Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72ed735bc66c1e4f3d7b22980817cb0be001ac1116b797a24c934d10ac4cedc
+oid sha256:616e5335047e47880571774ed5c3a6ad6620c0d2925b03420e4dd001c6d9098f
 size 1256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f87affc22071e86ce66e46cf035148b7442b514cbb86d86fb1d780c2837e63
+oid sha256:62389a8b07b912e1a87e1c61761ec7bcc4a6454869d496e80469b6d6160612c7
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffeaf89b0b04791dc34ee66081eb9e7f6455f6c0432abdcf83d256ef8114b7a1
+oid sha256:47825806ca448e2b8f98b6c819788c83a5e93f7f9111a42270d492b6f5f7d198
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9305019305019306,
+  "epoch": 3.861003861003861,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27,13 +27,33 @@
       "eval_samples_per_second": 50.555,
       "eval_steps_per_second": 3.165,
       "step": 1000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.841698841698842e-05,
+      "loss": 2.291,
+      "step": 1500
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 8.455598455598456e-05,
+      "loss": 2.294,
+      "step": 2000
+    },
+    {
+      "epoch": 3.86,
+      "eval_loss": 2.303375720977783,
+      "eval_runtime": 58.0882,
+      "eval_samples_per_second": 50.32,
+      "eval_steps_per_second": 3.15,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
   "max_steps": 12950,
   "num_train_epochs": 25,
   "save_steps": 1000,
-  "total_flos": 8.660925478487654e+16,
+  "total_flos": 1.7292451037555098e+17,
   "trial_name": null,
   "trial_params": null
 }