Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22521e4ba949252646c8f1408918bf0de0a82c1aac569d59be6187115431b666
+oid sha256:ca04b2299c145c853e1432a5a6198722012a1d1edaeef342c37d90f34ab0641a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56930ecd8ca6eb7d02868aa236b71f1bfdb917d74a997c7b3d0b81052d976d08
+oid sha256:70d9302169ecc7af5559e14a5ec01e9ec1d71269bba3f41f92bc67bbe1885e9a
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc219238b72e832c7a2aaaa9e841df2fa4ab72c8b3dfd336609d01f6c6ad178
+oid sha256:e4776932fc8cfbfaf827b998218122fd854c542bb4c9b077bbb628a41d940b02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3da5b3ae9debb9fbcab0805794dfaab406f2d5635e0407c25e32749f5f7b455
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19715224534501644,
+  "epoch": 0.21905805038335158,
   "eval_steps": 5,
-  "global_step": 45,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 9.411,
       "eval_steps_per_second": 4.754,
       "step": 45
+    },
+    {
+      "epoch": 0.20153340635268346,
+      "grad_norm": 0.054891057312488556,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0059,
+      "step": 46
+    },
+    {
+      "epoch": 0.2059145673603505,
+      "grad_norm": 0.04845288023352623,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0045,
+      "step": 47
+    },
+    {
+      "epoch": 0.21029572836801752,
+      "grad_norm": 0.10850649327039719,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0181,
+      "step": 48
+    },
+    {
+      "epoch": 0.21467688937568455,
+      "grad_norm": 0.060124583542346954,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0067,
+      "step": 49
+    },
+    {
+      "epoch": 0.21905805038335158,
+      "grad_norm": 0.07994550466537476,
+      "learning_rate": 0.0,
+      "loss": 0.0124,
+      "step": 50
+    },
+    {
+      "epoch": 0.21905805038335158,
+      "eval_loss": 0.01418597437441349,
+      "eval_runtime": 10.3302,
+      "eval_samples_per_second": 9.39,
+      "eval_steps_per_second": 4.743,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -416,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.329215646662656e+16,
+  "total_flos": 3.69912849629184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null