Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8740e6818af4f7b3de81524dc8912b49bce0877f182ba27f482d246dcec98beb
+oid sha256:898c5e96d647648a7ef654501f82166a08f86b55c447364076d9a7be18c30d21
 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": "4.35.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2641a0fb5e8098c1e4392dd7fb772522aab8196dfa550989e9b11678c3074660
+size 267832560

run-2/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73bb318ea7868b4d3b5448eee3af2735d8e81824613de6e44e76ff1f949a34cf
+size 535727290

run-2/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff56f6cf771ddd7d20265eca53b8a64af4c290f26007b82e13456dec8a4076f6
+size 14308

run-2/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c001a95dc22efb46374f1f965702e4e20dbf9fde40fb4980df8a756842d4e0ac
+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 +1,108 @@
+{
+  "best_metric": 0.49329306040311344,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-3207",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.944660653119031e-06,
+      "loss": 0.5558,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.157496901381872e-06,
+      "loss": 0.5053,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4907635748386383,
+      "eval_matthews_correlation": 0.42854888313294803,
+      "eval_runtime": 0.8054,
+      "eval_samples_per_second": 1295.012,
+      "eval_steps_per_second": 81.947,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.370333149644712e-06,
+      "loss": 0.4286,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.5831693979075514e-06,
+      "loss": 0.3992,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5015696883201599,
+      "eval_matthews_correlation": 0.48409375114357234,
+      "eval_runtime": 0.8234,
+      "eval_samples_per_second": 1266.73,
+      "eval_steps_per_second": 80.157,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.796005646170392e-06,
+      "loss": 0.3434,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.008841894433232e-06,
+      "loss": 0.3371,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5880187749862671,
+      "eval_matthews_correlation": 0.49329306040311344,
+      "eval_runtime": 0.9037,
+      "eval_samples_per_second": 1154.15,
+      "eval_steps_per_second": 73.033,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.2216781426960722e-06,
+      "loss": 0.2988,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 4.345143909589123e-07,
+      "loss": 0.2797,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6395880579948425,
+      "eval_matthews_correlation": 0.49249265259737396,
+      "eval_runtime": 1.057,
+      "eval_samples_per_second": 986.747,
+      "eval_steps_per_second": 62.44,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 150793435338816.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.7318244048561916e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-2/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
+size 4664

run-3/checkpoint-268/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": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898c5e96d647648a7ef654501f82166a08f86b55c447364076d9a7be18c30d21
+size 267832560

run-3/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337aee2b1a486ea4479048b32762b72242d1b4f2f5d433c579fd962d5310805b
+size 535727290

run-3/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ec9d40a98694db4fec537074c925323970df8b2c023db2dd2e1f7829c4c7b1
+size 14244

run-3/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f78f6fdc3f5b0e504bfaa07cf6dbc0cc0e0a82a06d8a2aa0678b8e5810be57
+size 1064

run-3/checkpoint-268/special_tokens_map.json

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

run-3/checkpoint-268/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-3/checkpoint-268/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": 0.3884569188624487,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-268",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5160695314407349,
+      "eval_matthews_correlation": 0.3884569188624487,
+      "eval_runtime": 0.688,
+      "eval_samples_per_second": 1516.05,
+      "eval_steps_per_second": 95.934,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.597085082438434e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 25
+  }
+}

run-3/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700191263.faa202bf7ecf.336.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff12f3cc4840249d2eb97690265f7fff0151bca314454a237f78d63688d1d83
+size 6580

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
+oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
 size 4664