Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d785585acfcbc05b84b06e49ef0e8524b6ff41c71b99362f839670a6142a310a
+oid sha256:05c968488c791ec048ca50fe94b28e4af2ac5434b8a4bdde4b076f549b715a06
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac432822fa219b97229bd552d2008909680831f64b9e38fb9efb3f013513a155
+oid sha256:42764f328df0c11e665a3d1f1a28175b6cf44a65517dfb8430cf18864c4fb5f5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f28f1fb74779128912d7e99bf248891bbf757b23481d699c811a64071c9f1f
+oid sha256:054d52bab859a6d48721e83cd6abdf3a605011904b735d5df023417b14dbfa7b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14814814814814814,
+  "epoch": 0.2962962962962963,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -20,13 +20,26 @@
       "eval_samples_per_second": 1.903,
       "eval_steps_per_second": 0.239,
       "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0,
+      "loss": 8.4542,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "eval_runtime": 788.181,
+      "eval_samples_per_second": 1.903,
+      "eval_steps_per_second": 0.239,
+      "step": 200
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0824039882752e+16,
+  "total_flos": 4.1648079765504e+16,
   "trial_name": null,
   "trial_params": null
 }