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:fa2b952e891237bbf49bf81ba049b1855ac1acb286dd8edac89d301df5840f0c
+oid sha256:37ec49ad5f6a3565ecade879d6c04d945a92d2aa0c6d1beee15bee1942e67853
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9513669e8c22515fe419accd8e5213d30cf0cf63263a9274f473b640b78c3db7
+oid sha256:7cfeae1d77d8eef3e5b78215d53c88061097f6dfd7a04a9b087dd277a27c3aae
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035fb21ad9439c20703c98781225d585364cea97e05e48374824cfdb1d700cc5
+oid sha256:9ace8383f7a7ec6d26f22d1d28eeb4b7d08704d4c7ee9741934de484a5ff739e
 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": 0.00041828999831075196,
+  "epoch": 0.0005362692286035282,
   "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": 0.8204,
       "step": 35
+    },
+    {
+      "epoch": 0.0004290153828828225,
+      "grad_norm": 10.329523086547852,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7724,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004290153828828225,
+      "eval_loss": 0.965052604675293,
+      "eval_runtime": 1695.5597,
+      "eval_samples_per_second": 23.153,
+      "eval_steps_per_second": 11.577,
+      "step": 40
+    },
+    {
+      "epoch": 0.00048264230574317533,
+      "grad_norm": 5.659180641174316,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.922,
+      "step": 45
+    },
+    {
+      "epoch": 0.0005362692286035282,
+      "grad_norm": 5.8149213790893555,
+      "learning_rate": 0.0,
+      "loss": 0.9943,
+      "step": 50
+    },
+    {
+      "epoch": 0.0005362692286035282,
+      "eval_loss": 0.9484821557998657,
+      "eval_runtime": 1666.1755,
+      "eval_samples_per_second": 23.562,
+      "eval_steps_per_second": 11.781,
+      "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": 2730712954306560.0,
+  "total_flos": 3496008304558080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null