Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52693f69523ca8790141391928e69d77fdeac8125c9a7b352062146af443538e
+oid sha256:47f71b23de7b62db18fcca48da6b63b714af93b5c6852aa76643d00921b935ad
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f402383e304146447710931fdd7eeecdef7d945aa9f383478b215869138647e
+oid sha256:db510c8dbc20c46fd211c3f116efa990d638d6ef12bba1e95902decdcd11a213
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4f595e53a11daeaa16927192c84c01423620ce6e9c68ca46e9640ea3c6d56d
+oid sha256:cba1e2aa402a2b5e28f2164a78552b8e1e49267fb934299a266045cd326497d9
 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": 0.1306532663316583,
+  "epoch": 0.16750418760469013,
   "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": 0.9524,
       "step": 35
+    },
+    {
+      "epoch": 0.13400335008375208,
+      "grad_norm": 0.38849279284477234,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.792,
+      "step": 40
+    },
+    {
+      "epoch": 0.13400335008375208,
+      "eval_loss": 0.8592294454574585,
+      "eval_runtime": 13.246,
+      "eval_samples_per_second": 9.512,
+      "eval_steps_per_second": 4.756,
+      "step": 40
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 0.42209750413894653,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7356,
+      "step": 45
+    },
+    {
+      "epoch": 0.16750418760469013,
+      "grad_norm": 0.6707724332809448,
+      "learning_rate": 0.0,
+      "loss": 0.895,
+      "step": 50
+    },
+    {
+      "epoch": 0.16750418760469013,
+      "eval_loss": 0.8493944406509399,
+      "eval_runtime": 13.2605,
+      "eval_samples_per_second": 9.502,
+      "eval_steps_per_second": 4.751,
+      "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": 8503374869692416.0,
+  "total_flos": 1.0844883891781632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null