Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a6cbe8fc7036a6b49187e8ee3e49a7c8486d4ad1ddf2863d737a258241e0d3
+oid sha256:22b883449c19a6d9e914daeb970fd6499cefc3048f5720f1a5a067086c3bbb39
 size 267832560

run-4/checkpoint-214/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.1",
+  "transformers_version": "4.38.1",
   "vocab_size": 30522
 }

run-4/checkpoint-214/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364a4fe5c859fc06c370b5c35a46a55e286fd15f2709ded468089cc14d98bb66
+oid sha256:280d1c7a6e0982024f37efe4b4f8218e35bf232c7a45e709d5d854344dd5303e
 size 267832560

run-4/checkpoint-214/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632f4a3f94908895c6e5a5910a0b5439646a1c8e2a99cb7a4f5299a3a19bfe2b
-size 535724410
+oid sha256:f4f4a3f265266b61bcfddd3c86c28e7550f5e0e8cbf8c65ea1dba1310dfc3a4a
+size 535727290

run-4/checkpoint-214/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001c64e554515da567312d4220ddc8a1b09a80c19cc82cbcdeb833e38409d22e
-size 14054
+oid sha256:85447337a1adf6ff175fcd1a2a9e9e42ac6feb9eb26cdb16d5c081272dca5f2c
+size 14308

run-4/checkpoint-214/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f40026dcce78c279c83b88e9982a7ab93a525e2b1f8a5974daf4782ba77608
+oid sha256:451697dab5c2ffdc8bb676e3518c830dd5ee08d088c9bc1cf330c4d9d37f62ee
 size 1064

run-4/checkpoint-214/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-214",
-  "epoch": 1.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-107",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 214,
   "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6447671055793762,
+      "eval_loss": 0.6134856343269348,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 31.8352,
-      "eval_samples_per_second": 32.763,
-      "eval_steps_per_second": 2.073,
+      "eval_runtime": 0.4854,
+      "eval_samples_per_second": 2148.702,
+      "eval_steps_per_second": 135.968,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6115169525146484,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4759,
+      "eval_samples_per_second": 2191.828,
+      "eval_steps_per_second": 138.697,
       "step": 214
     }
   ],
   "logging_steps": 500,
   "max_steps": 214,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 4,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.131742234418895e-05,
-    "num_train_epochs": 1,
-    "per_device_train_batch_size": 4,
-    "seed": 8
+    "learning_rate": 5.1545570880959645e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 26
   }
 }

run-4/checkpoint-214/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7ed4c8eef23186e26133f531a89c2b088731c79cec75b73d8ccc06bb3c8ff6
-size 4792
+oid sha256:e4ce8c2944651b940b84be1f0c5e2370c963b754dfc3ad3c86f5be032f9123a1
+size 4984

run-5/checkpoint-54/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-5/checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b883449c19a6d9e914daeb970fd6499cefc3048f5720f1a5a067086c3bbb39
+size 267832560

run-5/checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17ae837efc95422a8363458c9a346edefad06bdb835467a88621082371bcdbf
+size 535727290

run-5/checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd71c33cabccb5a9b91a0f29548a9cff1a6a431fc2baa89c561f36714cf9db6c
+size 14244

run-5/checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d9791afbd6554ac2a356b83f0215b3e5ed2a0aa2f2023645e7066ed76b1880
+size 1064

run-5/checkpoint-54/special_tokens_map.json

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

run-5/checkpoint-54/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-5/checkpoint-54/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0928457264044978,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-54",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.566685676574707,
+      "eval_matthews_correlation": 0.0928457264044978,
+      "eval_runtime": 0.4852,
+      "eval_samples_per_second": 2149.743,
+      "eval_steps_per_second": 136.034,
+      "step": 54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.710392540206621e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 18
+  }
+}

run-5/checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad1fef1939082239593889150a2d97a7a6391f997be90b7eb656629366da7fd
+size 4984

runs/Feb23_10-35-48_ec6659c07f12/events.out.tfevents.1708685110.ec6659c07f12.1051.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5922af3b151ccc07fa3aaaa9a733c79d13f583cf2b6cd6d29712f73bd76358fd
+size 5548

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ce8c2944651b940b84be1f0c5e2370c963b754dfc3ad3c86f5be032f9123a1
+oid sha256:9ad1fef1939082239593889150a2d97a7a6391f997be90b7eb656629366da7fd
 size 4984