Training in progress, step 700, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9660653d81186c4ea8304a91b5b4f3e3d5116fa26b11d1bc68c8ad7dfda9a22
+oid sha256:6dd03b0f621ace53dbb41365520e9d264fbf7b64c28301f32b12ea29ec6f3458
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1455d3eb76a40554a6ae8838b6fd3472bae7829a09664e4994e5a5172b1edc0
+oid sha256:9e3465e167409675f6fa80c05bb553328847f7fae6e8fb2bf8345054d99a3074
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4a55aedb3a8689db2ef4501ca946a84b5dfeaa4fba907dbb5c84c2391bac35f
+oid sha256:f9c1417b81bbf5bb143eea752aa484a07d2d358bf6e2d354641b4850ccd6daf8
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8888888888888888,
+  "epoch": 1.037037037037037,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,13 +85,26 @@
       "eval_samples_per_second": 1.905,
       "eval_steps_per_second": 0.239,
       "step": 600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0,
+      "loss": 8.4979,
+      "step": 700
+    },
+    {
+      "epoch": 1.04,
+      "eval_runtime": 788.4314,
+      "eval_samples_per_second": 1.903,
+      "eval_steps_per_second": 0.238,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.24944239296512e+17,
+  "total_flos": 1.45768279179264e+17,
   "trial_name": null,
   "trial_params": null
 }