Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe3aaef1664168b504e33315f6633b7b596edf79c2dd00b22d443ce79dd297f
+oid sha256:be315d39d2287ac5ce8d4d962e73c5519b2b6cff622451d924ec4bf93cd86f4c
 size 267832560

run-1/checkpoint-1070/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-1/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79de2ee2b9f2e5fc6096f20a1734ee2ea2173318c8e3e480efcd35aa22b6776
+size 267832560

run-1/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706ea802939f5b07feecf382b64d645b80b385cc3b782ee6bfd0d4e98c304711
+size 535727290

run-1/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3b6a489423928d55cd1cea4872cfb4b776e5394dc7800719aa0afe02c17bb9
+size 14244

run-1/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8e7f455ba6e2451bae5d26987f6f7b1a6952e361bec53543807236c17a6efb
+size 1064

run-1/checkpoint-1070/special_tokens_map.json

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

run-1/checkpoint-1070/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-1/checkpoint-1070/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.5002057401338981,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.8206261895616947e-05,
+      "loss": 0.5254,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4812505543231964,
+      "eval_matthews_correlation": 0.4559278202620904,
+      "eval_runtime": 0.73,
+      "eval_samples_per_second": 1428.785,
+      "eval_steps_per_second": 90.412,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.2358567240231335e-06,
+      "loss": 0.3218,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5361687541007996,
+      "eval_matthews_correlation": 0.5002057401338981,
+      "eval_runtime": 0.7925,
+      "eval_samples_per_second": 1316.068,
+      "eval_steps_per_second": 83.28,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 86032659644700.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.417666706721076e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 19
+  }
+}

run-1/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f24f981d79f17db058c213091fb3c5078f781cd40127f969745b1f0c26243ac
+size 4792

run-2/checkpoint-535/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-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be315d39d2287ac5ce8d4d962e73c5519b2b6cff622451d924ec4bf93cd86f4c
+size 267832560

run-2/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4916dbdd7195c86f845752d11d46b82f0acdf0d77b78f996486808a9e6fe668c
+size 535727290

run-2/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6f3a2f4401b856f9f52a0f5ee4fd72d313bffa3929a5f48d904461b63f5bb1
+size 14244

run-2/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3bc540815d2207ae675c4bedab7dbdcba24a77727f4e3753daabda370143776
+size 1064

run-2/checkpoint-535/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-535/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-535/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.4241202758215723,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.375008732822441e-06,
+      "loss": 0.5465,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5111424922943115,
+      "eval_matthews_correlation": 0.4241202758215723,
+      "eval_runtime": 0.7312,
+      "eval_samples_per_second": 1426.445,
+      "eval_steps_per_second": 90.264,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 42551012212032.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.354650693375582e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 28
+  }
+}

run-2/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c191c0ce6e62ba791581cb8d5777e2a2ea47ddf94e08537242d2e0c3e1e935ba
+size 4792

runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703299040.17d63b357dd6.603.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf1c7dbfeeb4fb9ace52f8def26f526d0c743871ad6d08ae97d804eccc3f9d9
+size 6176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f24f981d79f17db058c213091fb3c5078f781cd40127f969745b1f0c26243ac
+oid sha256:c191c0ce6e62ba791581cb8d5777e2a2ea47ddf94e08537242d2e0c3e1e935ba
 size 4792