Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c3d1cbe440a411f0f475e5c87660e28a75f309e47c86cf638b953dda981baf
+oid sha256:67978948fb3b549f5c65bac6be20371317a7760f6a1e185ee4429165340c2211
 size 2847145157

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a3ae8181352512e08922afd8724a2fb432bfeb737553e3566dfb9a74c2d512
+oid sha256:43af96f1ebc8edb6272710e8eded46b397b3566845920240e9b47c2c9d0eae77
 size 1524261149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ad8472e781590cdbac9b5b53b245b9f03b0cb18ed06d415314f34cc3fe6990
+oid sha256:a8442c4ffbd50200b4bc943e03cf1d899ee87f53e137754e23543c2176c8b920
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529d4be4283b5e985b0185b07ad9dee60dff604a0101122f4f66303ff0239736
+oid sha256:81baa9d1bbfebc8a9494097ebb00110cffda569e0baf3070d563ac3650b9b0ae
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5012506253126565,
-  "global_step": 5000,
+  "epoch": 3.0015007503751874,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,11 +106,31 @@
       "eval_samples_per_second": 15.693,
       "eval_steps_per_second": 2.617,
       "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 8.994497248624313e-06,
+      "loss": 2.8996,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.993996998499251e-06,
+      "loss": 2.9048,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.087371587753296,
+      "eval_runtime": 135.1793,
+      "eval_samples_per_second": 15.661,
+      "eval_steps_per_second": 2.611,
+      "step": 6000
     }
   ],
   "max_steps": 9995,
   "num_train_epochs": 5,
-  "total_flos": 1.41481746432e+16,
+  "total_flos": 1.697780957184e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a3ae8181352512e08922afd8724a2fb432bfeb737553e3566dfb9a74c2d512
+oid sha256:43af96f1ebc8edb6272710e8eded46b397b3566845920240e9b47c2c9d0eae77
 size 1524261149

runs/Mar24_13-56-57_9891ffea5fdc/events.out.tfevents.1679666221.9891ffea5fdc.675.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d6e21e818982a1c1de43fa58a1e157de11294ee7be4712ce886020f296227ac
-size 7080
+oid sha256:a6e457789aa349f649882cc826e73d6081fa6cf62da58a798635cc8ae63d2c16
+size 7665