Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62d4b0647d1418cd1085889fd0a9afc812ac7bdef71d4c0ed8007b040501df1c
+oid sha256:4ee749c59d711d61b92c57c4d41b946f2e89fdd6873d8230dd34471a8fc5a588
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19548a393c378c8315c8d3e810b842b1e07d9fd17489d4b3cdba2a3eda438b74
+oid sha256:9be625eb8223eb7b9f106fc5883f1922a9a1eb6b62ef093725f5e168dd79b5a1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c1a9efc636b7b869b56b9a3c249a5137faaba5ff8c17f65984f4c6ae31ad9e
+oid sha256:c8c07670ce8c13a1c573ebda1e138b9cdd20b7c958607701a00698c7027abc81
 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": 0.01589080167057146,
+  "epoch": 0.020372822654578793,
   "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": 3.9542,
       "step": 35
+    },
+    {
+      "epoch": 0.016298258123663034,
+      "grad_norm": 14.647441864013672,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.3534,
+      "step": 40
+    },
+    {
+      "epoch": 0.016298258123663034,
+      "eval_loss": 1.0314518213272095,
+      "eval_runtime": 74.2852,
+      "eval_samples_per_second": 13.919,
+      "eval_steps_per_second": 6.96,
+      "step": 40
+    },
+    {
+      "epoch": 0.018335540389120913,
+      "grad_norm": 8.370624542236328,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.4477,
+      "step": 45
+    },
+    {
+      "epoch": 0.020372822654578793,
+      "grad_norm": 10.46690559387207,
+      "learning_rate": 0.0,
+      "loss": 4.6308,
+      "step": 50
+    },
+    {
+      "epoch": 0.020372822654578793,
+      "eval_loss": 1.0267705917358398,
+      "eval_runtime": 74.0879,
+      "eval_samples_per_second": 13.956,
+      "eval_steps_per_second": 6.978,
+      "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": 7405029845630976.0,
+  "total_flos": 9683500567363584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null