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:ab0d7ff46a1436d0267a0401c35acdf6111755fc3175befe6e3f9eccb62d1f68
+oid sha256:9749baa7622468e6b3a56f99324a359bc4e77ee91bc0f758501def80a7c29038
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6363bf6449cc8b8183888ceb7784ea055b2f79fc478db7f00d8e928bb5a49cf
+oid sha256:b8e093d8606ccaa85f9d061f88d5bdb56163f1cd3460ab37483359bb55b3d89a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c1a9efc636b7b869b56b9a3c249a5137faaba5ff8c17f65984f4c6ae31ad9e
+oid sha256:7b432d447d201080a8272bc495a7779d5eaf902f1c0a55b4fdb635a1cfc884b4
 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": 0.010608636518191092,
+  "epoch": 0.013600816048962938,
   "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": 1.3344,
       "step": 35
+    },
+    {
+      "epoch": 0.01088065283917035,
+      "grad_norm": 1.5634682178497314,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2248,
+      "step": 40
+    },
+    {
+      "epoch": 0.01088065283917035,
+      "eval_loss": 1.217478632926941,
+      "eval_runtime": 109.1101,
+      "eval_samples_per_second": 14.188,
+      "eval_steps_per_second": 7.094,
+      "step": 40
+    },
+    {
+      "epoch": 0.012240734444066644,
+      "grad_norm": 1.930158257484436,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.329,
+      "step": 45
+    },
+    {
+      "epoch": 0.013600816048962938,
+      "grad_norm": 1.5811973810195923,
+      "learning_rate": 0.0,
+      "loss": 1.3372,
+      "step": 50
+    },
+    {
+      "epoch": 0.013600816048962938,
+      "eval_loss": 1.211333155632019,
+      "eval_runtime": 109.0379,
+      "eval_samples_per_second": 14.197,
+      "eval_steps_per_second": 7.098,
+      "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": 7814408948416512.0,
+  "total_flos": 9848929621377024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null