Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd0920a0a2b2a375b29a323167ca4a31a857f68d2b65debf8a9882fa5ae31fe
+oid sha256:98f833bc1311d51535e9ed4e4847f5397d63df02d0cee27d28080ff18fd03df5
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed88f63287e232eb699cca9a15ff2216b1e94501bff2fb865957b466aea38a59
+oid sha256:9c39a2e128f8c949eaaea84a21ca5cbad58546981005544259eddeb277df7064
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456da919d39e466c3bd01b5900d133fdaee5040879b60691cd49c4faed6eba19
+oid sha256:97ad8011d23bb31a56a8497a797afca3296b8c39e7823e6ef869307fa2dbbb17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007571360068646998,
+  "epoch": 0.010095146758195997,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 17.925,
       "eval_steps_per_second": 8.962,
       "step": 150
+    },
+    {
+      "epoch": 0.008076117406556798,
+      "grad_norm": 0.45891937613487244,
+      "learning_rate": 0.0002,
+      "loss": 2.0011,
+      "step": 160
+    },
+    {
+      "epoch": 0.008580874744466598,
+      "grad_norm": 0.3792056441307068,
+      "learning_rate": 0.0002,
+      "loss": 1.9976,
+      "step": 170
+    },
+    {
+      "epoch": 0.009085632082376397,
+      "grad_norm": 0.41122955083847046,
+      "learning_rate": 0.0002,
+      "loss": 1.981,
+      "step": 180
+    },
+    {
+      "epoch": 0.009590389420286198,
+      "grad_norm": 0.445315420627594,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 190
+    },
+    {
+      "epoch": 0.010095146758195997,
+      "grad_norm": 0.4807380735874176,
+      "learning_rate": 0.0002,
+      "loss": 1.9983,
+      "step": 200
+    },
+    {
+      "epoch": 0.010095146758195997,
+      "eval_loss": 2.010718584060669,
+      "eval_runtime": 465.4569,
+      "eval_samples_per_second": 17.922,
+      "eval_steps_per_second": 8.961,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.320737721909248e+16,
+  "total_flos": 3.077232615358464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null