Training in progress, epoch 3

logs/events.out.tfevents.1702102715.joseph_legion.21824.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16855c117e31f3f264d59be6a661e2f14634b8c726a4c092f0f19e06a48df84f
-size 5609
+oid sha256:bc2ac90376063e7e21c482d54fad719640b39dcf47fb125412dda3145b25d5f7
+size 6089

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24d4de8522e9f9e1724ed7f0817d2365b40bd85329083891c76ea26eaf13bf3
+oid sha256:d44d0759ee84e6571c50629d14d6f8a45767b401dfcaa1ee0246342d925d522d
 size 17550344

run-5/checkpoint-2874/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_pretrain",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "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-5/checkpoint-2874/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44d0759ee84e6571c50629d14d6f8a45767b401dfcaa1ee0246342d925d522d
+size 17550344

run-5/checkpoint-2874/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059c147e8817875b859ed9ada67f7b2da03b393392523ef20e3bf266a2ac20e8
+size 35125946

run-5/checkpoint-2874/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec91d29514cb5db6204b6e1ee95cf837915b2baed9814f22811ba30988c98a00
+size 14308

run-5/checkpoint-2874/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409ef6cae5c4bb0fc483ee4b74c15546c4430a3a318953c13c5858cc009b529a
+size 1064

run-5/checkpoint-2874/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-2874/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-5/checkpoint-2874/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8615173674588665,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-5\\checkpoint-2874",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2874,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3151780085887827e-05,
+      "loss": 0.4979,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.48700252175331116,
+      "eval_runtime": 10.7411,
+      "eval_samples_per_second": 203.703,
+      "eval_steps_per_second": 1.676,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.767853390591884e-06,
+      "loss": 0.4717,
+      "step": 1916
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8578610603290676,
+      "eval_loss": 0.4791734516620636,
+      "eval_runtime": 10.7469,
+      "eval_samples_per_second": 203.593,
+      "eval_steps_per_second": 1.675,
+      "step": 1916
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.383926695295942e-06,
+      "loss": 0.4658,
+      "step": 2874
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8615173674588665,
+      "eval_loss": 0.47797009348869324,
+      "eval_runtime": 10.7674,
+      "eval_samples_per_second": 203.207,
+      "eval_steps_per_second": 1.672,
+      "step": 2874
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2954016825216.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7535706781183768e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 17
+  }
+}

run-5/checkpoint-2874/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d62a2892c289bfba720cfa14c57d0a1acaceeec92177b2eddad453a6ac795e20
+size 4792