Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e51e563e316add60af860ed4c649cf9be7db912fe546a36df80026a14206ea1
+oid sha256:6d39eb33b310765184b69c1297893109498e8e427e4184cae2e0be81c2c24b77
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a4f2b5e058d8a303d88189b19a825022f6bfca9ed038a8724e38bcaa4757e3
+oid sha256:a7b8748f09e2f47b8efbbac440f2d0e089b1ef56067fb6f9509e51986993c53d
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325ac916028333cff48d1655ec49518bb3508c9da4047901b750b21ad73910fb
+oid sha256:95285a3badbe4821254fc16db8e2fe6d0496ef3801dee6b0f065bf2796f5cf6e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2727272727272727,
+  "epoch": 1.4545454545454546,
   "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": 36.203,
       "eval_steps_per_second": 4.741,
       "step": 63
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.0798910856246948,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 2.1019,
+      "step": 66
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 1.1480613946914673,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 2.1791,
+      "step": 69
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.9959827661514282,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 2.0875,
+      "step": 72
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "eval_loss": 2.130913257598877,
+      "eval_runtime": 2.3152,
+      "eval_samples_per_second": 36.283,
+      "eval_steps_per_second": 4.751,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.645082316374016e+16,
+  "total_flos": 1.880210707002163e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null