Training in progress, epoch 3

logs/events.out.tfevents.1702113837.joseph_legion.21152.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8ca26daf110313da3ae1a1ffd13e66a9d4864e34c5a8ff84e9dbd9b7182b10
-size 5403
+oid sha256:737a7fd8479e7af59666a75e95ca3dd0908d5918250768bc50b37366dfd09b16
+size 6237

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fdcae9fdb68fd662340a382fc8db47a172f196825b366acd1427bc38a663da
+oid sha256:65bc361f09a17c2f01d950c41c7675a22ba192471ae5451d5f8c3bcb474e442a
 size 17549312

run-9/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-9/checkpoint-363/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bc361f09a17c2f01d950c41c7675a22ba192471ae5451d5f8c3bcb474e442a
+size 17549312

run-9/checkpoint-363/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548fbce23262f82cc27d036d968512922a89b7002763b3ee2c61de69a1b22353
+size 35123898

run-9/checkpoint-363/rng_state.pth

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

run-9/checkpoint-363/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79e18e40415a0d4920f673663c3af849bfadf42fcadc3f50abf53c163b05704
+size 1064

run-9/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-9/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-9/checkpoint-363/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7601456815816857,
+  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-9\\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": 0.0002622085234877425,
+      "loss": 0.236,
+      "step": 121
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7580645161290323,
+      "eval_loss": 0.2295788824558258,
+      "eval_runtime": 5.3953,
+      "eval_samples_per_second": 356.235,
+      "eval_steps_per_second": 2.966,
+      "step": 121
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013110426174387126,
+      "loss": 0.2239,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.759105098855359,
+      "eval_loss": 0.2274383157491684,
+      "eval_runtime": 5.4149,
+      "eval_samples_per_second": 354.944,
+      "eval_steps_per_second": 2.955,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2174,
+      "step": 363
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7601456815816857,
+      "eval_loss": 0.22863133251667023,
+      "eval_runtime": 5.482,
+      "eval_samples_per_second": 350.6,
+      "eval_steps_per_second": 2.919,
+      "step": 363
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 363,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8247964642380.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3527253554518407,
+    "learning_rate": 0.0003933127852316138,
+    "num_train_epochs": 3,
+    "temperature": 26
+  }
+}

run-9/checkpoint-363/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bd6efce6f998c5e3803261b96cabbe61b44e9e9f5498d4b63ce27de623e59c
+size 4792