Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be064b98d7ce84f0f87b29a8757eccb1399e97dd3a9ead375580f8385cb38ae0
+oid sha256:6c02b1c4818c76710695c94927c70256bcd1bd1dd43a4840f601c342e6fc5387
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dab75d1b881e4ead97c7b35c04bdfc0b13ee515650f0d93db5249be6c65f7b7
+oid sha256:cf92737c1f19f1c068662d4b916b15ebbfd44a1610d74ba35bb5e7f6c48d3c1b
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
+oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18541767262192177,
+  "epoch": 0.2317720907774022,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 196.289,
       "eval_steps_per_second": 98.593,
       "step": 24
+    },
+    {
+      "epoch": 0.19314340898116852,
+      "grad_norm": 0.07490590214729309,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9273,
+      "step": 25
+    },
+    {
+      "epoch": 0.20086914534041525,
+      "grad_norm": 0.06475649774074554,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9329,
+      "step": 26
+    },
+    {
+      "epoch": 0.208594881699662,
+      "grad_norm": 0.05650734528899193,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.9241,
+      "step": 27
+    },
+    {
+      "epoch": 0.21632061805890873,
+      "grad_norm": 0.0597919225692749,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.9358,
+      "step": 28
+    },
+    {
+      "epoch": 0.22404635441815549,
+      "grad_norm": 0.06450095772743225,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 11.9166,
+      "step": 29
+    },
+    {
+      "epoch": 0.2317720907774022,
+      "grad_norm": 0.06534530222415924,
+      "learning_rate": 0.0,
+      "loss": 11.9311,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 143898181632.0,
+  "total_flos": 179872727040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null