Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b09a6eac8e466f5ada412bf43920b165bf31a80fc890163f29999c5e267266
+oid sha256:b9e13fe829399366b0a60237a76a6fa47f869f0a95e1bb37f876e7347a101714
 size 267832560

run-4/checkpoint-8552/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": "4.38.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e13fe829399366b0a60237a76a6fa47f869f0a95e1bb37f876e7347a101714
+size 267832560

run-4/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b192d2057bd5035eaf232aa7a1d2bec6e0c55e6d760b21c6a335170cd692897
+size 535727290

run-4/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f990838f8212b3aeb4fdec6f127ab912879aa5e4eddc343c62c6efda2318d0
+size 14244

run-4/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417959ace7a96594aafc9ecc39cde9418e47efca00b10a012fea336e46c0da00
+size 1064

run-4/checkpoint-8552/special_tokens_map.json

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

run-4/checkpoint-8552/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-4/checkpoint-8552/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.4286063983911785,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.632926940917969,
+      "learning_rate": 1.2946011611760917e-06,
+      "loss": 0.6259,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.080592155456543,
+      "learning_rate": 1.2310780423745168e-06,
+      "loss": 0.6096,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.2639031410217285,
+      "learning_rate": 1.1675549235729423e-06,
+      "loss": 0.5698,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 12.567307472229004,
+      "learning_rate": 1.1040318047713676e-06,
+      "loss": 0.5589,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5995281934738159,
+      "eval_matthews_correlation": 0.08036809130702588,
+      "eval_runtime": 0.3414,
+      "eval_samples_per_second": 3055.256,
+      "eval_steps_per_second": 193.334,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 15.908562660217285,
+      "learning_rate": 1.0405086859697929e-06,
+      "loss": 0.5387,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.577272415161133,
+      "learning_rate": 9.769855671682182e-07,
+      "loss": 0.5105,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 36.38253402709961,
+      "learning_rate": 9.134624483666437e-07,
+      "loss": 0.5256,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 11.872018814086914,
+      "learning_rate": 8.499393295650689e-07,
+      "loss": 0.511,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5569708347320557,
+      "eval_matthews_correlation": 0.39137710349170013,
+      "eval_runtime": 0.5165,
+      "eval_samples_per_second": 2019.532,
+      "eval_steps_per_second": 127.794,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 20.970304489135742,
+      "learning_rate": 7.864162107634943e-07,
+      "loss": 0.475,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 9.216538429260254,
+      "learning_rate": 7.228930919619195e-07,
+      "loss": 0.4814,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 19.621673583984375,
+      "learning_rate": 6.593699731603449e-07,
+      "loss": 0.4871,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 19.49756622314453,
+      "learning_rate": 5.958468543587703e-07,
+      "loss": 0.4675,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5788199305534363,
+      "eval_matthews_correlation": 0.39891405791978285,
+      "eval_runtime": 0.3422,
+      "eval_samples_per_second": 3047.878,
+      "eval_steps_per_second": 192.867,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 49.59273910522461,
+      "learning_rate": 5.323237355571956e-07,
+      "loss": 0.5038,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 34.72640609741211,
+      "learning_rate": 4.6880061675562097e-07,
+      "loss": 0.4434,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 55.005916595458984,
+      "learning_rate": 4.052774979540463e-07,
+      "loss": 0.4816,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 79.78916931152344,
+      "learning_rate": 3.417543791524717e-07,
+      "loss": 0.4923,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 49.529483795166016,
+      "learning_rate": 2.78231260350897e-07,
+      "loss": 0.4698,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6026819944381714,
+      "eval_matthews_correlation": 0.4286063983911785,
+      "eval_runtime": 0.3402,
+      "eval_samples_per_second": 3065.812,
+      "eval_steps_per_second": 194.002,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 138507342838860.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3581242799776662e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 5
+  }
+}

run-4/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09d686d744a0008ff792f3863883364cd703287c8e9332ee8d8209d508c0a5d
+size 4984