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:e2136c8ff5d71ca7d4789a262ec5c8dd00233cb72deca905d9d5d40562524258
+oid sha256:c10d8742a96123bc4ec5bd0cb5add5c75bcaf287a550975b3053087e64d2a7c8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f5f00f91c0c013453d6be956b41a5568f541424ad55fbee8d6f14a22544462
+oid sha256:eafe6a6a23973cfd31482aa204d97a6bd87194a3a1a66d4a6b4798f359ec9766
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8328f1c10a87491f0acb3c77648996c536eb4221051fcbe3f1afbed534cac62
+oid sha256:7f7f2f359800d420c08376fc6ebde2ee65980d6cbc7f7b333ad138376863dbf7
 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": 0.0014193430988990992,
+  "epoch": 0.0018196706396142299,
   "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": 0.223,
       "step": 35
+    },
+    {
+      "epoch": 0.001455736511691384,
+      "grad_norm": 0.437232106924057,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3237,
+      "step": 40
+    },
+    {
+      "epoch": 0.001455736511691384,
+      "eval_loss": 0.31940722465515137,
+      "eval_runtime": 1166.033,
+      "eval_samples_per_second": 9.923,
+      "eval_steps_per_second": 4.961,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016377035756528068,
+      "grad_norm": 0.322145938873291,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2223,
+      "step": 45
+    },
+    {
+      "epoch": 0.0018196706396142299,
+      "grad_norm": 0.36519697308540344,
+      "learning_rate": 0.0,
+      "loss": 0.2629,
+      "step": 50
+    },
+    {
+      "epoch": 0.0018196706396142299,
+      "eval_loss": 0.3180951476097107,
+      "eval_runtime": 1172.1167,
+      "eval_samples_per_second": 9.871,
+      "eval_steps_per_second": 4.936,
+      "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": 1.1513537444708352e+16,
+  "total_flos": 1.479651398516736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null