Training in progress, epoch 5

logs/events.out.tfevents.1702225460.joseph_legion.22340.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef63c6d38e18f896cb82c9955587041b641e668c2c637481257a9790e71a688
-size 5941
+oid sha256:cd09fd2407cc823eb13c73011a48b069c08166cad2afd0417922a718a414ed73
+size 6901

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b08eb72d0e89374338470f86532bc650e951ad3b10ee6678042b93de18ea845
+oid sha256:925b24fb64b9d59b735d59e2616f5479dd8c1f627adc972085a9024560f6bd28
 size 17549312

run-5/checkpoint-220/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "agvidit1/TinyBert-Berttoken-Toxigen-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": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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-220/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d93569bf47993ab4ca3bd2ef544927c185269efb183b719b0546d1449f7b785
+size 17549312

run-5/checkpoint-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a68c485f0973a1bdefd35fa5b2a8fbfae3fc7f1f76ee77b06376945a50413fd
+size 35123898

run-5/checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7490a59add9b8bbe4259dbc0adb9870a059024eef767fd9d1db3db4b03e7ff2
+size 14308

run-5/checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffbac67983b1f8f3e3a2d0c4c594b4c9c3c8366d9bf2dd81a14e348d32e29ce
+size 1064

run-5/checkpoint-220/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-220/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-220/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.7626262626262627,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-5\\checkpoint-220",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.445560435088227e-05,
+      "loss": 0.265,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6898989898989899,
+      "eval_loss": 0.25976529717445374,
+      "eval_runtime": 3.3203,
+      "eval_samples_per_second": 596.328,
+      "eval_steps_per_second": 4.819,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.3564483480705814e-05,
+      "loss": 0.2555,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7368686868686869,
+      "eval_loss": 0.2521827816963196,
+      "eval_runtime": 3.3412,
+      "eval_samples_per_second": 592.604,
+      "eval_steps_per_second": 4.789,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.267336261052936e-05,
+      "loss": 0.2496,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.73989898989899,
+      "eval_loss": 0.25000467896461487,
+      "eval_runtime": 3.3777,
+      "eval_samples_per_second": 586.19,
+      "eval_steps_per_second": 4.737,
+      "step": 165
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.1782241740352907e-05,
+      "loss": 0.247,
+      "step": 220
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7626262626262627,
+      "eval_loss": 0.24974669516086578,
+      "eval_runtime": 3.3894,
+      "eval_samples_per_second": 584.175,
+      "eval_steps_per_second": 4.721,
+      "step": 220
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 3368572315560.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.38098176211619805,
+    "learning_rate": 6.534672522105872e-05,
+    "num_train_epochs": 6,
+    "temperature": 20
+  }
+}

run-5/checkpoint-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fecd2afca1c38077cffcce0276b35fce40e373fd017432a66fb6d7282a0935
+size 4792

run-5/checkpoint-275/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "agvidit1/TinyBert-Berttoken-Toxigen-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": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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-275/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925b24fb64b9d59b735d59e2616f5479dd8c1f627adc972085a9024560f6bd28
+size 17549312

run-5/checkpoint-275/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b10780f8547fb5bb7e503cdedfb4aac0d6d8363647558c1598cecdff0e94e3
+size 35123898

run-5/checkpoint-275/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062bcffe46043de7404ecbcc480dc564c6157abb3a7eacf3e7ac3e8f25f25191
+size 14308

run-5/checkpoint-275/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fba10e66bd1fc621c0a5095c4902e6b75f9ec0f2ba84606433c90ea6a6d6dba
+size 1064

run-5/checkpoint-275/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-275/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-275/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.7626262626262627,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-5\\checkpoint-220",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 275,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.445560435088227e-05,
+      "loss": 0.265,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6898989898989899,
+      "eval_loss": 0.25976529717445374,
+      "eval_runtime": 3.3203,
+      "eval_samples_per_second": 596.328,
+      "eval_steps_per_second": 4.819,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.3564483480705814e-05,
+      "loss": 0.2555,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7368686868686869,
+      "eval_loss": 0.2521827816963196,
+      "eval_runtime": 3.3412,
+      "eval_samples_per_second": 592.604,
+      "eval_steps_per_second": 4.789,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.267336261052936e-05,
+      "loss": 0.2496,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.73989898989899,
+      "eval_loss": 0.25000467896461487,
+      "eval_runtime": 3.3777,
+      "eval_samples_per_second": 586.19,
+      "eval_steps_per_second": 4.737,
+      "step": 165
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.1782241740352907e-05,
+      "loss": 0.247,
+      "step": 220
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7626262626262627,
+      "eval_loss": 0.24974669516086578,
+      "eval_runtime": 3.3894,
+      "eval_samples_per_second": 584.175,
+      "eval_steps_per_second": 4.721,
+      "step": 220
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.0891120870176453e-05,
+      "loss": 0.2453,
+      "step": 275
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.753030303030303,
+      "eval_loss": 0.24921274185180664,
+      "eval_runtime": 3.3235,
+      "eval_samples_per_second": 595.759,
+      "eval_steps_per_second": 4.814,
+      "step": 275
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 4228806186960.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.38098176211619805,
+    "learning_rate": 6.534672522105872e-05,
+    "num_train_epochs": 6,
+    "temperature": 20
+  }
+}

run-5/checkpoint-275/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fecd2afca1c38077cffcce0276b35fce40e373fd017432a66fb6d7282a0935
+size 4792