Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3506cf268e0620f9e639dc32e30e18ded892d1220776dfe11f11c62e375741
+oid sha256:368f3743f12c66e1c8fd9c80d129e71bc486e7b8dd9d279aa86f30cb40684c22
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9f59ceb6258c1e8dff594a418e54bf947c4c938cc7e6ca23d35743fc0c7399
+oid sha256:0348caf9146aa158455cbde43a37ddd770ae9f8bf5be91ed8d50145fea413278
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545ed9b26ef45d3c09c64e53bca6166da38654567e84bc6ae8dec6c5ac8c7de5
+oid sha256:6abbfa748829994b73c81874e366bcd6bc4e73f496917f551661f274d6a54f52
 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": 0.013189042948934731,
+  "epoch": 0.016909029421711193,
   "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": 0.2444,
       "step": 35
+    },
+    {
+      "epoch": 0.013527223537368955,
+      "grad_norm": 5.653206825256348,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1572,
+      "step": 40
+    },
+    {
+      "epoch": 0.013527223537368955,
+      "eval_loss": 0.27314549684524536,
+      "eval_runtime": 56.0294,
+      "eval_samples_per_second": 22.22,
+      "eval_steps_per_second": 11.119,
+      "step": 40
+    },
+    {
+      "epoch": 0.015218126479540075,
+      "grad_norm": 7.612532615661621,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2223,
+      "step": 45
+    },
+    {
+      "epoch": 0.016909029421711193,
+      "grad_norm": 2.5386624336242676,
+      "learning_rate": 0.0,
+      "loss": 0.1316,
+      "step": 50
+    },
+    {
+      "epoch": 0.016909029421711193,
+      "eval_loss": 0.2503856122493744,
+      "eval_runtime": 55.5128,
+      "eval_samples_per_second": 22.427,
+      "eval_steps_per_second": 11.223,
+      "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": 2800285258874880.0,
+  "total_flos": 3582973685268480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null