Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3174c4bceaf17c6fd8f91ab665d33e290f8891a668106cea81878598fee3b6d0
+oid sha256:d5eb50ec1e00c8d244ca1da9812e341ebdf5fadf6c0a200b9ca956a8a41127c9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6bd8afc04fd637da65c302c81bc4900d8c52922894cc13b5a4a82ca73a8665
+oid sha256:9e72cdd53f7ec59d3d113dc7aca779c60e18f88458dcd03dfd84054784b7cbe1
 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": 0.007976275692811126,
+  "epoch": 0.010225994477962982,
   "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": 0.1435,
       "step": 35
+    },
+    {
+      "epoch": 0.008180795582370386,
+      "grad_norm": 0.042203761637210846,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1276,
+      "step": 40
+    },
+    {
+      "epoch": 0.008180795582370386,
+      "eval_loss": 0.13725407421588898,
+      "eval_runtime": 140.2588,
+      "eval_samples_per_second": 14.68,
+      "eval_steps_per_second": 7.344,
+      "step": 40
+    },
+    {
+      "epoch": 0.009203395030166683,
+      "grad_norm": 0.029296882450580597,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1244,
+      "step": 45
+    },
+    {
+      "epoch": 0.010225994477962982,
+      "grad_norm": 0.0394265353679657,
+      "learning_rate": 0.0,
+      "loss": 0.1291,
+      "step": 50
+    },
+    {
+      "epoch": 0.010225994477962982,
+      "eval_loss": 0.1366967409849167,
+      "eval_runtime": 139.8716,
+      "eval_samples_per_second": 14.721,
+      "eval_steps_per_second": 7.364,
+      "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