Training in progress, epoch 5

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f1ab52c1d09c4a47cc708502b04849748d58bc59bce2da13b303e5e378683bb
-size 5884
+oid sha256:c94d25e15b00fb570e7519363d0c2f92ad02030dad75a2725a6b80f2d2a364ba
+size 6844

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d56853c81d13e9d6d82db9eb1d4540d0c672f7163e675daa538b5d191d6b2d8b
+oid sha256:4f8ac9b4ac5d3a199eb097deae22e478ebefb7457fb9cf3b6c79c74bb4a34130
 size 17549312

run-1/checkpoint-484/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-484/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3048501b2e3281b0f3ebdef6d5e3ece4789def04e5e25fef21b25d04dcf5122c
+size 17549312

run-1/checkpoint-484/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3cad1dc689109608e7a038e5e9b3e026f9facc4b4f63f6e537795aa7761cb4
+size 35123898

run-1/checkpoint-484/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8a3330c813834e4c485b34be4f2caec2b74c220dd9549f784aeeae29566825
+size 14308

run-1/checkpoint-484/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e302581bf5e9503b02128b6e45d73891c4213f1e7f5d2ffbddc0513d88abb3
+size 1064

run-1/checkpoint-484/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-484/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-484/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.7101977107180021,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-1\\checkpoint-484",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 484,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 10998668340780.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6084476315511869,
+    "learning_rate": 2.4847718043043563e-05,
+    "num_train_epochs": 7,
+    "temperature": 19
+  }
+}

run-1/checkpoint-484/training_args.bin

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

run-1/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-1/checkpoint-605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8ac9b4ac5d3a199eb097deae22e478ebefb7457fb9cf3b6c79c74bb4a34130
+size 17549312

run-1/checkpoint-605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe654a622693ae3923de1b89b45921a837b87a5579615338039bdc5a59abdc9
+size 35123898

run-1/checkpoint-605/rng_state.pth

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

run-1/checkpoint-605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08855068ae3e1916d4d86aca3f1385ec889cfbd67debadcbb0cece214171e1e
+size 1064

run-1/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-1/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-1/checkpoint-605/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.7127991675338189,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-1\\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": 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
+    }
+  ],
+  "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": 0.6084476315511869,
+    "learning_rate": 2.4847718043043563e-05,
+    "num_train_epochs": 7,
+    "temperature": 19
+  }
+}

run-1/checkpoint-605/training_args.bin

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