Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5822060e3c3a7ebd53d16d93cb50d2a5cfd7bad9d36edadaceeb261b16e3f07b
+oid sha256:67f65ebac087eecb3136c25266c13fe1748c83541d47af3665a593199e8fbbbf
 size 437958648

run-0/checkpoint-358/config.json

@@ -9,52 +9,8 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9",
-    "10": "LABEL_10",
-    "11": "LABEL_11",
-    "12": "LABEL_12",
-    "13": "LABEL_13",
-    "14": "LABEL_14",
-    "15": "LABEL_15",
-    "16": "LABEL_16",
-    "17": "LABEL_17",
-    "18": "LABEL_18",
-    "19": "LABEL_19"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_10": 10,
-    "LABEL_11": 11,
-    "LABEL_12": 12,
-    "LABEL_13": 13,
-    "LABEL_14": 14,
-    "LABEL_15": 15,
-    "LABEL_16": 16,
-    "LABEL_17": 17,
-    "LABEL_18": 18,
-    "LABEL_19": 19,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

run-0/checkpoint-358/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72271a98ada970df47cd57bfbd4c33eb65e05fb14cb2ea7bf120b4542b53b217
-size 438014016
+oid sha256:67f65ebac087eecb3136c25266c13fe1748c83541d47af3665a593199e8fbbbf
+size 437958648

run-0/checkpoint-358/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0ed4b296a7a4a44743d3b8e9ccc1ab801744d507fdd9cac2d034648b6104f4
-size 876149114
+oid sha256:d3e3d0aba04ad0e517ef1c40249cfc00da0057c2c9df2644889c84eb16cdb733
+size 876038394

run-0/checkpoint-358/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72340d53a573e35b8a2892a74e8a02c506aa351bd83a86e183b25bf359bda426
-size 14308
+oid sha256:be6a2abdc636a987f2524cd4857edadf7650cb9e40eb358dcc1c55bc8335346e
+size 14244

run-0/checkpoint-358/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b86cf7e053c2579534fed3f160f846f769dd4b4c1af244f53ae21315dfe462a
+oid sha256:d80a787c544b76e19fce4aa5a7af8bca8cf13afd6c290f7a34439d52dcc83275
 size 1064

run-0/checkpoint-358/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.6224137544631958,
+  "best_metric": 0.6166871786117554,
   "best_model_checkpoint": "./results/run-0/checkpoint-358",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 358,
   "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6795138888888889,
-      "eval_loss": 0.6224137544631958,
-      "eval_runtime": 10.0132,
-      "eval_samples_per_second": 95.375,
-      "eval_steps_per_second": 11.984,
+      "eval_accuracy": 0.6253472222222222,
+      "eval_loss": 0.642154335975647,
+      "eval_runtime": 10.3326,
+      "eval_samples_per_second": 92.426,
+      "eval_steps_per_second": 11.614,
+      "step": 179
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6413194444444446,
+      "eval_loss": 0.6166871786117554,
+      "eval_runtime": 10.3148,
+      "eval_samples_per_second": 92.585,
+      "eval_steps_per_second": 11.634,
       "step": 358
     }
   ],
   "logging_steps": 500,
-  "max_steps": 716,
+  "max_steps": 358,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 8,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.2830875674148802e-05,
+    "learning_rate": 9.375386211631406e-06,
     "num_train_epochs": 2,
-    "per_device_train_batch_size": 8,
-    "seed": 14
+    "per_device_train_batch_size": 16,
+    "seed": 4
   }
 }

run-0/checkpoint-358/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7492942e77c037e56d91ad59372c979d1f8ff2bc44d6c8e69149791748c37a
+oid sha256:362bc42377e8cdf8bb785935f0b5fbe5a696f30de3dafe660b2fe381b2a64dc6
 size 4920

runs/Mar09_23-14-00_aa189cdd2d19/events.out.tfevents.1710026630.aa189cdd2d19.2368.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f56ef902ddb4652d3084a3d86a3c0dd6d4da9d1e67283e4dc2e3d5e44640dc
-size 4885
+oid sha256:823abab9c7a85287656f94527b6673e6a0a1dd6d604fd9331149aafd1612e315
+size 5562