Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a3eea9d1fa6290220cf46b07fb62985e27093d257e77a48314f73c0764625f
+oid sha256:93fc1c475c67deccfc9fedf9532cd31c5a80821693d62383c3cc6240ae81119e
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153e2d49ba9ba2ccfbf3bfae08347b3f0f38d757bcccfe7fa79912f2e02a5be4
+oid sha256:c72bfe6df38d31747971d88448110b98ec5ce45079ee99b0b2f20fbce0c4ed23
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92ff51f2aa2d47f51b12f0f0bb45e8de9788980d700a69cb0111b82a788b793
+oid sha256:c194e1392a42c2eda06336d0305e55c4adfb29a6e43a5dec7cc518e3e72b0450
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51094b5d327949483be134a2a7ce82f120d34a302bf097e81122d94eff7cf8c6
+oid sha256:64297a6969c9113e6582dde9428f08d78a5599aec9c2adf99caa5d81625685a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1063406312197896,
+  "epoch": 0.11373329542223486,
   "eval_steps": 34,
-  "global_step": 374,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -971,6 +971,69 @@
       "eval_samples_per_second": 35.237,
       "eval_steps_per_second": 4.408,
       "step": 374
+    },
+    {
+      "epoch": 0.10662496445834518,
+      "grad_norm": 0.46795177459716797,
+      "learning_rate": 5.052336989433082e-07,
+      "loss": 0.4216,
+      "step": 375
+    },
+    {
+      "epoch": 0.10747796417401194,
+      "grad_norm": 0.560074508190155,
+      "learning_rate": 3.915515781850565e-07,
+      "loss": 0.4089,
+      "step": 378
+    },
+    {
+      "epoch": 0.10833096388967871,
+      "grad_norm": 0.5042891502380371,
+      "learning_rate": 2.922400983217416e-07,
+      "loss": 0.4484,
+      "step": 381
+    },
+    {
+      "epoch": 0.10918396360534546,
+      "grad_norm": 0.4858133792877197,
+      "learning_rate": 2.0735725446094923e-07,
+      "loss": 0.4354,
+      "step": 384
+    },
+    {
+      "epoch": 0.11003696332101223,
+      "grad_norm": 0.5573092103004456,
+      "learning_rate": 1.3695261579316777e-07,
+      "loss": 0.3903,
+      "step": 387
+    },
+    {
+      "epoch": 0.11088996303667899,
+      "grad_norm": 0.4502072334289551,
+      "learning_rate": 8.106729664475176e-08,
+      "loss": 0.416,
+      "step": 390
+    },
+    {
+      "epoch": 0.11174296275234574,
+      "grad_norm": 0.5383118987083435,
+      "learning_rate": 3.9733932468333234e-08,
+      "loss": 0.4726,
+      "step": 393
+    },
+    {
+      "epoch": 0.11259596246801251,
+      "grad_norm": 0.6252465844154358,
+      "learning_rate": 1.297666078462767e-08,
+      "loss": 0.4435,
+      "step": 396
+    },
+    {
+      "epoch": 0.11344896218367927,
+      "grad_norm": 0.5062450170516968,
+      "learning_rate": 8.111070868010995e-10,
+      "loss": 0.373,
+      "step": 399
     }
   ],
   "logging_steps": 3,
@@ -985,12 +1048,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.197680065857454e+17,
+  "total_flos": 1.280941246906368e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null