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:d5845dd82b3c73f9daaebfac713c4eb809b10082e786415e67d57227b9cf02ab
+oid sha256:7dabc8ab84b6e3ce61e2ccfadff51ffb02405665ad9fa4d3636f642890736fad
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6fd52649ad7e5024e08dda868264c17c1f6ebef2ca447c263cb99354b10a3f
+oid sha256:167240c15e123abb1bcc65f9ddf7a9ad2451488ec24110f6cd1c9c7f9ca8d76c
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642b8e1d179ab2764f041e738c2f1ba096bcbbcc310b84d42b905f50dea8b501
+oid sha256:8944d8a5e11223d6600eda0d1a50c046555531586fed89119f0372aff9b68db3
 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": 0.07107061503416856,
+  "epoch": 0.09111617312072894,
   "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": 1.5868,
       "step": 35
+    },
+    {
+      "epoch": 0.07289293849658314,
+      "grad_norm": 1.7055730819702148,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6779,
+      "step": 40
+    },
+    {
+      "epoch": 0.07289293849658314,
+      "eval_loss": 1.5071282386779785,
+      "eval_runtime": 19.8313,
+      "eval_samples_per_second": 11.699,
+      "eval_steps_per_second": 5.849,
+      "step": 40
+    },
+    {
+      "epoch": 0.08200455580865604,
+      "grad_norm": 2.081904411315918,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4324,
+      "step": 45
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "grad_norm": 2.442922592163086,
+      "learning_rate": 0.0,
+      "loss": 1.5104,
+      "step": 50
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "eval_loss": 1.4958969354629517,
+      "eval_runtime": 19.6801,
+      "eval_samples_per_second": 11.789,
+      "eval_steps_per_second": 5.894,
+      "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": 7692142950481920.0,
+  "total_flos": 9794343508377600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null