Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b33a499c9ba166861abe0b43880c9770a68c95cbe96891effad9d7abb0086ca
+oid sha256:923ebb47b6080ad9f8fdffc175b8dd5a2fe62749f33013f83e13ad03904adf39
 size 267832560

run-0/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14eb0faa2824a1d661e3d5e7974f72926d7ad722098c73e9cf58d9bd53b227d
+oid sha256:8304426a12eae324205c222b175ac2ce8346db4f17790e4b907a5442157224f1
 size 267832560

run-0/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf125fa6bdba9fc29916967adfe49b0367dd3adeb18470b56830d767003dd55
-size 535724410
+oid sha256:a5673afda31e709f4353a4360b1f8c84f3651b6091d24226616b1eb7c03ecd08
+size 535727290

run-0/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b652edcdbfa99232c2b28dd8d37e6ea195a5d540c564441ffa67c3a85597ac
-size 13990
+oid sha256:a06bdf85f59358deef9e12fb0db3d26f1ad915d689bd2e3f1d387afcd1467cfe
+size 14308

run-0/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f366e87a42a7cb0b355a2213188dee6192b6e415f47bfe52f5b773fdb7945e8a
+oid sha256:efebaa84af45e6bcf206f1d946713407d92b9f2ca132dcdef933d8774bf59048
 size 1064

run-0/checkpoint-54/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-54",
-  "epoch": 1.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-27",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 54,
   "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6191213130950928,
+      "eval_loss": 0.614648163318634,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 31.3263,
-      "eval_samples_per_second": 33.295,
-      "eval_steps_per_second": 2.107,
+      "eval_runtime": 0.4799,
+      "eval_samples_per_second": 2173.307,
+      "eval_steps_per_second": 137.525,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6087808012962341,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4818,
+      "eval_samples_per_second": 2164.673,
+      "eval_steps_per_second": 136.978,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 108,
+  "max_steps": 81,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.165583831913945e-06,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 16,
-    "seed": 1
+    "learning_rate": 1.054776898695923e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 33
   }
 }

run-0/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72a55a072bd05abfdbbccc44f98c0201a2f2461afeb211106285f98e7a3c3bb
+oid sha256:f9aeee846d5ef57126383822d22cfd2d6a81bccc1f37b1bef0d1bfbebbae36a2
 size 4792

run-0/checkpoint-81/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": "4.37.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499fb7147d100923f08e518478e2b9287737dda72f24d0729b7ca4c6f1d89c4f
+size 267832560

run-0/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc17d298df4198f4e6a0b93df9e614250a684f7c891f32554ca86df62f72943
+size 535727290

run-0/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045a6900f317dfd6ff4468644a11849458df491e7ca043c93725d9cafd593d59
+size 14308

run-0/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bdb163e38597d2bfd0d6ba3aae048050c815e60e7db612dbb438e32f00fa13
+size 1064

run-0/checkpoint-81/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-81/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-81/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.614648163318634,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4799,
+      "eval_samples_per_second": 2173.307,
+      "eval_steps_per_second": 137.525,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6087808012962341,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4818,
+      "eval_samples_per_second": 2164.673,
+      "eval_steps_per_second": 136.978,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6076169610023499,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4775,
+      "eval_samples_per_second": 2184.076,
+      "eval_steps_per_second": 138.206,
+      "step": 81
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 81,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.054776898695923e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 33
+  }
+}

run-0/checkpoint-81/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9aeee846d5ef57126383822d22cfd2d6a81bccc1f37b1bef0d1bfbebbae36a2
+size 4792

run-1/checkpoint-27/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": "4.37.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923ebb47b6080ad9f8fdffc175b8dd5a2fe62749f33013f83e13ad03904adf39
+size 267832560

run-1/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c1a17e1496b575ea0206eabf6c4581cc1f8020efe0cad23dd7a5075750267a
+size 535727290

run-1/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5425099ca9d294d1bb9490e66c6878a1540dcb3dc87e1cff0f594fdfa9eef99b
+size 14244

run-1/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49449c7540dad0b1c06011a66eee84f13d88cc61d258137641fb0ba68fbf791e
+size 1064

run-1/checkpoint-27/special_tokens_map.json

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

run-1/checkpoint-27/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-1/checkpoint-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.003737743780434562,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-27",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6868433952331543,
+      "eval_matthews_correlation": 0.003737743780434562,
+      "eval_runtime": 0.4777,
+      "eval_samples_per_second": 2183.527,
+      "eval_steps_per_second": 138.171,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 27,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6803195765411705e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 16
+  }
+}

run-1/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485611b40c1fe7edaffd11ff6ff3d5588eb109b033918a450124a960165560f3
+size 4792

runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706535827.f96070633581.4947.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d7c2003dc99f0b0368a9c72d44c2a535d0302896fdaa336ae59c5def2b653f
-size 4989
+oid sha256:64d81283c972ff5fc0b59764717e0cafdf679b809c6ce14117cb3f0bf95e7b3b
+size 5666

runs/Jan29_13-40-22_f96070633581/events.out.tfevents.1706535867.f96070633581.4947.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb4bb4cca37b5aa1d579be570fad39b5d14890483cb6d9a3f53b40d8957deb3
+size 5009

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9aeee846d5ef57126383822d22cfd2d6a81bccc1f37b1bef0d1bfbebbae36a2
+oid sha256:485611b40c1fe7edaffd11ff6ff3d5588eb109b033918a450124a960165560f3
 size 4792