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:dfc85162a35ec74086fd8d5dcbc51fcfb79a3767e9737cfde818c6135d996e70
+oid sha256:e7a2068be50d459f3c9e91f568c6737ff6f5d89da89b0a308b27a721c82860e3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39022d8d185266a49dcefab0bd650bb62a1277e11c0e5a8a291de760656012fb
+oid sha256:c515e9f25831e50a396bf298c5c533fe8ff3f1967118d9ffbe83067d74639e82
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.015522388059701492,
+  "epoch": 0.01990049751243781,
   "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": 4.3175,
       "step": 35
+    },
+    {
+      "epoch": 0.015920398009950248,
+      "grad_norm": 8.222445487976074,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.979,
+      "step": 40
+    },
+    {
+      "epoch": 0.015920398009950248,
+      "eval_loss": 4.122116565704346,
+      "eval_runtime": 71.9841,
+      "eval_samples_per_second": 14.698,
+      "eval_steps_per_second": 7.349,
+      "step": 40
+    },
+    {
+      "epoch": 0.01791044776119403,
+      "grad_norm": 7.3780436515808105,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.1388,
+      "step": 45
+    },
+    {
+      "epoch": 0.01990049751243781,
+      "grad_norm": 7.28754997253418,
+      "learning_rate": 0.0,
+      "loss": 4.1384,
+      "step": 50
+    },
+    {
+      "epoch": 0.01990049751243781,
+      "eval_loss": 4.111135959625244,
+      "eval_runtime": 71.766,
+      "eval_samples_per_second": 14.742,
+      "eval_steps_per_second": 7.371,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null