Training in progress, epoch 2

logs/events.out.tfevents.1702224850.joseph_legion.22340.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458875c93fe15a46b214a58d74adadc27ee35628ea67d7bed03988fbfe6ef62c
-size 7365
+oid sha256:80f65c5740ccaecec8a72ff8586ee45b264229a552ab159c9aded931447589f0
+size 8199

logs/events.out.tfevents.1702224982.joseph_legion.22340.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b16e5fe7dad9fc5f608f7bd27db58f675cb7e5b0d4dd6edd46869a7abcf2050
+size 5462

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf324c06cb9d60397ee154003601ff807e33e168a04ec8e37a13183662938f4b
+oid sha256:4395a6838d080ffd9551cd1a40241874bb0bcb1cc6338ccd2ddd5aaaf5cb7f4f
 size 17549312

run-0/checkpoint-110/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-0/checkpoint-110/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4395a6838d080ffd9551cd1a40241874bb0bcb1cc6338ccd2ddd5aaaf5cb7f4f
+size 17549312

run-0/checkpoint-110/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93496ee7ac7b6c0a47d9fd6d4ccd1045a3ab1934cd8c8907742965e6aef80241
+size 35123898

run-0/checkpoint-110/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9551bc1e2c99dce1fea8d9f3955131307048d879abc6b8cfc77903906edd6323
+size 14308

run-0/checkpoint-110/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782866c4b9c4cb7725c13eb0a2ea449b4554188125f801ecbdfcf85bdf41200a
+size 1064

run-0/checkpoint-110/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-0/checkpoint-110/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-0/checkpoint-110/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.6782828282828283,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-0\\checkpoint-110",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 110,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.1639231036686423e-05,
+      "loss": 0.3688,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6378787878787879,
+      "eval_loss": 0.3670942187309265,
+      "eval_runtime": 3.2946,
+      "eval_samples_per_second": 600.98,
+      "eval_steps_per_second": 4.856,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6229423277514814e-05,
+      "loss": 0.3633,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6782828282828283,
+      "eval_loss": 0.3586779534816742,
+      "eval_runtime": 3.2782,
+      "eval_samples_per_second": 603.989,
+      "eval_steps_per_second": 4.881,
+      "step": 110
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 275,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1682283651840.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5339855376932713,
+    "learning_rate": 2.7049038795858027e-05,
+    "num_train_epochs": 5,
+    "temperature": 24
+  }
+}

run-0/checkpoint-110/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4b5d2e8689e8402348a8a7f0484dd982845d1acc2eb0c6b3b9db93248be3f5
+size 4792

run-0/checkpoint-55/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-0/checkpoint-55/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30434c48f142c07c16911fb037e335224a083575c5a31bb5597228004ce7cfb1
+size 17549312

run-0/checkpoint-55/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19c870ab54db69078b131a92b28e569691e50c0ff8f529f73389957f79c3a9f
+size 35123898

run-0/checkpoint-55/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9684c683f536a580a60f9875e5f0c89c28c0f0b16080832ddf6bf0362cbd5e4
+size 14308

run-0/checkpoint-55/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3988591defe5087e6469f0ac360027c08ee67faebbfa8cfdd9c70b322f64f7e2
+size 1064

run-0/checkpoint-55/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-0/checkpoint-55/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-0/checkpoint-55/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.6378787878787879,
+  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-0\\checkpoint-55",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 55,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.1639231036686423e-05,
+      "loss": 0.3688,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6378787878787879,
+      "eval_loss": 0.3670942187309265,
+      "eval_runtime": 3.2946,
+      "eval_samples_per_second": 600.98,
+      "eval_steps_per_second": 4.856,
+      "step": 55
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 275,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 847072419720.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5339855376932713,
+    "learning_rate": 2.7049038795858027e-05,
+    "num_train_epochs": 5,
+    "temperature": 24
+  }
+}

run-0/checkpoint-55/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4b5d2e8689e8402348a8a7f0484dd982845d1acc2eb0c6b3b9db93248be3f5
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a34f682ad386e0676127a583584cafdf3fb14063e10b793527acfb22f5eb41d
+oid sha256:fb4b5d2e8689e8402348a8a7f0484dd982845d1acc2eb0c6b3b9db93248be3f5
 size 4792