Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be315d39d2287ac5ce8d4d962e73c5519b2b6cff622451d924ec4bf93cd86f4c
+oid sha256:27ea673a6d6baf61ce35ae743e2623e5ae5c2292045d5315e963490f3892bccd
 size 267832560

run-2/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-2/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caae777cfd3792c35be35d5cb5e2a5ad7ffca72ac5f4bb9527c13181ab6ab74
+size 267832560

run-2/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef5ccf32030117f6436af76d38948f2ab07215ecfa7a1015a2c5b09b516c8f1
+size 535727290

run-2/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4e4f21d33092b09c1193e5af11508f217a17d0c02aae6912348dc4e6289543
+size 14244

run-2/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d29c19ae93e3a2cd9c047a3cbf3f3f2397f9a36a744a3db0fe529a563c2b8f
+size 1064

run-2/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-2/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-2/checkpoint-1070/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.45610100596076714,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 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
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.3953667722693003e-06,
+      "loss": 0.4351,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5108652114868164,
+      "eval_matthews_correlation": 0.45610100596076714,
+      "eval_runtime": 0.8042,
+      "eval_samples_per_second": 1296.893,
+      "eval_steps_per_second": 82.066,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 85314955418388.0,
+  "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-1070/training_args.bin

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

run-2/checkpoint-1605/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-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062ecb58cc5517e4e411e21af31f3656d9a27916b7998f4434fd60bc9ce94e63
+size 267832560

run-2/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6313d56c2224d4ac2c9c62cdd36f9b3505800f116928c03eb82b7badb1caea
+size 535727290

run-2/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86fbd0f0cb7cb012d87e220997050f3ddc4ff5fa4a8ac30824368534a8914be9
+size 14244

run-2/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e905ed76601033ec7cd88ea0fd79398c140ec74110585ebcc64da3502f6a51
+size 1064

run-2/checkpoint-1605/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-1605/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-1605/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.45610100596076714,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1070",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "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
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.3953667722693003e-06,
+      "loss": 0.4351,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5108652114868164,
+      "eval_matthews_correlation": 0.45610100596076714,
+      "eval_runtime": 0.8042,
+      "eval_samples_per_second": 1296.893,
+      "eval_steps_per_second": 82.066,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 4.1572481171615953e-07,
+      "loss": 0.3868,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.505622148513794,
+      "eval_matthews_correlation": 0.45429014878916396,
+      "eval_runtime": 0.8139,
+      "eval_samples_per_second": 1281.517,
+      "eval_steps_per_second": 81.093,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 127930648977420.0,
+  "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-1605/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.1703299183.17d63b357dd6.603.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c475891c7d356daf6e30f6212f86211138b047879eb1c73146bf18771c13bd
+size 6198

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c191c0ce6e62ba791581cb8d5777e2a2ea47ddf94e08537242d2e0c3e1e935ba
+oid sha256:f25ec3327ec2c416e9b63376a8fab6023c71e90fd3f7d78cfb63d0fc4b7cce55
 size 4792