Training in progress, epoch 7

logs/events.out.tfevents.1702113279.joseph_legion.21152.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dab000b238a6195d65d44b330ed7fdcfd8df73567209470c156c6bdaec8ff16
-size 7324
+oid sha256:fb4f86a9c6f6ed3556a283a0fcf9136632f7e8349fdaede28b491c4779dbd894
+size 8158

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a05f9d8da2a48455083fcce1fc22d3e80b6e68e642581a6b0e28949ae4bd543
+oid sha256:570f070ffb3b7d86163c367b3ea508ea65c0e565fd5d15b53fa5662c64f56ed5
 size 17549312

run-4/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-4/checkpoint-847/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570f070ffb3b7d86163c367b3ea508ea65c0e565fd5d15b53fa5662c64f56ed5
+size 17549312

run-4/checkpoint-847/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11de4bc6b4660fae443f654c1fa7c7617970862bfc7ad8bc422669bd7b1a69c
+size 35123898

run-4/checkpoint-847/rng_state.pth

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

run-4/checkpoint-847/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a5e704dc631d8884e0ccd75579408e681f74ca716a9ee6b4a22e49bcc44561
+size 1064

run-4/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-4/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-4/checkpoint-847/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.7585848074921956,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-4\\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": 0.00014466984065051867,
+      "loss": 0.3523,
+      "step": 121
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7346514047866806,
+      "eval_loss": 0.3383758068084717,
+      "eval_runtime": 5.3759,
+      "eval_samples_per_second": 357.519,
+      "eval_steps_per_second": 2.976,
+      "step": 121
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001205582005420989,
+      "loss": 0.3282,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7544224765868887,
+      "eval_loss": 0.33105042576789856,
+      "eval_runtime": 5.4179,
+      "eval_samples_per_second": 354.751,
+      "eval_steps_per_second": 2.953,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.644656043367911e-05,
+      "loss": 0.3153,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7554630593132154,
+      "eval_loss": 0.33135876059532166,
+      "eval_runtime": 5.3821,
+      "eval_samples_per_second": 357.112,
+      "eval_steps_per_second": 2.973,
+      "step": 363
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.233492032525934e-05,
+      "loss": 0.304,
+      "step": 484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7554630593132154,
+      "eval_loss": 0.33476221561431885,
+      "eval_runtime": 5.3945,
+      "eval_samples_per_second": 356.288,
+      "eval_steps_per_second": 2.966,
+      "step": 484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.8223280216839555e-05,
+      "loss": 0.2946,
+      "step": 605
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7580645161290323,
+      "eval_loss": 0.33405163884162903,
+      "eval_runtime": 5.3765,
+      "eval_samples_per_second": 357.48,
+      "eval_steps_per_second": 2.976,
+      "step": 605
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.4111640108419778e-05,
+      "loss": 0.2871,
+      "step": 726
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7585848074921956,
+      "eval_loss": 0.3366258144378662,
+      "eval_runtime": 5.3901,
+      "eval_samples_per_second": 356.581,
+      "eval_steps_per_second": 2.968,
+      "step": 726
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 0.283,
+      "step": 847
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7580645161290323,
+      "eval_loss": 0.338644415140152,
+      "eval_runtime": 5.4116,
+      "eval_samples_per_second": 355.164,
+      "eval_steps_per_second": 2.957,
+      "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": 0.543866580390613,
+    "learning_rate": 0.00016878148075893845,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-4/checkpoint-847/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ff081b3a6ff2508f06d2f68c32f682d03896bb152914dd2b16bfe1092b0639
+size 4792