Training in progress, epoch 3

logs/events.out.tfevents.1702104892.joseph_legion.21824.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3593836f60c6dee5c50d4f5671dd928cc51340c459a6ca20ea36aa8091273960
-size 5608
+oid sha256:398020736144683ae13bfa4c03f89496ba19c474f3785dd721f44df061fcb765
+size 6442

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38179b5e84993a5d50efd2ea429aea42c04907bf6a907ca9642820b2f489b103
+oid sha256:3dc6ac54fe27dcc578c066a7db2026c65deb654e76d8e56bc38f5ca6a703371c
 size 17550344

run-18/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-18/checkpoint-2874/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc6ac54fe27dcc578c066a7db2026c65deb654e76d8e56bc38f5ca6a703371c
+size 17550344

run-18/checkpoint-2874/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf335ffe431f670263bc142177094d55fbf89d6bdac0b4419c9f7afae9836aa
+size 35125946

run-18/checkpoint-2874/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf8a0aaca358318942e5441dedae0f132def7bae81d1b5661994ef23114da2c
+size 14244

run-18/checkpoint-2874/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7723a21d3533ecd1ee599b69a7d74c08262fb745b9658130db0e955d08ffda
+size 1064

run-18/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-18/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-18/checkpoint-2874/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8724862888482633,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-18\\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": 3.465716376002269e-05,
+      "loss": 0.4791,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8670018281535649,
+      "eval_loss": 0.4717980623245239,
+      "eval_runtime": 10.7271,
+      "eval_samples_per_second": 203.97,
+      "eval_steps_per_second": 1.678,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.7328581880011345e-05,
+      "loss": 0.4594,
+      "step": 1916
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8679159049360147,
+      "eval_loss": 0.4765470027923584,
+      "eval_runtime": 10.6457,
+      "eval_samples_per_second": 205.528,
+      "eval_steps_per_second": 1.691,
+      "step": 1916
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4504,
+      "step": 2874
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8724862888482633,
+      "eval_loss": 0.471828430891037,
+      "eval_runtime": 10.7233,
+      "eval_samples_per_second": 204.041,
+      "eval_steps_per_second": 1.679,
+      "step": 2874
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2874,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2922632109696.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.198574564003404e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 39
+  }
+}

run-18/checkpoint-2874/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d52e1b96c1eb778ef233c1c0c4dba803828ef1e416751dfa8618fe1269ede9d
+size 4792