Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45273d24519907b1e6cd0335bd18fcf660d057efd4c7aeb8de7f6a267295f20d
+oid sha256:4aa7079cdad18393c657923235d5cacae351eba7b6e15c6e3d8f8fc6a38d4428
 size 267832560

run-3/checkpoint-268/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.45.0",
   "vocab_size": 30522
 }

run-3/checkpoint-268/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898c5e96d647648a7ef654501f82166a08f86b55c447364076d9a7be18c30d21
+oid sha256:6c05300ede6529e3a246c0e33330d011877666dfbf40217701aeabc1d0048412
 size 267832560

run-3/checkpoint-268/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337aee2b1a486ea4479048b32762b72242d1b4f2f5d433c579fd962d5310805b
+oid sha256:99934653c6a2fdd935701d0c7b07374cd643b5fb562a1bc6039e0b9e886a746c
 size 535727290

run-3/checkpoint-268/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ec9d40a98694db4fec537074c925323970df8b2c023db2dd2e1f7829c4c7b1
+oid sha256:78c847ef2246a3cbbb350f163b5174d59dc3e92096635ffb211ffbe141be238d
 size 14244

run-3/checkpoint-268/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f78f6fdc3f5b0e504bfaa07cf6dbc0cc0e0a82a06d8a2aa0678b8e5810be57
+oid sha256:79301c8fad0aad269d146a13c27ececcddc8bfb7508fafcbcedf1d483c46672a
 size 1064

run-3/checkpoint-268/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.3884569188624487,
+  "best_metric": 0.4063400389101911,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-268",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 268,
   "is_hyper_param_search": true,
@@ -10,24 +10,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5160695314407349,
-      "eval_matthews_correlation": 0.3884569188624487,
-      "eval_runtime": 0.688,
-      "eval_samples_per_second": 1516.05,
-      "eval_steps_per_second": 95.934,
+      "eval_loss": 0.5295282602310181,
+      "eval_matthews_correlation": 0.3577028127616067,
+      "eval_runtime": 0.7966,
+      "eval_samples_per_second": 1309.259,
+      "eval_steps_per_second": 82.849,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.516920268535614,
+      "eval_matthews_correlation": 0.4063400389101911,
+      "eval_runtime": 1.4666,
+      "eval_samples_per_second": 711.177,
+      "eval_steps_per_second": 45.003,
       "step": 268
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1340,
-  "num_train_epochs": 5,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
   "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
   "total_flos": 0,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.597085082438434e-06,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 32,
-    "seed": 25
+    "learning_rate": 1.1486502446056178e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 27
   }
 }

run-3/checkpoint-268/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
-size 4664
+oid sha256:c947f4ef41847348dc05333cc6dacba9abdd7f0fda6f36ebd85c0073a00d6b56
+size 5304

run-4/checkpoint-134/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.45.0",
   "vocab_size": 30522
 }

run-4/checkpoint-134/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b7b79ad7d628ee954291594a9c617d6f0042ff7ff358712495239061c1e8cb
+oid sha256:4aa7079cdad18393c657923235d5cacae351eba7b6e15c6e3d8f8fc6a38d4428
 size 267832560

run-4/checkpoint-134/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624c7d0678ee103872690eea9636756712f9c1352f32a056649a0c52d0bb9431
+oid sha256:3f45ca2bf044e783b56c8609a3a3770cabd0218b6912fe8adfb04e8b6361ad39
 size 535727290

run-4/checkpoint-134/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b229645b40fbde71bfefe569bc58bee6d1d10d8f74232c3f3372fca937d6d3
+oid sha256:ffbedc8e8c2b12a6cdec62b00f66726f6fbed1fabc7eb56d566fccd2a38eb920
 size 14244

run-4/checkpoint-134/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b8f80f8d88a81e1c1d461e7e75d2259bb99880860ab571ad3113bd523146cb
+oid sha256:4b6e282de9b783dc108c58480bd48d0a4b10b87525ef4df4c9c7538e17b928d0
 size 1064

run-4/checkpoint-134/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0,
+  "best_metric": 0.1315571677438866,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-134",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,26 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5651528239250183,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.8455,
-      "eval_samples_per_second": 1233.59,
-      "eval_steps_per_second": 78.06,
+      "eval_loss": 0.5480445623397827,
+      "eval_matthews_correlation": 0.1315571677438866,
+      "eval_runtime": 0.809,
+      "eval_samples_per_second": 1289.215,
+      "eval_steps_per_second": 81.58,
       "step": 134
     }
   ],
   "logging_steps": 500,
-  "max_steps": 134,
+  "max_steps": 268,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 2,
   "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
   "total_flos": 0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0647254903827648e-05,
-    "num_train_epochs": 1,
+    "learning_rate": 7.4123504722847965e-06,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 64,
-    "seed": 35
+    "seed": 19
   }
 }

run-4/checkpoint-134/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a12fdc24cb9dc9a62bc10545627abe46debf8706f86ab2fc532296984bfd9c9
-size 4984
+oid sha256:19cda161a8b2dbe3bebb87bfaa14d6f1770a695864450cbc067761031c985a6b
+size 5304

runs/Sep26_13-34-33_f266a1036e13/events.out.tfevents.1727358715.f266a1036e13.258.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b04020c7998155e14880e8e5e342898937e70d14f75434a8246ca21995cad2a
+size 5985

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c947f4ef41847348dc05333cc6dacba9abdd7f0fda6f36ebd85c0073a00d6b56
+oid sha256:19cda161a8b2dbe3bebb87bfaa14d6f1770a695864450cbc067761031c985a6b
 size 5304