Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be6cfe8739e42f10532a9fb1000e79850c23cf8328bca1ef035214eba9d359a
+oid sha256:4233c5b0ceb702f80ac44329886a8258a0e3e495c1e0c3b429d09a24ea5fec00
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30642f462ce258be1e8deb06c2bad7eb1333b2715398c12c27bfbf8cff7be7f6
+oid sha256:618301d0f61ac9e5f92e3b9989c9e9ae275e5c0afd329cc31db80bc2ca95f6c9
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89125b381bd706e47d0969ca57bde232385b184bb6fee985c4b095b282bae7af
+oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
 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": 0.035511040291372635,
+  "epoch": 0.04552697473252902,
   "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": 1.6025,
       "step": 35
+    },
+    {
+      "epoch": 0.03642157978602322,
+      "grad_norm": 8.27290153503418,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9629,
+      "step": 40
+    },
+    {
+      "epoch": 0.03642157978602322,
+      "eval_loss": 1.8377580642700195,
+      "eval_runtime": 37.3981,
+      "eval_samples_per_second": 12.38,
+      "eval_steps_per_second": 6.204,
+      "step": 40
+    },
+    {
+      "epoch": 0.04097427725927612,
+      "grad_norm": 10.21114444732666,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7723,
+      "step": 45
+    },
+    {
+      "epoch": 0.04552697473252902,
+      "grad_norm": 8.158187866210938,
+      "learning_rate": 0.0,
+      "loss": 1.9387,
+      "step": 50
+    },
+    {
+      "epoch": 0.04552697473252902,
+      "eval_loss": 1.8228884935379028,
+      "eval_runtime": 37.2908,
+      "eval_samples_per_second": 12.416,
+      "eval_steps_per_second": 6.221,
+      "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": 7453256523448320.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null