Training in progress, epoch 3

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4a560270d8af95a7d1dadcb432e4d7a2309f8dbbcbbfe62744f37a88c8dcec
-size 5403
+oid sha256:5547be418d8ec8ea69187cdd6c4f02b7586bd992f47390f42ecb76937ad4828b
+size 5883

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df862278ae902952c69ee85e6ef4b6da65f15dea82c549a48208c9974af27a70
+oid sha256:289e49f2787bb798de92e775a996e48eea71683a3a68b5654286673add3fe0df
 size 17549312

run-2/checkpoint-363/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-363/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289e49f2787bb798de92e775a996e48eea71683a3a68b5654286673add3fe0df
+size 17549312

run-2/checkpoint-363/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fdceb0b4a82ea5558573d7729d3fc2d5c6e87d1ffd5025f2ccc011a1de3691
+size 35123898

run-2/checkpoint-363/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7915dd38af4270aefc78e183c118c69b6f8d50285ff32709d8aff7d88a6ead2a
+size 14308

run-2/checkpoint-363/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0c042006e9dcfae9ee652835ba10c2e257be7c132bd6c287e8bca88be5fa00
+size 1064

run-2/checkpoint-363/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-363/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-363/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7507804370447451,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-2\\checkpoint-363",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 363,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 847,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 8247964642380.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4285130419277947,
+    "learning_rate": 0.0001286744242350192,
+    "num_train_epochs": 7,
+    "temperature": 15
+  }
+}

run-2/checkpoint-363/training_args.bin

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