Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d3a0c0107f5816bb9de9d09cea285eb542031f67774ae9694cce5d71b146ad
+oid sha256:c360e553d157936718cf6be990e147d21346274ac808e87443ceef418127fde4
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b403382ec3cd3845c2b35f1a77e684479e586bceceb3cff6f1ccd4cb50b8bc7
+oid sha256:de4659248af871d8a5bc8618f52c5ea1baa9d060fad262290330351318b749ff
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83049c51a143a5f65a87d33e5b2532e7c39e6bd214a2a68aae1c7cf02b35b9d7
+oid sha256:815ec9236e78d8ac2fa18b52a6a75f823894c470f485337750679c813cd4c0ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea4678c53cc7838df809d52cc1412950e9b0dcea30908f808cd26e436e2acd3
+oid sha256:c794fb315dbb1d737ad184da5b30abdc3101c9a540dba62326f5d08191ea2bdb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5758654157230669,
+  "epoch": 0.5823358136525396,
   "eval_steps": 386,
-  "global_step": 445,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3138,6 +3138,41 @@
       "learning_rate": 9.737129810366952e-05,
       "loss": 0.8703,
       "step": 445
+    },
+    {
+      "epoch": 0.5771594953089615,
+      "grad_norm": 0.8351484537124634,
+      "learning_rate": 9.735808998885915e-05,
+      "loss": 0.9626,
+      "step": 446
+    },
+    {
+      "epoch": 0.578453574894856,
+      "grad_norm": 0.860819399356842,
+      "learning_rate": 9.734484967493282e-05,
+      "loss": 0.9061,
+      "step": 447
+    },
+    {
+      "epoch": 0.5797476544807506,
+      "grad_norm": 0.7928848266601562,
+      "learning_rate": 9.733157717089277e-05,
+      "loss": 0.9141,
+      "step": 448
+    },
+    {
+      "epoch": 0.581041734066645,
+      "grad_norm": 0.9132540822029114,
+      "learning_rate": 9.7318272485763e-05,
+      "loss": 0.7613,
+      "step": 449
+    },
+    {
+      "epoch": 0.5823358136525396,
+      "grad_norm": 0.7894258499145508,
+      "learning_rate": 9.730493562858953e-05,
+      "loss": 0.8234,
+      "step": 450
     }
   ],
   "logging_steps": 1,
@@ -3157,7 +3192,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.9748204140363776e+17,
+  "total_flos": 5.030717272621056e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null