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:d26c267ddf7d7bd8946474210f2fb27ec07b38750e2c0a21cc630fa9e6e3e1e5
+oid sha256:0770f730ce1f6f8a1c680cf1d74c8cc1c8d8167ae4944a5793667314821ed3d9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8606471fbadd4b09cab3624b8c4b0a215cc613e949fa31070d1da83a24a26583
+oid sha256:c5c76dda34e77686ff78cf996b525671b0fcf02129df26acfc9134b2ec823165
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfbc0801bd4d766f17422a6f7435f703d09d8f581accc93a6fe45904abe559e
+oid sha256:f34bba95447e0ec764b895aa1b44bf630fd1c25c2065aec5f8a5c165a3d1b571
 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": 0.09437386569872959,
+  "epoch": 0.12099213551119177,
   "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": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.09679370840895342,
+      "grad_norm": 0.002887232694774866,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.09679370840895342,
+      "eval_loss": 5.233088813838549e-05,
+      "eval_runtime": 14.6142,
+      "eval_samples_per_second": 11.906,
+      "eval_steps_per_second": 5.953,
+      "step": 40
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "grad_norm": 0.0019215194042772055,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.12099213551119177,
+      "grad_norm": 0.0021148412488400936,
+      "learning_rate": 0.0,
+      "loss": 0.0002,
+      "step": 50
+    },
+    {
+      "epoch": 0.12099213551119177,
+      "eval_loss": 5.048857201472856e-05,
+      "eval_runtime": 14.4828,
+      "eval_samples_per_second": 12.014,
+      "eval_steps_per_second": 6.007,
+      "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": 8924147497304064.0,
+  "total_flos": 1.1513537444708352e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null