Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd19cda316070d3e3f94fb918221600874ba04159c80c2a33c3c04232467f84a
+oid sha256:442df65564514e2bcc7df66b726bccb6f7b65ce3f32173d9990d94b218f2ac93
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7540bb3bb15bc56066f57aaafe396db9576b3b655ac225b282db08e427e01ef
+oid sha256:d0bbb2d63910d4363d4b34c60b543b0b2af5f1e4bd6e1f0600670083ca507c5e
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60b8b9947943f155a3901f3504f0eef1d1d3ba94a39b929f0b0d24b0e733ead
+oid sha256:b0c8a695403e170e19412286af76531e3897bf3a7407da89603c2bb763350ab1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023353835586499734,
+  "epoch": 0.02497736426363608,
   "eval_steps": 17,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -537,6 +537,34 @@
       "eval_samples_per_second": 21.744,
       "eval_steps_per_second": 2.718,
       "step": 187
+    },
+    {
+      "epoch": 0.023603609229136097,
+      "grad_norm": 0.19206172227859497,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.6255,
+      "step": 189
+    },
+    {
+      "epoch": 0.023978269693090637,
+      "grad_norm": 0.28804811835289,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.7236,
+      "step": 192
+    },
+    {
+      "epoch": 0.024352930157045177,
+      "grad_norm": 0.21254993975162506,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.5912,
+      "step": 195
+    },
+    {
+      "epoch": 0.024727590620999718,
+      "grad_norm": 0.23355689644813538,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.6693,
+      "step": 198
     }
   ],
   "logging_steps": 3,
@@ -551,12 +579,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0614987043110912e+17,
+  "total_flos": 1.1345629008415949e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null