Training in progress, step 595, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82629658711d670f84c7a7fc3a20ba8e3dcbc990f244c9299b86f85a744188c
+oid sha256:c35efd6027c46ea303ace3ca2fc857edaf9a717f2a0a10234aa34b94e9c5e0d3
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c7d1bd3550ec241db41c3448c71d17115a04af1f8a9aec77a08e12d754aa86
+oid sha256:a991f10ff23690bf025824285b1b3419a2f2f666189339cade465a8ddecabee4
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afbf82d3230b609b502d55d64659ac6e6c22197c8cac1b28cdebcd6c48a1b49
+oid sha256:85e48d9ae6181493bd3b8a928b8a13d1634e32359d372bd3fa8e0dd035c5302b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a008bced67f47328a54ecc4a98a10481a4ca06770d461c44cbc5f85912d24c
+oid sha256:61e4d9141381fe9ddfc2a83c3eaf7e360c528de29b24838d2596dc4ab7ca60c6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7635069556777742,
+  "epoch": 0.7699773536072468,
   "eval_steps": 386,
-  "global_step": 590,
+  "global_step": 595,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4153,6 +4153,41 @@
       "learning_rate": 9.512482595387132e-05,
       "loss": 0.9836,
       "step": 590
+    },
+    {
+      "epoch": 0.7648010352636687,
+      "grad_norm": 0.6959390640258789,
+      "learning_rate": 9.510705372583118e-05,
+      "loss": 0.8525,
+      "step": 591
+    },
+    {
+      "epoch": 0.7660951148495633,
+      "grad_norm": 0.6348171234130859,
+      "learning_rate": 9.50892508291713e-05,
+      "loss": 0.7776,
+      "step": 592
+    },
+    {
+      "epoch": 0.7673891944354578,
+      "grad_norm": 1.0133094787597656,
+      "learning_rate": 9.507141727599602e-05,
+      "loss": 0.8943,
+      "step": 593
+    },
+    {
+      "epoch": 0.7686832740213523,
+      "grad_norm": 0.8890700340270996,
+      "learning_rate": 9.50535530784305e-05,
+      "loss": 0.9169,
+      "step": 594
+    },
+    {
+      "epoch": 0.7699773536072468,
+      "grad_norm": 0.7059516310691833,
+      "learning_rate": 9.503565824862076e-05,
+      "loss": 0.7544,
+      "step": 595
     }
   ],
   "logging_steps": 1,
@@ -4172,7 +4207,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.595829312992051e+17,
+  "total_flos": 6.65172617157673e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null