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:ac07f1f175f453cfefd4ddee35c3e7ed2d367c6f48c1d57b55dc84149aafd2bd
+oid sha256:23e34dfe2b25658bdaa0bf87a91c122a77e50b16879f88df5a34a1680e00af92
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8efb47491de43c300c0f2797696fcf409f2756861230f5ad531fd1dfc61d230e
+oid sha256:676a05f2ae84b581cadafe3a25ba5446e8682addf24b2347104a5a642509d4a4
 size 9568884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b496b2d683f615cab7cf9d3d3d62d0da9eefb9481e332df819b1d2f3cd78f8fe
+oid sha256:d75878d450f8b56e1194c2e648caeda6a46a6de5fca326f17e1180c7d4d951ac
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630879f5e9b9f4eafdd5b8e94669b88a2fe5c5df3d0f91f82f7978e226047bfc
+oid sha256:44426dbe40f9521d80889e468939dbe72ea261a639a1d870a6eb675566451b20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819a139f220b1ee28bfe92139612448f42168577671e503f23038d2ae5fe8d17
+oid sha256:db031522d3b6733485b8f61dd537f02352bcf5798fabfd3d43422551c92eec42
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba45a4dbad6b21b2a703192126521fa6304032181770f459cc50f9534ebf31b
+oid sha256:bc39f874bb07429f8a565a2853b5e1a45eb52d1a11e23649fd21f57d6bf5ed2c
 size 15024

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": 0.057927961381359076,
+  "epoch": 0.07426661715558856,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,27 @@
       "eval_samples_per_second": 174.67,
       "eval_steps_per_second": 21.872,
       "step": 39
+    },
+    {
+      "epoch": 0.05941329372447085,
+      "grad_norm": 0.16342025995254517,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0029,
+      "step": 40
+    },
+    {
+      "epoch": 0.06683995544002971,
+      "grad_norm": 0.18511657416820526,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0015,
+      "step": 45
+    },
+    {
+      "epoch": 0.07426661715558856,
+      "grad_norm": 0.040974825620651245,
+      "learning_rate": 0.0,
+      "loss": 0.0012,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1388995338567680.0,
+  "total_flos": 1780763250917376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null