Training in progress, epoch 5

logs/events.out.tfevents.1702166110.joseph_legion.21448.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4b27ac54c966aba843108a719fcc01bc26e460286922ba4fd2b5ec0e712bcf
-size 6376
+oid sha256:1f9f1f64b55773a4d988fd43ca0885a9d1d4e19ef14d419ec66d29cbb5052869
+size 6856

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2abce79f121186551e81577bc4e62d565eee50e1d00458fcb7f12aaaa76e6f
+oid sha256:2547d5c66457fe469db44e53cfe295f11dba3b58bfe2ddcf829779d0d80b2d0d
 size 267838720

run-5/checkpoint-2395/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "vocab_size": 30522
+}

run-5/checkpoint-2395/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2547d5c66457fe469db44e53cfe295f11dba3b58bfe2ddcf829779d0d80b2d0d
+size 267838720

run-5/checkpoint-2395/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9f03b277c1beb4b3c1078bfff51fdd9d6ed265c22ce11b95364821b537a42d
+size 535739578

run-5/checkpoint-2395/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f67dc3384c4c3ac05b083cd11fe1e115282f847709bd7d9c29ce5ed3d24d5b5
+size 14308

run-5/checkpoint-2395/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c3ccbe13c32fcefcf21d550b449102de06aca2ec7983375fecf5930546dfbe
+size 1064

run-5/checkpoint-2395/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-5/checkpoint-2395/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-5/checkpoint-2395/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.8738574040219378,
+  "best_model_checkpoint": "distilbert-hate_speech18\\run-5\\checkpoint-2395",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2395,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4395797527808295e-06,
+      "loss": 0.2516,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8624314442413162,
+      "eval_loss": 0.24848461151123047,
+      "eval_runtime": 9.4673,
+      "eval_samples_per_second": 231.112,
+      "eval_steps_per_second": 7.288,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.1516638022246633e-06,
+      "loss": 0.2482,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8638025594149908,
+      "eval_loss": 0.2472020387649536,
+      "eval_runtime": 9.4556,
+      "eval_samples_per_second": 231.396,
+      "eval_steps_per_second": 7.297,
+      "step": 958
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.637478516684976e-07,
+      "loss": 0.2469,
+      "step": 1437
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8688299817184644,
+      "eval_loss": 0.24652723968029022,
+      "eval_runtime": 9.4688,
+      "eval_samples_per_second": 231.075,
+      "eval_steps_per_second": 7.287,
+      "step": 1437
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.758319011123317e-07,
+      "loss": 0.2461,
+      "step": 1916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8715722120658135,
+      "eval_loss": 0.24602682888507843,
+      "eval_runtime": 9.478,
+      "eval_samples_per_second": 230.849,
+      "eval_steps_per_second": 7.28,
+      "step": 1916
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.8791595055616583e-07,
+      "loss": 0.2456,
+      "step": 2395
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8738574040219378,
+      "eval_loss": 0.24580524861812592,
+      "eval_runtime": 9.467,
+      "eval_samples_per_second": 231.118,
+      "eval_steps_per_second": 7.288,
+      "step": 2395
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 641954735265312.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.19436109341303698,
+    "learning_rate": 1.7274957033369952e-06,
+    "num_train_epochs": 6,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 16,
+    "temperature": 12
+  }
+}

run-5/checkpoint-2395/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7316aa93f572ca44c9682ad225b35745f9d355c0713119fad66ce1bad923e9c4
+size 4792