Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418cf71d40f31601a0fb7898371e7cbd777ab4dac5d7db6b21568f304cb32419
+oid sha256:e7fd699c55557ed55070429a00f0683c6e4782303df524e0788ed06fef3cf8c0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330a3ce1fc5554bc4e11b0e93ff306fa93402f571796182bca7cabd783009e61
+oid sha256:ae78be996d1f5d59a47198d4c0588e6633e2a4e293e3706e977b2391ef5bd4ac
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87951bd1d28cfc789427636c05788fc21db0e7e40be21589b4278413c44c66bd
+oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0045955491255691245,
+  "epoch": 0.005361473979830646,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 13.845,
       "eval_steps_per_second": 1.731,
       "step": 54
+    },
+    {
+      "epoch": 0.004850857410322965,
+      "grad_norm": 2.7015180587768555,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 4.4799,
+      "step": 57
+    },
+    {
+      "epoch": 0.005106165695076805,
+      "grad_norm": 2.699486017227173,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 4.4337,
+      "step": 60
+    },
+    {
+      "epoch": 0.005361473979830646,
+      "grad_norm": 2.7420105934143066,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 4.4129,
+      "step": 63
+    },
+    {
+      "epoch": 0.005361473979830646,
+      "eval_loss": 1.1171752214431763,
+      "eval_runtime": 1430.265,
+      "eval_samples_per_second": 13.837,
+      "eval_steps_per_second": 1.73,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.59380728306729e+16,
+  "total_flos": 8.859441830245171e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null