Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be5438055ea40c57c749d84b7aecc3cf301c5479ddaf92895f19f5b06547046
+oid sha256:a330e0b6db208900b6e399aa0458ef64f60addab7b8ad364af10ba6b4b166898
 size 174616272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc518ebd678ec2ca935cd91c855ea71001eb22d8c7a40271b887b722a62c1cd9
+oid sha256:af53f2196422fb0c681520e351b28ae1cebe8417b1b52780b546b9079015feec
 size 88887179

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70e60def841c16ba8a8199bc6623c78efc0768849f2be1622d4191cc7397db4
+oid sha256:4a73006dd3b9a511097b2cc23228fdd2bcfc5bbd45bea564da56dbddb2ea452a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.48,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,62 @@
       "learning_rate": 2.0424e-05,
       "loss": 0.674065170288086,
       "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9938817620277405,
+      "learning_rate": 1.9824000000000002e-05,
+      "loss": 0.6814962005615235,
+      "step": 425
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.024253010749817,
+      "learning_rate": 1.9224e-05,
+      "loss": 0.6611297607421875,
+      "step": 450
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.974202036857605,
+      "learning_rate": 1.8624e-05,
+      "loss": 0.6642023468017578,
+      "step": 475
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.002221941947937,
+      "learning_rate": 1.8024e-05,
+      "loss": 0.6777601623535157,
+      "step": 500
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.0006694793701172,
+      "learning_rate": 1.7424e-05,
+      "loss": 0.6704077911376953,
+      "step": 525
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.020803689956665,
+      "learning_rate": 1.6824e-05,
+      "loss": 0.6599659729003906,
+      "step": 550
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0786882638931274,
+      "learning_rate": 1.6224e-05,
+      "loss": 0.6600012969970703,
+      "step": 575
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9785409569740295,
+      "learning_rate": 1.5624e-05,
+      "loss": 0.6729351043701172,
+      "step": 600
     }
   ],
   "logging_steps": 25,
@@ -139,7 +195,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.080841439827251e+16,
+  "total_flos": 3.128936745402547e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null