Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93dabe7d67dc173f5c2a40253f7eb3ad9e0e1c5b36a26861b1e532ac078fc0ca
+oid sha256:f0c1ee7d47c7e39984510cdd1c4cbda06fa1640cf7e143bba612e86a82cc3dcf
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d5765e579f2ebcb335e581db671c13a4f71b9713196abc8519217de7181d38
+oid sha256:7ff4911ba19536d936d8f49a7ac7e0dcaefd3b7a2fe346d995b1576ec0ab93e2
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f5b8fc91a819fc39bd479452495c8f8f43e1c210ee91583af5c241cfc6079a
+oid sha256:ab25f1bb566d6940a6c530bc3bcd4512bcc2278b20c9a86ed24b271b2778f563
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32379924446842956,
+  "epoch": 0.4317323259579061,
   "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": 20.969,
       "eval_steps_per_second": 10.538,
       "step": 150
+    },
+    {
+      "epoch": 0.3453858607663249,
+      "grad_norm": 0.7738764882087708,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.5586,
+      "step": 160
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.8597546815872192,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.671,
+      "step": 170
+    },
+    {
+      "epoch": 0.38855909336211547,
+      "grad_norm": 0.7972836494445801,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.571,
+      "step": 180
+    },
+    {
+      "epoch": 0.4101457096600108,
+      "grad_norm": 0.7099116444587708,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.6595,
+      "step": 190
+    },
+    {
+      "epoch": 0.4317323259579061,
+      "grad_norm": 0.5930240154266357,
+      "learning_rate": 0.0,
+      "loss": 0.5227,
+      "step": 200
+    },
+    {
+      "epoch": 0.4317323259579061,
+      "eval_loss": 0.6163676381111145,
+      "eval_runtime": 9.3049,
+      "eval_samples_per_second": 20.957,
+      "eval_steps_per_second": 10.532,
+      "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": 4.7493062590464e+16,
+  "total_flos": 6.3324083453952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null