Training in progress, step 300, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c968488c791ec048ca50fe94b28e4af2ac5434b8a4bdde4b076f549b715a06
+oid sha256:6c379412e43b828c4f834738bf3859e9b72cd4483da794f92ccc258e1da4ba76
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42764f328df0c11e665a3d1f1a28175b6cf44a65517dfb8430cf18864c4fb5f5
+oid sha256:37f266dce13902dcd132a0f2e952191cdba75f4d6424635380e0dcb339856fe0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054d52bab859a6d48721e83cd6abdf3a605011904b735d5df023417b14dbfa7b
+oid sha256:60deaf5bce1420ec9463a4509f65e88e0a5a4f9976041c81ec5379366458be94
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2962962962962963,
+  "epoch": 0.4444444444444444,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33,13 +33,26 @@
       "eval_samples_per_second": 1.903,
       "eval_steps_per_second": 0.239,
       "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0,
+      "loss": 8.4751,
+      "step": 300
+    },
+    {
+      "epoch": 0.44,
+      "eval_runtime": 787.7273,
+      "eval_samples_per_second": 1.904,
+      "eval_steps_per_second": 0.239,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.1648079765504e+16,
+  "total_flos": 6.2472119648256e+16,
   "trial_name": null,
   "trial_params": null
 }