Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d4283642738016a6d96065df9b72d861da182de01092ba3dd76933042e913d
+oid sha256:15c97b0a045597bc1f785c2ea4a2097bd9df7d7784e078e21701b2a79346c6ff
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266a78ed30af35a0a0b47f426db8dd5799b89e7336dd1c7980c6c9025fa4a951
+oid sha256:838088358b3d5dc10bc4470aacf692658cf21b7327eee3442a22be6949cc11ae
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f45df35fd8ad79b1bd72715bcd1d74342a7a953e3627b33b4e36f1dec1b0db4
+oid sha256:dfd3ceec50f1e33b04e78f133658a3bb748ee81a17f6cd4480fbb02e22d2d502
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014450867052023121,
+  "epoch": 0.028901734104046242,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 2.706,
       "eval_steps_per_second": 2.706,
       "step": 25
+    },
+    {
+      "epoch": 0.017341040462427744,
+      "grad_norm": 0.04972805827856064,
+      "learning_rate": 5e-05,
+      "loss": 0.0181,
+      "step": 30
+    },
+    {
+      "epoch": 0.02023121387283237,
+      "grad_norm": 0.10225903242826462,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0344,
+      "step": 35
+    },
+    {
+      "epoch": 0.023121387283236993,
+      "grad_norm": 0.15425756573677063,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0059,
+      "step": 40
+    },
+    {
+      "epoch": 0.02601156069364162,
+      "grad_norm": 0.3811052441596985,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0107,
+      "step": 45
+    },
+    {
+      "epoch": 0.028901734104046242,
+      "grad_norm": 0.34359514713287354,
+      "learning_rate": 0.0,
+      "loss": 0.0056,
+      "step": 50
+    },
+    {
+      "epoch": 0.028901734104046242,
+      "eval_loss": 0.016979020088911057,
+      "eval_runtime": 71.5297,
+      "eval_samples_per_second": 2.698,
+      "eval_steps_per_second": 2.698,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2318397761126400.0,
+  "total_flos": 4636795522252800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null