Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc98819f094296e8ee7a58a6487045ff94eb1d9595f0b8e4befce59472d08bca
+oid sha256:789f63451e9f6a5a3aebb1c50893986c8358b205c41d3693f1f42a195cfa69b3
 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": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789f63451e9f6a5a3aebb1c50893986c8358b205c41d3693f1f42a195cfa69b3
+size 267832560

run-2/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6fe246d43e7d66c6445ad07491ca43da0ccc9e890269e1d7a2e6d94ec20240
+size 535727290

run-2/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ed84bd1face77164633021c7a0f546091a5c542f5edef4e7559bdb387617d8
+size 14244

run-2/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb73dec8478dbf86daec0e19bb88225fec8d9173464785438dbca3a59d95cb0f
+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 +1,100 @@
+{
+  "best_metric": 0.43999593210437116,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 13.068270683288574,
+      "learning_rate": 3.279225406846597e-05,
+      "loss": 0.6237,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 19.185081481933594,
+      "learning_rate": 3.118321314263349e-05,
+      "loss": 0.589,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 15.156795501708984,
+      "learning_rate": 2.957417221680101e-05,
+      "loss": 0.5822,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.616458415985107,
+      "learning_rate": 2.7965131290968525e-05,
+      "loss": 0.5617,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5167925357818604,
+      "eval_matthews_correlation": 0.43340222780977355,
+      "eval_runtime": 13.6246,
+      "eval_samples_per_second": 76.553,
+      "eval_steps_per_second": 4.844,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.24055208265781403,
+      "learning_rate": 2.6356090365136045e-05,
+      "loss": 0.4543,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 12.348481178283691,
+      "learning_rate": 2.474704943930356e-05,
+      "loss": 0.4826,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.1964465230703354,
+      "learning_rate": 2.313800851347108e-05,
+      "loss": 0.4657,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 140.90501403808594,
+      "learning_rate": 2.1528967587638597e-05,
+      "loss": 0.4826,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7125852704048157,
+      "eval_matthews_correlation": 0.43999593210437116,
+      "eval_runtime": 13.4225,
+      "eval_samples_per_second": 77.706,
+      "eval_steps_per_second": 4.917,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 65281072449384.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.440129499429845e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 9
+  }
+}

run-2/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd6c4335817ae53c5fab910e26963e9341f2b70248fdfe65446f308172d5c35
+size 4984

runs/Apr07_19-11-28_4f2b1ef740c5/events.out.tfevents.1712517736.4f2b1ef740c5.698.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4a66b292413d9a4bbdc2a6aa22b6d1955460a0fc530750641d1d16b21a09ac
-size 5930
+oid sha256:1bbe840ce6774fe3d3579cc1922cbf1cafc4f1f78442746f2b364abd05c5b25a
+size 7109