Training in progress, step 610, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b390cff10ccb0462e2ce56478461d8e6338b504fc23e78bc158e0819d8dc9de
+oid sha256:32edca6079f3b9484783f232ac0ccb1d340292cb18066f64fd7821f34d446723
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286cc2bd89d71803d1810c6df9f8f1ffd3acec5c70032db2dcefd9830c184d3f
+oid sha256:fd94789a924990bbe5fdd71e1ae4a4ed24b474b41e969e7e388565234d65aee6
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a876f1e76952adad9028628bf8945815972da7c35421764155ece90dc00dd324
+oid sha256:609743375850d853d6f9c3893828fefdf1e7c4e4f00a29e837453857db0e6e70
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0544bca5420fca1dbd853da9c587baf2b7fb350e9011928f11101b6ff88e6e56
+oid sha256:7f797c771cc3ef7f2bb02c5a7bc50a7c409a56da80db274d374a4aaeeeecf121
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7829181494661922,
+  "epoch": 0.7893885473956649,
   "eval_steps": 386,
-  "global_step": 605,
+  "global_step": 610,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4258,6 +4258,41 @@
       "learning_rate": 9.485502786409107e-05,
       "loss": 1.0692,
       "step": 605
+    },
+    {
+      "epoch": 0.7842122290520867,
+      "grad_norm": 0.733768105506897,
+      "learning_rate": 9.483679688718135e-05,
+      "loss": 0.8835,
+      "step": 606
+    },
+    {
+      "epoch": 0.7855063086379812,
+      "grad_norm": 0.7453616261482239,
+      "learning_rate": 9.481853542540154e-05,
+      "loss": 0.7778,
+      "step": 607
+    },
+    {
+      "epoch": 0.7868003882238758,
+      "grad_norm": 0.8596757650375366,
+      "learning_rate": 9.480024349116771e-05,
+      "loss": 0.9711,
+      "step": 608
+    },
+    {
+      "epoch": 0.7880944678097703,
+      "grad_norm": 0.6516830325126648,
+      "learning_rate": 9.478192109691674e-05,
+      "loss": 0.8342,
+      "step": 609
+    },
+    {
+      "epoch": 0.7893885473956649,
+      "grad_norm": 0.8740130662918091,
+      "learning_rate": 9.476356825510612e-05,
+      "loss": 0.9179,
+      "step": 610
     }
   ],
   "logging_steps": 1,
@@ -4277,7 +4312,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.763519888746086e+17,
+  "total_flos": 6.819416747330765e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null