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:d66405de85034bd7b54f4c80df9615dea9abfdec5033628e345279c5d8739dd0
+oid sha256:b6245a68bee01cf3ff25d9b94e6fbc5c0b627024771e4d18bd217f5d00766a59
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d1fe9ffbf618e9492747eda64b6b3827c71b4f8fabac72ff6925e6bd5e85ed
+oid sha256:7fc7e6815a36225a99f10f4d637ef098705f3c08839675c1bc39645d8686f0f9
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cce00927943e545f38db920e14c68afdcbd9c32a13585978045f5eaff63d9c2
+oid sha256:b6fdb25d8aaba00761ed5aca09337bb966cfac27797928fea61ca14ae2db0cb4
 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": 0.049273531269740996,
+  "epoch": 0.06317119393556538,
   "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": 0.569,
       "step": 35
+    },
+    {
+      "epoch": 0.05053695514845231,
+      "grad_norm": 0.4335253834724426,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5527,
+      "step": 40
+    },
+    {
+      "epoch": 0.05053695514845231,
+      "eval_loss": 0.5540109276771545,
+      "eval_runtime": 41.8184,
+      "eval_samples_per_second": 7.987,
+      "eval_steps_per_second": 3.993,
+      "step": 40
+    },
+    {
+      "epoch": 0.056854074542008845,
+      "grad_norm": 0.48217666149139404,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5588,
+      "step": 45
+    },
+    {
+      "epoch": 0.06317119393556538,
+      "grad_norm": 0.45759883522987366,
+      "learning_rate": 0.0,
+      "loss": 0.5631,
+      "step": 50
+    },
+    {
+      "epoch": 0.06317119393556538,
+      "eval_loss": 0.5510811805725098,
+      "eval_runtime": 41.4399,
+      "eval_samples_per_second": 8.06,
+      "eval_steps_per_second": 4.03,
+      "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": 1.2631125277016064e+16,
+  "total_flos": 1.61937503551488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null