Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8a5cfa008be2a3e66c86cfb075f6663d48bcc4314c01e4634109ab6193d664
+oid sha256:031d6aeb8a3af212966f78779e52e250ab2623db944ee625a1e46de52ca9ddca
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e500af2cb4ca1336ace8d46617ebf96b5aa12fe255f1316aac7dade674575ce
+oid sha256:00faf126bcc146d1d9b9fd48c4032a74b2d2e16a132ec3a8b950ac47a360c884
 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": 3.9519,
       "step": 35
+    },
+    {
+      "epoch": 0.016298258123663034,
+      "grad_norm": 13.718193054199219,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.3358,
+      "step": 40
+    },
+    {
+      "epoch": 0.016298258123663034,
+      "eval_loss": 1.0276206731796265,
+      "eval_runtime": 75.3406,
+      "eval_samples_per_second": 13.724,
+      "eval_steps_per_second": 6.862,
+      "step": 40
+    },
+    {
+      "epoch": 0.018335540389120913,
+      "grad_norm": 8.468703269958496,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.4373,
+      "step": 45
+    },
+    {
+      "epoch": 0.020372822654578793,
+      "grad_norm": 10.509159088134766,
+      "learning_rate": 0.0,
+      "loss": 4.6255,
+      "step": 50
+    },
+    {
+      "epoch": 0.020372822654578793,
+      "eval_loss": 1.0231385231018066,
+      "eval_runtime": 75.3527,
+      "eval_samples_per_second": 13.722,
+      "eval_steps_per_second": 6.861,
+      "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