Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f2c3a5f3243656fca6b8797830979cd9ddff00ba52ad64c6bfde0d1160a4c
+oid sha256:52e4c82d133e24d979fa50dd1f5da3cf993a9afba45f61351030b87bca8dbce1
 size 1668076741

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ec64142d1f0a3cb201e869b089a93963530f2ebd5859646122ef979057409f
+oid sha256:9fd8f7f94f77022b5215a867cb7b7f69f0fd389a147841d8656911b44dad2903
 size 834053717

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deebbc10a778a0deea9d7ee66aff117a2ff1030819c46684fc2078337a13f7de
+oid sha256:23dc9ace1d0befcffec0a9d9e2805d913d33cd0dc2a3259a8ebde02165bcc5ae
 size 17641

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1320d1dde11a646ceaddba0cc632bafb7ccddf41a813071e1e3284de4cbb041e
+oid sha256:0d4c16f0bde844db19274bd1d26b71a9ec83b8f990d97e0bf43faadfb838da90
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311fdf8544236bc9183022ce6f609475cd525084b757c5f4405c36c6da5663bf
+oid sha256:25d6cb48c005e9d751ad0f279e5f0e2c753346576d9fd073fad547f015a9c4a4
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
-  "global_step": 40000,
+  "epoch": 1.0,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -282,11 +282,80 @@
       "eval_samples_per_second": 23.908,
       "eval_steps_per_second": 0.598,
       "step": 40000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.5893320607754046e-06,
+      "loss": 0.8543,
+      "step": 41000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.0596740374389e-06,
+      "loss": 0.8245,
+      "step": 42000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.587044866629908e-06,
+      "loss": 0.8451,
+      "step": 43000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1725653761999294e-06,
+      "loss": 0.8217,
+      "step": 44000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.185497391612495e-07,
+      "loss": 0.7959,
+      "step": 45000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.265459758197716e-07,
+      "loss": 0.8161,
+      "step": 46000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.980276904853785e-07,
+      "loss": 0.811,
+      "step": 47000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3353680835990033e-07,
+      "loss": 0.8219,
+      "step": 48000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.412003109892648e-08,
+      "loss": 0.8384,
+      "step": 49000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3123017789107294e-11,
+      "loss": 0.8297,
+      "step": 50000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8507072999639782,
+      "eval_loss": 0.6616092920303345,
+      "eval_runtime": 184.1184,
+      "eval_samples_per_second": 27.156,
+      "eval_steps_per_second": 0.679,
+      "step": 50000
     }
   ],
   "max_steps": 50000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 1.2626650202112e+19,
+  "total_flos": 1.578331275264e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ec64142d1f0a3cb201e869b089a93963530f2ebd5859646122ef979057409f
+oid sha256:9fd8f7f94f77022b5215a867cb7b7f69f0fd389a147841d8656911b44dad2903
 size 834053717