Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8dea4d325a4635d3c239e793bad657771e2130c83b3dfef9813d57f5058df9
+oid sha256:8f12882e795e48b5e34ae38b2a3dc13d970ae8ed794446b433b285dcae5e4b45
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a691a2dd0083ffd45de8f8ba46f1319a1176b01199ed67ae21c5b8f4c7c5d65a
+oid sha256:0f41bf5ac8dd82b27bccf99bb00806066e352c1bf853a1398026d130ed323742
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77af5db692d8169680b37a82ccaf2369394b341d2c152f145639fd25a259d63f
+oid sha256:1b5b7c38c3608ce56ea60cd8715a5aebe62a252c04517ce9587d7d3c27fbbbdf
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14206d6f39047b8dbff5f90ecc0ad71bc03ad9f0a166b1d0248ef5714395ce2a
+oid sha256:b60382b672a7ee5b1056446dd64188b841f33ae83dfad90e6f0c3d3114911f38
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 400,
-  "best_metric": 2.2951860427856445,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.43431053203040176,
+  "best_global_step": 600,
+  "best_metric": 2.2626566886901855,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.6514657980456026,
   "eval_steps": 200,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,42 @@
       "eval_samples_per_second": 81.949,
       "eval_steps_per_second": 2.586,
       "step": 400
+    },
+    {
+      "epoch": 0.48859934853420195,
+      "grad_norm": 0.6011854410171509,
+      "learning_rate": 0.00018951481098083322,
+      "loss": 2.2901,
+      "step": 450
+    },
+    {
+      "epoch": 0.5428881650380022,
+      "grad_norm": 0.6126257181167603,
+      "learning_rate": 0.00018678530414333524,
+      "loss": 2.3023,
+      "step": 500
+    },
+    {
+      "epoch": 0.5971769815418024,
+      "grad_norm": 0.6901931762695312,
+      "learning_rate": 0.00018376495001023636,
+      "loss": 2.2943,
+      "step": 550
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "grad_norm": 0.6403626203536987,
+      "learning_rate": 0.00018046387082331516,
+      "loss": 2.2696,
+      "step": 600
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "eval_loss": 2.2626566886901855,
+      "eval_runtime": 7.335,
+      "eval_samples_per_second": 82.072,
+      "eval_steps_per_second": 2.59,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -108,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1185423411367117e+17,
+  "total_flos": 1.6793449133565542e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null