Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9992887f6907f8916987f3e3d5b5cd5f9a668b44cebeae398a79e142aced221
+oid sha256:26cd8608c74765cf0d7e63a3bd73516440951ea66a7798b1db8fabaf293cd73d
 size 267832560

run-2/checkpoint-2138/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-2/checkpoint-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23a968971b19293287438eef60ae5c1918ec542ff71380aae31cd91c873538f
+oid sha256:26cd8608c74765cf0d7e63a3bd73516440951ea66a7798b1db8fabaf293cd73d
 size 267832560

run-2/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de823e79a240af7a023f39e071d2ee53375f471e37d82ffc8ad524d0210c963
+oid sha256:27036bd6d5c147ed5ca1ab4795ea0dd675b03aeeab4bc7c35494d8353c84cd75
 size 535727290

run-2/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11edc7ed6e233cf8ded4a33dfcfe8204ae40733acbe38c974b94308bacdc2d6d
-size 14308
+oid sha256:69e0a553a49d736b29e905a2d4bf1244efc8e9ef91880c8ee0b1a1f54b22212d
+size 14244

run-2/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4faa4bda620d03b6edc8353e8edb3a8710818368d5ef4d63d2cae7608666363
+oid sha256:0ed3f34b5f9517f54c77536f0ba18982652f4f4de915e227c452430419d32086
 size 1064

run-2/checkpoint-2138/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.48409375114357234,
+  "best_metric": 0.3853198145814999,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 2138,
   "is_hyper_param_search": true,
@@ -9,58 +9,55 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.47,
-      "learning_rate": 5.944660653119031e-06,
-      "loss": 0.5558,
+      "epoch": 0.23,
+      "grad_norm": 4.28505277633667,
+      "learning_rate": 3.0702893894484785e-06,
+      "loss": 0.6069,
       "step": 500
     },
     {
-      "epoch": 0.94,
-      "learning_rate": 5.157496901381872e-06,
-      "loss": 0.5053,
+      "epoch": 0.47,
+      "grad_norm": 9.482794761657715,
+      "learning_rate": 2.9196373094951675e-06,
+      "loss": 0.5628,
       "step": 1000
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 0.4907635748386383,
-      "eval_matthews_correlation": 0.42854888313294803,
-      "eval_runtime": 0.8054,
-      "eval_samples_per_second": 1295.012,
-      "eval_steps_per_second": 81.947,
-      "step": 1069
-    },
-    {
-      "epoch": 1.4,
-      "learning_rate": 4.370333149644712e-06,
-      "loss": 0.4286,
+      "epoch": 0.7,
+      "grad_norm": 22.521339416503906,
+      "learning_rate": 2.7689852295418565e-06,
+      "loss": 0.5565,
       "step": 1500
     },
     {
-      "epoch": 1.87,
-      "learning_rate": 3.5831693979075514e-06,
-      "loss": 0.3992,
+      "epoch": 0.94,
+      "grad_norm": 26.7753849029541,
+      "learning_rate": 2.6183331495885454e-06,
+      "loss": 0.5184,
       "step": 2000
     },
     {
-      "epoch": 2.0,
-      "eval_loss": 0.5015696883201599,
-      "eval_matthews_correlation": 0.48409375114357234,
-      "eval_runtime": 0.8234,
-      "eval_samples_per_second": 1266.73,
-      "eval_steps_per_second": 80.157,
+      "epoch": 1.0,
+      "eval_loss": 0.5730993747711182,
+      "eval_matthews_correlation": 0.3853198145814999,
+      "eval_runtime": 0.7612,
+      "eval_samples_per_second": 1370.225,
+      "eval_steps_per_second": 86.706,
       "step": 2138
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4276,
-  "num_train_epochs": 4,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 75782994673692.0,
+  "total_flos": 32530060484016.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 6.7318244048561916e-06,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 8,
-    "seed": 14
+    "learning_rate": 3.2209414694017896e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 16
   }
 }

run-2/checkpoint-2138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
-size 4664
+oid sha256:88d2c3d6804ca2d9d22cb74f328c5ae8ec320f8d12a0ef15ea5ae2037f02bd85
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710554238.6e5f088ca464.226.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2728a30252b8c7698d4b1cbbee9e9398c0d44f7fa3ab038a041c0d6da1827ad
+size 5979

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
+oid sha256:88d2c3d6804ca2d9d22cb74f328c5ae8ec320f8d12a0ef15ea5ae2037f02bd85
 size 4984