Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6958982483993a00aa40a8d87de2e7b4b52e491369b4736ab24ddbc0dfc846
+oid sha256:ea4084f05edcfee38d7da7b0761cf1447b642717d90849273550df2441a28aa8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d98d7bd7eb46683125a86f5931bca69925cc504784a56424c199b0bd84a46ac
+oid sha256:dbb9c1eaf20ba6b9ab238b92b711c656020f3981e257668c19bc86321d6b185f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
+oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0727062896710906,
+  "epoch": 0.0830929024812464,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 13.975,
       "eval_steps_per_second": 1.752,
       "step": 63
+    },
+    {
+      "epoch": 0.07616849394114253,
+      "grad_norm": 3.730220317840576,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 7.9821,
+      "step": 66
+    },
+    {
+      "epoch": 0.07963069821119446,
+      "grad_norm": 3.3771941661834717,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 7.2337,
+      "step": 69
+    },
+    {
+      "epoch": 0.0830929024812464,
+      "grad_norm": 3.681811809539795,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 7.4931,
+      "step": 72
+    },
+    {
+      "epoch": 0.0830929024812464,
+      "eval_loss": 1.9186850786209106,
+      "eval_runtime": 104.5007,
+      "eval_samples_per_second": 13.971,
+      "eval_steps_per_second": 1.751,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.833465868038963e+16,
+  "total_flos": 1.00953895634731e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null