Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a0cd116856436be14632b63b6b76697e6acbc599abfea55c35256599d029a8
+oid sha256:02799c6288fd6be713dcb703b97e2603053e03b860695800a7120e144e762fb5
 size 267832560

run-2/checkpoint-4276/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911d166a8e20e374cc62b8d8c784ca4818c3f1ed8b65f60e7574e127d3a1510a
+size 267832560

run-2/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e323adea3c46e480885972b95e28b395eaecea4050b4cb6a06aa5fd912d114
+size 535727290

run-2/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a671fb0f280894a47ad3fa3f40448e902a5016ade3b8ae8c284c6f3a658d2b0
+size 14308

run-2/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86e6bec8d7496a933517aa7d6a66ccb425f37c926ce29ae3591f3468c24af6c
+size 1064

run-2/checkpoint-4276/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-4276/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-4276/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.45722196195216697,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-2/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.717583231684137e-06,
+      "loss": 0.5783,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.318734463364544e-06,
+      "loss": 0.5628,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.919885695044952e-06,
+      "loss": 0.5371,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.52103692672536e-06,
+      "loss": 0.5214,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5808761715888977,
+      "eval_matthews_correlation": 0.4304260866765428,
+      "eval_runtime": 0.7545,
+      "eval_samples_per_second": 1382.293,
+      "eval_steps_per_second": 87.47,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.1221881584057677e-06,
+      "loss": 0.4706,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7233393900861752e-06,
+      "loss": 0.5064,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.324490621766583e-06,
+      "loss": 0.5363,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.925641853446991e-06,
+      "loss": 0.4672,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7189328074455261,
+      "eval_matthews_correlation": 0.45722196195216697,
+      "eval_runtime": 0.7349,
+      "eval_samples_per_second": 1419.238,
+      "eval_steps_per_second": 89.808,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 65202419931432.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.1164320000037285e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 26
+  }
+}

run-2/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33df9fa76c45a070b235b52e6deaa801af62492a1cc0e084d107a267b67a3f43
+size 4728

run-2/checkpoint-6414/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02799c6288fd6be713dcb703b97e2603053e03b860695800a7120e144e762fb5
+size 267832560

run-2/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2276e2d089968a4fce29efa499d2466bc22d783ce52c4d7e4259b4dca6fadf14
+size 535727290

run-2/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2276213d45264db040275028de0a8d1f0c5368380334f20db9fcc540f0a46e
+size 14308

run-2/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb705f927a9210cd8113000e5db86b8d002e6cb9cdde9b4c93e62b36f46b774
+size 1064

run-2/checkpoint-6414/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-6414/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-6414/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.45722196195216697,
+  "best_model_checkpoint": "hw-01-finetuned-cola/run-2/checkpoint-4276",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.717583231684137e-06,
+      "loss": 0.5783,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.318734463364544e-06,
+      "loss": 0.5628,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.919885695044952e-06,
+      "loss": 0.5371,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.52103692672536e-06,
+      "loss": 0.5214,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5808761715888977,
+      "eval_matthews_correlation": 0.4304260866765428,
+      "eval_runtime": 0.7545,
+      "eval_samples_per_second": 1382.293,
+      "eval_steps_per_second": 87.47,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.1221881584057677e-06,
+      "loss": 0.4706,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7233393900861752e-06,
+      "loss": 0.5064,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.324490621766583e-06,
+      "loss": 0.5363,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.925641853446991e-06,
+      "loss": 0.4672,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7189328074455261,
+      "eval_matthews_correlation": 0.45722196195216697,
+      "eval_runtime": 0.7349,
+      "eval_samples_per_second": 1419.238,
+      "eval_steps_per_second": 89.808,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.5267930851273988e-06,
+      "loss": 0.458,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1279443168078067e-06,
+      "loss": 0.4648,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.290955484882145e-07,
+      "loss": 0.4544,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.3024678016862234e-07,
+      "loss": 0.4311,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8178148865699768,
+      "eval_matthews_correlation": 0.4511413176850326,
+      "eval_runtime": 0.7355,
+      "eval_samples_per_second": 1417.999,
+      "eval_steps_per_second": 89.73,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97903756622304.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.1164320000037285e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 26
+  }
+}

run-2/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33df9fa76c45a070b235b52e6deaa801af62492a1cc0e084d107a267b67a3f43
+size 4728

runs/Dec23_02-07-05_42b18358a534/events.out.tfevents.1703298389.42b18358a534.403.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b7a43702de137acdc162d56ae73c2fe0445c9cc2211dc4aaa88a455cb77cf2
-size 5407
+oid sha256:dfe06b7983661c89febae0b674cd603749aa694efcc17a637ce48af62ac1e272
+size 7530