Training in progress, epoch 6

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1dd87ae6eacdb8e8ee7f4b2f4d4418d64576e2533b5f88be227cec7559ffda
-size 6363
+oid sha256:6394979b9945a1f34184a06934ebc4c9c7f473e41f252d7d818b66cdfbf2b27b
+size 7323

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1297b63fce77eb534d0e0734d93d52e8607e4ce352e4226a4c3418a22793e4e7
+oid sha256:4b55dd38f630a2e83924aba305a40fec0da99a49536ab69c5f47b87d16ff1444
 size 17549312

run-2/checkpoint-605/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-605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02dc0f367ee88156f52193fe779ec920405f28827898f52bdb8fc8d25967af2
+size 17549312

run-2/checkpoint-605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b0daf29adba2478fecb86a3268fccc4b84bebd8cdd9f5e397045bfc100a240
+size 35123898

run-2/checkpoint-605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8118854752a1ec21f28c87a05813d1c425eb3cb9564cd451d69a2e71f89d6a84
+size 14308

run-2/checkpoint-605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28799875ccbcb39ce0ae9c03316230357412491a5a291659a019a8c9dd1df65
+size 1064

run-2/checkpoint-605/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-605/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-605/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.763267429760666,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-2\\checkpoint-605",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 605,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.191030302501371e-05,
+      "loss": 0.2718,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7476586888657648,
+      "eval_loss": 0.27226677536964417,
+      "eval_runtime": 5.4231,
+      "eval_samples_per_second": 354.413,
+      "eval_steps_per_second": 2.95,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.352824242001096e-05,
+      "loss": 0.2651,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7507804370447451,
+      "eval_loss": 0.27160072326660156,
+      "eval_runtime": 5.419,
+      "eval_samples_per_second": 354.676,
+      "eval_steps_per_second": 2.953,
+      "step": 363
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.514618181500822e-05,
+      "loss": 0.2597,
+      "step": 484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7622268470343392,
+      "eval_loss": 0.27192601561546326,
+      "eval_runtime": 5.3166,
+      "eval_samples_per_second": 361.509,
+      "eval_steps_per_second": 3.009,
+      "step": 484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.676412121000548e-05,
+      "loss": 0.2551,
+      "step": 605
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.763267429760666,
+      "eval_loss": 0.2703154385089874,
+      "eval_runtime": 5.4247,
+      "eval_samples_per_second": 354.304,
+      "eval_steps_per_second": 2.949,
+      "step": 605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 13731632367600.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4285130419277947,
+    "learning_rate": 0.0001286744242350192,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-2/checkpoint-605/training_args.bin

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

run-2/checkpoint-726/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-726/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b55dd38f630a2e83924aba305a40fec0da99a49536ab69c5f47b87d16ff1444
+size 17549312

run-2/checkpoint-726/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93873a692efebf3b08f79ddbba8f721b6857cd230761432100c0b3606ebb81c1
+size 35123898

run-2/checkpoint-726/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdf7321c47b3be59e90473a4d202ef1312697271ebe5149a4771636c9e4b35c
+size 14308

run-2/checkpoint-726/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a130daaf71695a68706d0754aaa23301e8374e6c2c3ebd15a0f7b13760025f
+size 1064

run-2/checkpoint-726/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-726/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-726/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.763267429760666,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-2\\checkpoint-605",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 726,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.191030302501371e-05,
+      "loss": 0.2718,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7476586888657648,
+      "eval_loss": 0.27226677536964417,
+      "eval_runtime": 5.4231,
+      "eval_samples_per_second": 354.413,
+      "eval_steps_per_second": 2.95,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.352824242001096e-05,
+      "loss": 0.2651,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7507804370447451,
+      "eval_loss": 0.27160072326660156,
+      "eval_runtime": 5.419,
+      "eval_samples_per_second": 354.676,
+      "eval_steps_per_second": 2.953,
+      "step": 363
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.514618181500822e-05,
+      "loss": 0.2597,
+      "step": 484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7622268470343392,
+      "eval_loss": 0.27192601561546326,
+      "eval_runtime": 5.3166,
+      "eval_samples_per_second": 361.509,
+      "eval_steps_per_second": 3.009,
+      "step": 484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.676412121000548e-05,
+      "loss": 0.2551,
+      "step": 605
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.763267429760666,
+      "eval_loss": 0.2703154385089874,
+      "eval_runtime": 5.4247,
+      "eval_samples_per_second": 354.304,
+      "eval_steps_per_second": 2.949,
+      "step": 605
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.838206060500274e-05,
+      "loss": 0.2513,
+      "step": 726
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7606659729448492,
+      "eval_loss": 0.2714059352874756,
+      "eval_runtime": 5.5229,
+      "eval_samples_per_second": 348.007,
+      "eval_steps_per_second": 2.897,
+      "step": 726
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 16472407904580.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4285130419277947,
+    "learning_rate": 0.0001286744242350192,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-2/checkpoint-726/training_args.bin

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