Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2510fa40919fc3d3b0e863aa34c5e35befaa3fd2d1ef2017dfb63e57462e782b
+oid sha256:ec1b6fa61d50899498832ece20a1ca2208f182783279c7d503d580ec9e5b53e8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8080881397ecd15e288dad2fdfd14b950a9df4bdb3b9b1421698c6db2cb59071
+oid sha256:a9fd49970899bd026502398621ea726b075a54601e5723ec0cc9c6b0d1840017
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e511691c1c60702224c5ca3c82328af0c41b6b7b13305562de4a4bff23df96c9
+oid sha256:b7042bdbd5d7c9a3eb673dc175e638e7b8ab24fef9447fe35d89ab1bc819bafe
 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": 0.006581445386659917,
+  "epoch": 0.00843775049571784,
   "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": 4.1778,
       "step": 35
+    },
+    {
+      "epoch": 0.006750200396574273,
+      "grad_norm": 18.384992599487305,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.5596,
+      "step": 40
+    },
+    {
+      "epoch": 0.006750200396574273,
+      "eval_loss": 1.176118016242981,
+      "eval_runtime": 222.9214,
+      "eval_samples_per_second": 11.192,
+      "eval_steps_per_second": 5.598,
+      "step": 40
+    },
+    {
+      "epoch": 0.007593975446146058,
+      "grad_norm": 23.817644119262695,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.7036,
+      "step": 45
+    },
+    {
+      "epoch": 0.00843775049571784,
+      "grad_norm": 18.593435287475586,
+      "learning_rate": 0.0,
+      "loss": 4.9152,
+      "step": 50
+    },
+    {
+      "epoch": 0.00843775049571784,
+      "eval_loss": 1.1747710704803467,
+      "eval_runtime": 222.5705,
+      "eval_samples_per_second": 11.21,
+      "eval_steps_per_second": 5.607,
+      "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": 7229762867036160.0,
+  "total_flos": 9157699631579136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null