Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0363b5b0f1521d630f471fe481b45c4b279ff9f81401d9f897b62b5a9b62b59e
+oid sha256:fda10e081a49b666d72784a18a66f01c23855013ce88f10fbea0b25d73eb4b43
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bbe6ef3cdd23f2bfab0199d2cd49b003a9bc33b07ad10cebac54ea7d2776a53
+oid sha256:ef7599c9537d68fec0554118dc152f3659739699f536f0201690b35ff3529ecf
 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": 0.0011010495260546432,
+  "epoch": 0.0014116019564803116,
   "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": 3.5494,
       "step": 35
+    },
+    {
+      "epoch": 0.0011292815651842494,
+      "grad_norm": 5.923633098602295,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.5106,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011292815651842494,
+      "eval_loss": 0.8934321403503418,
+      "eval_runtime": 1315.4296,
+      "eval_samples_per_second": 11.339,
+      "eval_steps_per_second": 5.67,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012704417608322806,
+      "grad_norm": 6.608625411987305,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.7016,
+      "step": 45
+    },
+    {
+      "epoch": 0.0014116019564803116,
+      "grad_norm": 5.440760135650635,
+      "learning_rate": 0.0,
+      "loss": 3.3832,
+      "step": 50
+    },
+    {
+      "epoch": 0.0014116019564803116,
+      "eval_loss": 0.8904063701629639,
+      "eval_runtime": 1315.2003,
+      "eval_samples_per_second": 11.34,
+      "eval_steps_per_second": 5.671,
+      "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": 6835412165197824.0,
+  "total_flos": 8763348929740800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null