Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b2cb0c1d3c14e08d992a592e0ed3080678d0addf23085da45bfaa05c3b58bd
+oid sha256:04b612a580cfac2c9686c1f1d37b4adf5e976ef018b8ab50b7f31ccbb8be979e
 size 267832560

run-0/checkpoint-214/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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b612a580cfac2c9686c1f1d37b4adf5e976ef018b8ab50b7f31ccbb8be979e
+size 267832560

run-0/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968f6da2c8d9985ff31192f4827fa5df737c855555dee7f4ab9e34e456cef419
+size 535727290

run-0/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6a70890eb166220abdede7b7d71d4310400c7c19352213087d18301eaa3bcd
+size 14244

run-0/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3587430174d270c4faf744e553ba77cea23ccca0bed4742dcf38834fdf02860
+size 1064

run-0/checkpoint-214/special_tokens_map.json

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

run-0/checkpoint-214/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-0/checkpoint-214/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5878534317016602,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9866,
+      "eval_samples_per_second": 525.026,
+      "eval_steps_per_second": 65.943,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.143357679659004e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 6
+  }
+}

run-0/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6380478865745a4c7273017600e79375bf0566f3c411b9e3401106e044e923ec
+size 4984

run-0/checkpoint-7/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c20218e0b94e6e2ea38637345298b3961120e6cb8a7eeb5d67366251638204b2
+oid sha256:f852ca35d13bce7b0d6b4cf8c76c14b0866185fbfb3b1e2f04e69690cd980748
 size 267832560

run-0/checkpoint-7/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757b20889d8c4ebb99ee094617216a9e872f8506f241e47a172f81d09ef4ee67
-size 535727290
+oid sha256:ff32d8455ee1d4b038a82ed2565170dbbeb7a1b9886ae938fd0bd87ade4fef20
+size 531007934

run-0/checkpoint-7/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc4ef5ffcc2a39c74e8598a37e0687340047329a8f9dbf3d4c35e5148d94b74
+oid sha256:7292ec256a201cbbd03671c7bef6fcff63ba96bd69bab8722fc35689009d72a7
 size 4984

runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709058944.d3d09c0dfc16.836.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7943d10b2e5d857c9d2d1d9c07469b2b7c064f0b79ed203b2589ae09f5e94dbb
+size 423

runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709061541.d3d09c0dfc16.836.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11413398ec2068b660c3e6288c030a04d63e1158e53209855184bce672523817
+size 4869

runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709061564.d3d09c0dfc16.836.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2677b7a31e9777e5c340f6f27baa5e860c17ac283cac12e7be292f189c3e416a
+size 5562

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0217581794ae6950079b9eb597029b99d93d55c51b3e0e9cd50a8e181c91a58
+oid sha256:6380478865745a4c7273017600e79375bf0566f3c411b9e3401106e044e923ec
 size 4984