Training in progress, step 189, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376c1539161dc35ee7656886a50f802f6e2f1e85db06a39df8d4512c98347a1e
+oid sha256:2e31caa0549662895406b35f60ee272ab02940a6d1169d24cf30843d63008545
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65aeaef577b1a8e4576abf9c9c86db18a32c69b2007bb249b839a1a38a72370
+oid sha256:1a691ecd73b2e1973b2873ff3d47ecc200e0a85a6854d7fd2dc11400647afb9e
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71416d694a6814725dec641fd551c41fa66aba026680767844a670043a5a519e
+oid sha256:b4d35c87f5d0e8ea62bc673d149da7d93d79a8b9b3951cb1475638c45526807b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f1659825841d1ed6f30cab4376f396fc018e1826ceec69f151ade48995de07
+oid sha256:cd12c7442104c6bee1178cd38829bd00c01ded478e430b03fe72cfaff700e4be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0362537764350455,
+  "epoch": 2.290030211480363,
   "eval_steps": 21,
-  "global_step": 168,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -471,6 +471,63 @@
       "eval_samples_per_second": 539.382,
       "eval_steps_per_second": 69.349,
       "step": 168
+    },
+    {
+      "epoch": 2.0725075528700905,
+      "grad_norm": 0.19772112369537354,
+      "learning_rate": 2.4057435257851175e-05,
+      "loss": 10.1846,
+      "step": 171
+    },
+    {
+      "epoch": 2.108761329305136,
+      "grad_norm": 0.29851359128952026,
+      "learning_rate": 2.2392494902427025e-05,
+      "loss": 10.1801,
+      "step": 174
+    },
+    {
+      "epoch": 2.1450151057401814,
+      "grad_norm": 0.21380534768104553,
+      "learning_rate": 2.07704802418419e-05,
+      "loss": 10.1843,
+      "step": 177
+    },
+    {
+      "epoch": 2.1812688821752264,
+      "grad_norm": 0.1674821972846985,
+      "learning_rate": 1.9193913275316626e-05,
+      "loss": 10.1844,
+      "step": 180
+    },
+    {
+      "epoch": 2.217522658610272,
+      "grad_norm": 0.1863589584827423,
+      "learning_rate": 1.7665245337452368e-05,
+      "loss": 10.18,
+      "step": 183
+    },
+    {
+      "epoch": 2.2537764350453173,
+      "grad_norm": 0.22038479149341583,
+      "learning_rate": 1.6186853286758397e-05,
+      "loss": 10.1813,
+      "step": 186
+    },
+    {
+      "epoch": 2.290030211480363,
+      "grad_norm": 0.17609906196594238,
+      "learning_rate": 1.4761035809979395e-05,
+      "loss": 10.1798,
+      "step": 189
+    },
+    {
+      "epoch": 2.290030211480363,
+      "eval_loss": 10.172968864440918,
+      "eval_runtime": 0.2591,
+      "eval_samples_per_second": 540.238,
+      "eval_steps_per_second": 69.459,
+      "step": 189
     }
   ],
   "logging_steps": 3,
@@ -490,7 +547,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 18740510982144.0,
+  "total_flos": 21083074854912.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null