Training in progress, epoch 5

logs/events.out.tfevents.1702103615.joseph_legion.21824.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d02ea249d0bf7b630522b9dffc41f6ed150bdd2fefd059d27ac26c7083b7a2
-size 6557
+oid sha256:54f71c486810bade201ff9b4939b280955d8082dcb43c63dc9ba11fd9eb9e751
+size 7391

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:055568c53fdbd7443db13edd741448b84af03fd4833eac7e04f78f27126daaf3
+oid sha256:876cee19bb295d402ba62a181bd30e7bbe482c2c16704ec27a3b746be3297b40
 size 17550344

run-11/checkpoint-600/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-11/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876cee19bb295d402ba62a181bd30e7bbe482c2c16704ec27a3b746be3297b40
+size 17550344

run-11/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb89e685c3a973b2583e1cd5cc817c02bf68fe543aed02258ae0e09226603b8
+size 35125946

run-11/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:524b9db6b9011ecae9251b86855540e9d6d59efaa7188ba3627db2ddaa0ad50c
+size 14244

run-11/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c34d279402f962e3147d79a6e2120f6bff9b016b37242edcd3cc1372dc4079
+size 1064

run-11/checkpoint-600/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-11/checkpoint-600/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-11/checkpoint-600/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8729433272394881,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-11\\checkpoint-600",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.546076859205841e-05,
+      "loss": 0.5075,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.4903055727481842,
+      "eval_runtime": 10.8207,
+      "eval_samples_per_second": 202.205,
+      "eval_steps_per_second": 1.663,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.15955764440438e-05,
+      "loss": 0.4756,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.856489945155393,
+      "eval_loss": 0.4780411124229431,
+      "eval_runtime": 10.8942,
+      "eval_samples_per_second": 200.84,
+      "eval_steps_per_second": 1.652,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.7730384296029203e-05,
+      "loss": 0.4648,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8656307129798904,
+      "eval_loss": 0.47325029969215393,
+      "eval_runtime": 10.798,
+      "eval_samples_per_second": 202.631,
+      "eval_steps_per_second": 1.667,
+      "step": 360
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.3865192148014602e-05,
+      "loss": 0.4567,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8720292504570384,
+      "eval_loss": 0.47100675106048584,
+      "eval_runtime": 10.8776,
+      "eval_samples_per_second": 201.147,
+      "eval_steps_per_second": 1.655,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.4533,
+      "step": 600
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8729433272394881,
+      "eval_loss": 0.4702821373939514,
+      "eval_runtime": 10.8456,
+      "eval_samples_per_second": 201.741,
+      "eval_steps_per_second": 1.66,
+      "step": 600
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 9988136054880.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.9325960740073e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 9
+  }
+}

run-11/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f701614cf2d5168dc20cf1308f2133dde2098a7365b20e6033011c4b998f66cc
+size 4792