Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6c4161c4dd3dc9b4e9a5d44d5a18d575588576042850228add9672b4d54ab9
+oid sha256:829f106fd55b2912b7f5c5f264cc910970bb6011b6377b65f97fbf91500648a6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3cce985cc9676723ff347ed5321611961dfc7286ee38d0988d4701435a69d8c
+oid sha256:eef0ea7e26d4551860bf0154f1234febb3373aab3e4ef7adf8b56f28415a8217
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.0006015339114742594,
+  "epoch": 0.0007711973224028966,
   "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": 1.5411,
       "step": 35
+    },
+    {
+      "epoch": 0.0006169578579223173,
+      "grad_norm": 4.415103912353516,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.542,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006169578579223173,
+      "eval_loss": 1.4406354427337646,
+      "eval_runtime": 2262.4038,
+      "eval_samples_per_second": 12.066,
+      "eval_steps_per_second": 6.033,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006940775901626069,
+      "grad_norm": 2.8680806159973145,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3983,
+      "step": 45
+    },
+    {
+      "epoch": 0.0007711973224028966,
+      "grad_norm": 2.7566418647766113,
+      "learning_rate": 0.0,
+      "loss": 1.3613,
+      "step": 50
+    },
+    {
+      "epoch": 0.0007711973224028966,
+      "eval_loss": 1.43626070022583,
+      "eval_runtime": 2265.8907,
+      "eval_samples_per_second": 12.048,
+      "eval_steps_per_second": 6.024,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null