoint-847/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6fea02e499111dcfa5c4ad7367bf20e888ad04d008f7eacd160d389612834e
+size 1064

run-1/checkpoint-847/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-1/checkpoint-847/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-1/checkpoint-847/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.7169614984391259,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-1\\checkpoint-726",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 847,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.129804403689448e-05,
+      "loss": 0.4131,
+      "step": 121
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6368366285119667,
+      "eval_loss": 0.4047480523586273,
+      "eval_runtime": 5.4349,
+      "eval_samples_per_second": 353.639,
+      "eval_steps_per_second": 2.944,
+      "step": 121
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7748370030745404e-05,
+      "loss": 0.3945,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6899063475546305,
+      "eval_loss": 0.38732439279556274,
+      "eval_runtime": 5.3621,
+      "eval_samples_per_second": 358.443,
+      "eval_steps_per_second": 2.984,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4198696024596321e-05,
+      "loss": 0.3823,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7018730489073881,
+      "eval_loss": 0.3818596303462982,
+      "eval_runtime": 5.4466,
+      "eval_samples_per_second": 352.882,
+      "eval_steps_per_second": 2.938,
+      "step": 363
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.064902201844724e-05,
+      "loss": 0.3756,
+      "step": 484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7101977107180021,
+      "eval_loss": 0.37931492924690247,
+      "eval_runtime": 5.4367,
+      "eval_samples_per_second": 353.52,
+      "eval_steps_per_second": 2.943,
+      "step": 484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.099348012298161e-06,
+      "loss": 0.3727,
+      "step": 605
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7127991675338189,
+      "eval_loss": 0.37749114632606506,
+      "eval_runtime": 5.3835,
+      "eval_samples_per_second": 357.016,
+      "eval_steps_per_second": 2.972,
+      "step": 605
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.5496740061490804e-06,
+      "loss": 0.369,
+      "step": 726
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7169614984391259,
+      "eval_loss": 0.3764614760875702,
+      "eval_runtime": 5.3772,
+      "eval_samples_per_second": 357.435,
+      "eval_steps_per_second": 2.976,
+      "step": 726
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 0.3687,
+      "step": 847
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7164412070759626,
+      "eval_loss": 0.3761356472969055,
+      "eval_runtime": 5.3953,
+      "eval_samples_per_second": 356.236,
+      "eval_steps_per_second": 2.966,
+      "step": 847
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 19207865758500.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6084476315511869,
+    "learning_rate": 2.4847718043043563e-05,
+    "num_train_epochs": 7,
+    "temperature": 19
+  }
+}

run-1/checkpoint-847/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee46da73b5b7f90d0402a1151d426bf28f4e4ce14b2c390c7f4085f19a11ca5
+size 4792

run-2/checkpoint-121/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-2/checkpoint-121/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02be72d67ba340cb865cd422613b3778066941df3ae9356c2f7b5cee49557151
+size 17549312

run-2/checkpoint-121/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad52c9498ec2c6c8ca9b004613ff5d787d9ac0721665a222950927e6024cd7e1
+size 35123898

run-2/checkpoint-121/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd181a05942c0fbede5477dd873682f74d182806068f5196db5614c596bd135e
+size 14308

run-2/checkpoint-121/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26393b2378188d11f046f280c7b7c648855d79eca121ef86652a797c4be45b0
+size 1064

run-2/checkpoint-121/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-2/checkpoint-121/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-2/checkpoint-121/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.7200832466181062,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-2\\checkpoint-121",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 121,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00011029236363001645,
+      "loss": 0.286,
+      "step": 121
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7200832466181062,
+      "eval_loss": 0.27681800723075867,
+      "eval_runtime": 5.4424,
+      "eval_samples_per_second": 353.152,
+      "eval_steps_per_second": 2.94,
+      "step": 121
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 2763562416840.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4285130419277947,
+    "learning_rate": 0.0001286744242350192,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-2/checkpoint-121/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e590d11240d33b6c62b0acacb758d8f7dea00e23d4b083076359fd31c39d79f3
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee46da73b5b7f90d0402a1151d426bf28f4e4ce14b2c390c7f4085f19a11ca5
+oid sha256:e590d11240d33b6c62b0acacb758d8f7dea00e23d4b083076359fd31c39d79f3
 size 4792