Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066345d2441980c02f3c476d10d2509bf43116518e00b6e621d39a896e373b24
+oid sha256:85cba4814f429cb77927f341895ba5921519a5097cfc5dd7ee984c7e0ff819db
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa6ec58820ac11b4428b02e2e07fb38486df4b886aa6705cd053dd752e83b7e
+oid sha256:092409dcdd11ef773950b2ab00d310d9021616991487be1d68b30023d863267d
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c7af0c928fdcc0d5052f7ecd28b407f46c40c36dcaf7ab51bd8ba421ff3920
+oid sha256:844fbd3d467f0640ba6a8563e377765306846b3d1e3b996e57d44fe34907b25f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03907815631262525,
+  "epoch": 0.050100200400801605,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 11.9261,
       "step": 35
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.2519756257534027,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9256,
+      "step": 40
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "eval_loss": 11.922998428344727,
+      "eval_runtime": 12.4912,
+      "eval_samples_per_second": 33.704,
+      "eval_steps_per_second": 16.892,
+      "step": 40
+    },
+    {
+      "epoch": 0.045090180360721446,
+      "grad_norm": 0.24407736957073212,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9222,
+      "step": 45
+    },
+    {
+      "epoch": 0.050100200400801605,
+      "grad_norm": 0.25673621892929077,
+      "learning_rate": 0.0,
+      "loss": 11.9223,
+      "step": 50
+    },
+    {
+      "epoch": 0.050100200400801605,
+      "eval_loss": 11.922431945800781,
+      "eval_runtime": 12.2926,
+      "eval_samples_per_second": 34.248,
+      "eval_steps_per_second": 17.165,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9762162868224.0,
+  "total_flos": 12515593420800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null