Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8915e517418e97b5c0dfb3779664d2c40b45665f64d48eb60d1382ec12d8cde9
+oid sha256:fb64cb3129d710a1751a01f4acbd1c058ac5b0e12f521112fcd5f217bb347bdd
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85624fa52d7ffe7f93b2576f3a9ef9539986c75b102284f236abe1a7e157ae84
+oid sha256:d3f1dc710e988b292d31154e2c7a36e9bc0e9a5e04e56ee5a1d294fe97706b91
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d1775f05b594bce7d5b393be72148726e66c23321342a55f0e172135811102
+oid sha256:12b2e94af90606a3af598219d73b8a827ed1198d20bd9c1b578a013f0d5cbfc8
 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": 0.03474222015791918,
+  "epoch": 0.03715745471435207,
   "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": 32.544,
       "eval_steps_per_second": 4.071,
       "step": 187
+    },
+    {
+      "epoch": 0.035113794705062706,
+      "grad_norm": 0.7612324357032776,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.6608,
+      "step": 189
+    },
+    {
+      "epoch": 0.035671156525777986,
+      "grad_norm": 0.7436925768852234,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.7133,
+      "step": 192
+    },
+    {
+      "epoch": 0.036228518346493266,
+      "grad_norm": 0.7385342717170715,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.7906,
+      "step": 195
+    },
+    {
+      "epoch": 0.036785880167208546,
+      "grad_norm": 0.8410016298294067,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.7085,
+      "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": 6.567372765580493e+16,
+  "total_flos": 7.020295025275699e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null