Training in progress, step 40000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a55d6487c86c6aead5e0412dc7bc934e36a0aa93b9f0928222c619b3a6dc26
+oid sha256:cccd8b5e6f95d7d23729d6518abbb1c7171130f5a3a3aa208c43d929630d2080
 size 1668076741

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa3a23b0ea1a2c3ccb9f24eefca4b14ffcdafa3ff984873e38ddff2e7290345
+oid sha256:1109492877baa8385171cce26f0c6475c82a564d58f6669c91912ca645fd8bbc
 size 834053717

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a94832b74f59af89e3b9e9505954479af47d9b9be6a042d5dc4a4c83a1ee819
+oid sha256:ca58160f675a0d686e519b17545add52c1791e5dbe907a2e86061685a34b7766
 size 15597

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fbddc5e4f36733a366bb458aab68ef6c96dc3f630fcba928b847be47bc6ff6
+oid sha256:b5eb5aa26622244bf7286739429fab4e82221f83ea489f4c5df476d8e490e060
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bbda704539dc18bceb7e94b4d3dd8ba0647f895bc67af2d0be585b02bce7e37
+oid sha256:1c2d0b879ccc77b0aa0757151f84d49c24e909fa2a6b674a23fe5416c55b8698
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
-  "global_step": 30000,
+  "epoch": 0.8,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,11 +213,80 @@
       "eval_samples_per_second": 39.738,
       "eval_steps_per_second": 2.488,
       "step": 30000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.0379844092057256e-05,
+      "loss": 0.7337,
+      "step": 31000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.446783607398505e-06,
+      "loss": 0.6781,
+      "step": 32000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.538901241148115e-06,
+      "loss": 0.7332,
+      "step": 33000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.659215159142834e-06,
+      "loss": 0.8189,
+      "step": 34000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.810733117141998e-06,
+      "loss": 0.8406,
+      "step": 35000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.998060655562913e-06,
+      "loss": 0.8554,
+      "step": 36000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.224751384305667e-06,
+      "loss": 0.8401,
+      "step": 37000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.494186788054548e-06,
+      "loss": 0.7826,
+      "step": 38000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.8095614399059063e-06,
+      "loss": 0.7544,
+      "step": 39000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.1744793390868967e-06,
+      "loss": 0.7466,
+      "step": 40000
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.8594107078575001,
+      "eval_loss": 0.6134777665138245,
+      "eval_runtime": 124.9907,
+      "eval_samples_per_second": 40.003,
+      "eval_steps_per_second": 2.504,
+      "step": 40000
     }
   ],
   "max_steps": 50000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 2.02026403233792e+19,
+  "total_flos": 2.69368537645056e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa3a23b0ea1a2c3ccb9f24eefca4b14ffcdafa3ff984873e38ddff2e7290345
+oid sha256:1109492877baa8385171cce26f0c6475c82a564d58f6669c91912ca645fd8bbc
 size 834053717