Training in progress, step 305, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a71f452e39be42f226077fc02ef1d9cd35fb105385d0893e5923d2ba4da0414
+oid sha256:5f85ee4007de30cce47e53502885ad7a6303b7507013ef2ac0c367abd0d2db62
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603fc44dc0dcc7e55622ab39fe350be7bf496843a61f644202a9539169eb455c
+oid sha256:98ccbba4e80f30bfb9eb8ba273a60067269331eebe7952e1fad15758917114fc
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8920f2a4268bc4fce4895714a93f0d42f4b23ede61ecccf586bc2a1a8d9321
+oid sha256:87f85da328c2d350b694213a4eb2a046df41e793247213e45a460c5007fc25d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad7fafc1af8d86c13379f526e0cfbac632a863b9b0610d9ebb41405c99da8a8
+oid sha256:c9ae4e393408096742838e5dcf898dde9c63683742cac0999c60bedcf0debf4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38822387576835976,
+  "epoch": 0.39469427369783244,
   "eval_steps": 386,
-  "global_step": 300,
+  "global_step": 305,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2115,6 +2115,41 @@
       "learning_rate": 9.894140129553981e-05,
       "loss": 0.8469,
       "step": 300
+    },
+    {
+      "epoch": 0.38951795535425426,
+      "grad_norm": 0.8275448083877563,
+      "learning_rate": 9.893294587985843e-05,
+      "loss": 0.8295,
+      "step": 301
+    },
+    {
+      "epoch": 0.3908120349401488,
+      "grad_norm": 0.9197372198104858,
+      "learning_rate": 9.892445719430493e-05,
+      "loss": 0.9363,
+      "step": 302
+    },
+    {
+      "epoch": 0.3921061145260433,
+      "grad_norm": 0.7137726545333862,
+      "learning_rate": 9.891593524465083e-05,
+      "loss": 0.8207,
+      "step": 303
+    },
+    {
+      "epoch": 0.3934001941119379,
+      "grad_norm": 0.9908462762832642,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.9287,
+      "step": 304
+    },
+    {
+      "epoch": 0.39469427369783244,
+      "grad_norm": 1.0070343017578125,
+      "learning_rate": 9.889879157624002e-05,
+      "loss": 1.2092,
+      "step": 305
     }
   ],
   "logging_steps": 1,
@@ -2134,7 +2169,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.353811515080704e+17,
+  "total_flos": 3.4097083736653824e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null