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:fcf5d0b76cc1c294d9b93d2adf150a4249df0c05abf194569df1f968f278e6d6
+oid sha256:d4078ddda77d9cf988aaa8d8d79506a8375eb72fae269c77fb8ffb6f4f3a170f
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0487ad0bf0060e91fc475f1ad2c6dc8aabe9f249c5c0af7a55edfceed33b3969
+oid sha256:ed76acf474a4bea362c5fa45003cae12aa34d27879b86dd8e1548d5940b47d27
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b925f41b93ae978efc363ec176c67bd523156ae2461120bbde365bcfec0fe9
+oid sha256:41dd8f1c6cda4d03a8c80cccd9bb3b4abfaf15090577dd9d9134cf8078750727
 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": 0.0012827048627670247,
+  "epoch": 0.0016444934138038778,
   "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": 1.626,
       "step": 35
+    },
+    {
+      "epoch": 0.0013155947310431021,
+      "grad_norm": 4.014774799346924,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9754,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013155947310431021,
+      "eval_loss": 1.7362017631530762,
+      "eval_runtime": 2024.1009,
+      "eval_samples_per_second": 6.325,
+      "eval_steps_per_second": 3.162,
+      "step": 40
+    },
+    {
+      "epoch": 0.00148004407242349,
+      "grad_norm": 3.1109697818756104,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8761,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016444934138038778,
+      "grad_norm": 4.039634704589844,
+      "learning_rate": 0.0,
+      "loss": 1.6882,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016444934138038778,
+      "eval_loss": 1.7280974388122559,
+      "eval_runtime": 2023.8579,
+      "eval_samples_per_second": 6.326,
+      "eval_steps_per_second": 3.163,
+      "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": 1.490651304689664e+16,
+  "total_flos": 1.9110914162688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null