Training in progress, step 10500

{checkpoint-9500 → checkpoint-10500}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee5c0fdabe1fb84604c932871d4d31efbf9a5e19da3a06925ed21acf376c951
+oid sha256:80559c1b1bf97ffea5492c8aafd7dec88753955d7295cfbc08b99df5ce302630
 size 267028677

{checkpoint-9500 → checkpoint-10500}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d196281040986c59679090ad9b52258214d65eb95663908e7e0109183ed6062d
+oid sha256:b5b915af613925ecdf2955e1a788f57e0f9ed1146924f573e0789a03c9f5d1fb
 size 133523761

{checkpoint-9500 → checkpoint-10500}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3976e9b3ae2e02fd0a92fc78e89d4ece213650eea7cb021e7c653ac619b95433
+oid sha256:89440c8497ea37eb9574fb3a4b717af648034e96d1e784a5ec340222f778f966
 size 14575

{checkpoint-9500 → checkpoint-10500}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9449ed0722d38afa219557eed961b86c1d4b84f8fc83a467196797246faeeb
+oid sha256:59eac2cccdc53a2b511c84a4ecc9b55c72027d8de648a98699746a3948afa715
 size 627

{checkpoint-9500 → checkpoint-10500}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8,
-  "global_step": 9500,
+  "epoch": 4.2,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,11 +402,37 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 3.8781509399414062,
       "step": 9375
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.0064e-06,
+      "loss": 0.6741,
+      "step": 10000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7376,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.46900177001953,
+      "eval_f1": 0.7334789109935773,
+      "eval_gpu_ram_allocated": 0.393521785736084,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 31,
+      "eval_loss": 0.8409038782119751,
+      "eval_precision": 0.7329890286601207,
+      "eval_recall": 0.7376,
+      "eval_runtime": 15.1968,
+      "eval_samples_per_second": 1316.067,
+      "eval_steps_per_second": 41.127,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.8847808837890625,
+      "step": 10000
     }
   ],
   "max_steps": 12500,
   "num_train_epochs": 5,
-  "total_flos": 4831927598639232.0,
+  "total_flos": 5340484590610176.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241ed085563766e8b22fce648138ece49f6a97c58c9e52f48e329a7840e905f4
+oid sha256:b5b915af613925ecdf2955e1a788f57e0f9ed1146924f573e0789a03c9f5d1fb
 size 133523761