Training in progress, step 600, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2bf4ba55112ac493fbfdf4fc212ea31e5e3c2df0a9a8f006552c0f9d7ffced
+oid sha256:b9660653d81186c4ea8304a91b5b4f3e3d5116fa26b11d1bc68c8ad7dfda9a22
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b6469988d6f22d7b6a42244e542a23529124dbec8bae8b086fba39a800d1b6
+oid sha256:e1455d3eb76a40554a6ae8838b6fd3472bae7829a09664e4994e5a5172b1edc0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390c0027bbfe2ad79f7eebbbab1c6be6399953d2c307f3b30d4435c5cefb6d38
+oid sha256:b4a55aedb3a8689db2ef4501ca946a84b5dfeaa4fba907dbb5c84c2391bac35f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7407407407407407,
+  "epoch": 0.8888888888888888,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -72,13 +72,26 @@
       "eval_samples_per_second": 1.903,
       "eval_steps_per_second": 0.239,
       "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0,
+      "loss": 8.7866,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "eval_runtime": 787.5816,
+      "eval_samples_per_second": 1.905,
+      "eval_steps_per_second": 0.239,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0412019941376e+17,
+  "total_flos": 1.24944239296512e+17,
   "trial_name": null,
   "trial_params": null
 }