Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a634fc2021caff6f2b80a76b2323bff9b246f415389e430fda426abb9e349c
+oid sha256:174d7fb67c1d5914f7bce13195ff08075217b774c12125d4b16fabf2e589a33b
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812c251523b90117be8640a1f401bb079058696642e8aa7f5cf7b19c06573f59
+oid sha256:dd0b3d8cd89fffd07a67787dfa320ec2b5f9bdd59aff140d541012dea00c011f
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe97754e91c297ae31c4ec01cc8074d82add99e6b7d330de4b929c9322ec461
+oid sha256:f409da3dcc8d395470a77e66ec88ee64f503054e416b434d299f2eda08c45ccd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2506641149520874,
   "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 14.842,
       "eval_steps_per_second": 1.861,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.0785,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2521893978118896,
+      "eval_runtime": 127.1994,
+      "eval_samples_per_second": 15.173,
+      "eval_steps_per_second": 1.903,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.963918665952051e+16,
+  "total_flos": 5.317568138938368e+16,
   "trial_name": null,
   "trial_params": null
 }