Training in progress, epoch 5

logs/events.out.tfevents.1702103838.joseph_legion.21824.13

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684ffad07b0d5df4fd2eea9fd5fbaed1dda9f1f8ef11bc2fd0a866f801016c39
-size 6560
+oid sha256:9c2ccc1470e8c81a52d0b7f19652c780b3fabf2050cfc190a89865cb56b28b0c
+size 7394

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26676e4d0399a0b3ef615ff04fc70cbf0ad9dd813bb862ad541f8106846b4013
+oid sha256:8fe538154549d9ca42914b921d4ca94d62e8e66cfe2d364075029be28395fcb5
 size 17550344

run-12/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-12/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe538154549d9ca42914b921d4ca94d62e8e66cfe2d364075029be28395fcb5
+size 17550344

run-12/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaca8174f71a14329d34919a310ba34f5e7e16bbaff21440ac1876e85458c134
+size 35125946

run-12/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad483b0510e5ecbcc84ed5eb463fe4d95279bb7de1b6695facb48d9eb637c4ac
+size 14180

run-12/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adddf9118681be26fcdbc872e94c91ba76c23977a2dde76290c8297f0470f05f
+size 1064

run-12/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-12/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-12/checkpoint-600/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.873400365630713,
+  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-12\\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": 6.854342606336822e-05,
+      "loss": 0.499,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.48665618896484375,
+      "eval_runtime": 10.8301,
+      "eval_samples_per_second": 202.03,
+      "eval_steps_per_second": 1.662,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.140756954752616e-05,
+      "loss": 0.4699,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8592321755027422,
+      "eval_loss": 0.48114827275276184,
+      "eval_runtime": 10.9276,
+      "eval_samples_per_second": 200.227,
+      "eval_steps_per_second": 1.647,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.427171303168411e-05,
+      "loss": 0.4591,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8724862888482633,
+      "eval_loss": 0.4719109833240509,
+      "eval_runtime": 10.8837,
+      "eval_samples_per_second": 201.035,
+      "eval_steps_per_second": 1.654,
+      "step": 360
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.7135856515842055e-05,
+      "loss": 0.4513,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8720292504570384,
+      "eval_loss": 0.4705061912536621,
+      "eval_runtime": 10.8611,
+      "eval_samples_per_second": 201.454,
+      "eval_steps_per_second": 1.657,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.4479,
+      "step": 600
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.873400365630713,
+      "eval_loss": 0.46913647651672363,
+      "eval_runtime": 10.7987,
+      "eval_samples_per_second": 202.617,
+      "eval_steps_per_second": 1.667,
+      "step": 600
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 9921791149920.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.567928257921027e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-12/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9e592a7885c23f5d6cba400735dc30195e5d0969925bcedd6884bf7519a0b7
+size 4792