Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74155891d985b0d42ab73fff22f25b8d3ec62478beed1d5b251aca605465c701
+oid sha256:15dce029c51b77276ae1e2af8f2c79296b9ad0e00cbc81423735c42f50bc9526
 size 267832560

run-1/checkpoint-28/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-1/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a74fcf90dad5f09e8b5a5cd9dee8c1e2dff71db3343cd13ce27df171e674be
+size 267832560

run-1/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3925ee5dcc1af0e888c296c2c41f3ac8b1174254b6777e47c0b2ebfc80b17686
+size 535727290

run-1/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59e5e117a7281d196f006d261cb771d649175d27382a76cf25f9a89b715d7cb
+size 14244

run-1/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298c23041f72b54004504b7fd56abdfaf126921b0c0b80e9b54e9740bfaf5a31
+size 1064

run-1/checkpoint-28/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-28/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-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-28",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6712570190429688,
+      "eval_matthews_correlation": -0.004094348593533731,
+      "eval_runtime": 0.4692,
+      "eval_samples_per_second": 2222.921,
+      "eval_steps_per_second": 140.664,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6607634425163269,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5052,
+      "eval_samples_per_second": 2064.347,
+      "eval_steps_per_second": 130.63,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.482861293435522e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 22
+  }
+}

run-1/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0f639343d75cb266d6d449e470a6f2e2f119cf3158ecf6b8d9125888beaf82
+size 4984

run-2/checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb089e9ac2ba3e9bfee178463e0a5351fb79b4046211f6167830b3a160bf33d
+oid sha256:15dce029c51b77276ae1e2af8f2c79296b9ad0e00cbc81423735c42f50bc9526
 size 267832560

run-2/checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9516b058e496477f19f51008db1771b000eaf246f9e98c490d8a5ab51f6be89
+oid sha256:a82fb3ad45ed9e7c92567e9c14edfe44978611e24e9b3865eace7d8476caeac8
 size 535727290

run-2/checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e4eac4ccb653df691c572046a6c191bf2e41b96f073d92f8e06f4ada58c10e
-size 14244
+oid sha256:1f64399dab3fa3d7587557002c1e88b3c04aab77244cf3e5548a2cb0245adaac
+size 14308

run-2/checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1004f35ea8de92c80186b5611f92fa28944e8ce2152f4d8a62ae02fcaacd2f9c
+oid sha256:00a9a18f85c8ac202d8c3196678d2d6fe3a31850cef31b63b3621296c806700c
 size 1064

run-2/checkpoint-27/trainer_state.json

@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5863072276115417,
+      "eval_loss": 0.6132858991622925,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.5165,
-      "eval_samples_per_second": 2019.464,
-      "eval_steps_per_second": 127.79,
+      "eval_runtime": 0.4871,
+      "eval_samples_per_second": 2141.162,
+      "eval_steps_per_second": 135.491,
       "step": 27
     }
   ],
@@ -27,9 +27,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.425091322202513e-05,
+    "learning_rate": 7.921646169086052e-06,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "seed": 27
+    "seed": 29
   }
 }

run-2/checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e90b8efb5f56f17604458520e4d53f07ee283e90d1f7b6a020b4be6c6503812e
+oid sha256:04b1732029c3014268c6be62d578a5b5765a6136da335617e7db8f5a0380b6d4
 size 4984

runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709676956.418b5b5ae03a.490.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8013a5ebad59daab150ec2dff5561e9a46e31d3926c0bb2ea3a7875302fcfe51
+size 6547

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0f639343d75cb266d6d449e470a6f2e2f119cf3158ecf6b8d9125888beaf82
+oid sha256:04b1732029c3014268c6be62d578a5b5765a6136da335617e7db8f5a0380b6d4
 size 4984