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:f82e2219e84cdc17e82479a4414ea9f995c9e069051c3c46a1108926139e568d
+oid sha256:e267fbb042d3d59301d0ef7b397bd6003613a16e163d64e2fae9bbc5af2dfb95
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf89c3c3061eb0a996cb848c6d7a37f09cbc9892c5f84977813d179203309a7
+oid sha256:c24a10a944a221d168e2e179f477d4be2583e0a3606b3c552cf305c36db60032
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f787b29bf216c0d76e55c689c8d0c8006e3b368e87bba3ec06a3d6ca7897c8cd
+oid sha256:9ae74ed5d8d7aa05e9979453feeae1039a93fc9dab62d2c41cef08e8a6ffd3dd
 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": 0.04529616724738676,
+  "epoch": 0.05807200929152149,
   "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": 0.7803,
       "step": 35
+    },
+    {
+      "epoch": 0.04645760743321719,
+      "grad_norm": 5.1860737800598145,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5171,
+      "step": 40
+    },
+    {
+      "epoch": 0.04645760743321719,
+      "eval_loss": 0.40528592467308044,
+      "eval_runtime": 14.0812,
+      "eval_samples_per_second": 25.779,
+      "eval_steps_per_second": 12.925,
+      "step": 40
+    },
+    {
+      "epoch": 0.05226480836236934,
+      "grad_norm": 5.927870273590088,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3046,
+      "step": 45
+    },
+    {
+      "epoch": 0.05807200929152149,
+      "grad_norm": 3.9271230697631836,
+      "learning_rate": 0.0,
+      "loss": 0.4715,
+      "step": 50
+    },
+    {
+      "epoch": 0.05807200929152149,
+      "eval_loss": 0.34220945835113525,
+      "eval_runtime": 13.9897,
+      "eval_samples_per_second": 25.948,
+      "eval_steps_per_second": 13.01,
+      "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": 556247568875520.0,
+  "total_flos": 713531364212736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null