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:a9ba578449ca3620199bfa568d92693be96bf5f8a8e5640bf989dcb2283c5095
+oid sha256:96718e58b0af181cf3ffc48939fa20d3b55098d572c756c1e21a1e90a8dae6e7
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d591063359492482634b664bfcfce6f82469778b43e026b3f7bdad58813ce784
+oid sha256:ec88a2653b21239349885b9283e8056a208513a5571fa5b28771294bc0a5a225
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.006592570679964501,
+  "epoch": 0.008452013692262181,
   "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": 10.3625,
       "step": 35
+    },
+    {
+      "epoch": 0.006761610953809745,
+      "grad_norm": 0.11446528136730194,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3597,
+      "step": 40
+    },
+    {
+      "epoch": 0.006761610953809745,
+      "eval_loss": 10.359040260314941,
+      "eval_runtime": 14.3392,
+      "eval_samples_per_second": 173.719,
+      "eval_steps_per_second": 86.895,
+      "step": 40
+    },
+    {
+      "epoch": 0.0076068123230359636,
+      "grad_norm": 0.10877200216054916,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3589,
+      "step": 45
+    },
+    {
+      "epoch": 0.008452013692262181,
+      "grad_norm": 0.11139176040887833,
+      "learning_rate": 0.0,
+      "loss": 10.3584,
+      "step": 50
+    },
+    {
+      "epoch": 0.008452013692262181,
+      "eval_loss": 10.358901023864746,
+      "eval_runtime": 14.1036,
+      "eval_samples_per_second": 176.622,
+      "eval_steps_per_second": 88.347,
+      "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": 633614499840.0,
+  "total_flos": 808181760000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null