Training in progress, step 445, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9779fb5aa80e5aa5419bba076caa89514a108718bdd23116ef4bf476d3b9c8
+oid sha256:06d3a0c0107f5816bb9de9d09cea285eb542031f67774ae9694cce5d71b146ad
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391bfb6ac94c63f7d6128408c737f45e0c7892c2a2b949443e80fa50e52edcff
+oid sha256:6b403382ec3cd3845c2b35f1a77e684479e586bceceb3cff6f1ccd4cb50b8bc7
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22180da8d1636aa73032f3645d9cd1697f1e0443328b03f72dfc859c0ada238
+oid sha256:83049c51a143a5f65a87d33e5b2532e7c39e6bd214a2a68aae1c7cf02b35b9d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ede706d34f67ff27af705e3a217dd4b9f1e883ef465d130d62c35a9e9452d7
+oid sha256:eea4678c53cc7838df809d52cc1412950e9b0dcea30908f808cd26e436e2acd3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5693950177935944,
+  "epoch": 0.5758654157230669,
   "eval_steps": 386,
-  "global_step": 440,
+  "global_step": 445,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3103,6 +3103,41 @@
       "learning_rate": 9.743685537743856e-05,
       "loss": 0.7948,
       "step": 440
+    },
+    {
+      "epoch": 0.5706890973794888,
+      "grad_norm": 0.8117014169692993,
+      "learning_rate": 9.742380839247425e-05,
+      "loss": 0.9382,
+      "step": 441
+    },
+    {
+      "epoch": 0.5719831769653834,
+      "grad_norm": 0.8515580296516418,
+      "learning_rate": 9.741072916371157e-05,
+      "loss": 0.9202,
+      "step": 442
+    },
+    {
+      "epoch": 0.5732772565512779,
+      "grad_norm": 0.8774899244308472,
+      "learning_rate": 9.739761770004318e-05,
+      "loss": 0.9129,
+      "step": 443
+    },
+    {
+      "epoch": 0.5745713361371725,
+      "grad_norm": 0.7189667820930481,
+      "learning_rate": 9.738447401038367e-05,
+      "loss": 0.7392,
+      "step": 444
+    },
+    {
+      "epoch": 0.5758654157230669,
+      "grad_norm": 0.7225956916809082,
+      "learning_rate": 9.737129810366952e-05,
+      "loss": 0.8703,
+      "step": 445
     }
   ],
   "logging_steps": 1,
@@ -3122,7 +3157,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.918923555451699e+17,
+  "total_flos": 4.9748204140363776e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null