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:acac4ca303b0458f4fe07a1aee3c0a55716ff9b88155be4c27e0d813e6e2f7b1
+oid sha256:679e43eb88826fda7fe65c6730acfc21525204b4abd339a751f987ab4174e979
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a583cc0858d83456cc4fc52c9ffc80cc92f9bc01e4893e1c65a040c2016a27c7
+oid sha256:b592638c142dd9f3d7b1d289d59e922ffd9f45fc5294582fe16369bf83a38d90
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944fe94c0494d2a85ccff394bd6aba27772336200e013252b50fe03d2f0feeb7
+oid sha256:f8f2f23a60a98dd8319238620ff65e8c82b6e0a3bf30ce73cacdc27a598f02f8
 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": 0.07890743550834597,
+  "epoch": 0.10116337885685382,
   "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": 0.2376,
       "step": 35
+    },
+    {
+      "epoch": 0.08093070308548306,
+      "grad_norm": 0.36699753999710083,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2272,
+      "step": 40
+    },
+    {
+      "epoch": 0.08093070308548306,
+      "eval_loss": 0.233597069978714,
+      "eval_runtime": 24.746,
+      "eval_samples_per_second": 8.446,
+      "eval_steps_per_second": 4.243,
+      "step": 40
+    },
+    {
+      "epoch": 0.09104704097116843,
+      "grad_norm": 0.36897045373916626,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2495,
+      "step": 45
+    },
+    {
+      "epoch": 0.10116337885685382,
+      "grad_norm": 0.26886501908302307,
+      "learning_rate": 0.0,
+      "loss": 0.2033,
+      "step": 50
+    },
+    {
+      "epoch": 0.10116337885685382,
+      "eval_loss": 0.23070070147514343,
+      "eval_runtime": 24.7663,
+      "eval_samples_per_second": 8.439,
+      "eval_steps_per_second": 4.24,
+      "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": 9969328686366720.0,
+  "total_flos": 1.27706276560896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null