Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b13a2fd1e81661a1743bc08fe6eef139f227ed7a8edf1eeec08d7f3a3da11fa
+oid sha256:965aa605c7cc180f82ad3aabf2f677da41f92274c07a2403d9ce12593eb1ef8f
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d658d4a41e6d022cdc071277fa2917474521088df4ce6a75b1d86e4271c1c4
+oid sha256:cc3c2a9d9f28e69d53ba9097b70ea92973940c38329d2296520922654cfbc718
 size 253144

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd0e6dc55bc7ef8b633a18916a82d102ca3bb71b1e3cf4ea9cb88a3fac61944
+oid sha256:5b41b5b5b74bced6349d0144307b8c5d544c2100be4c7c03093d724746633141
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4bc9b8dc8df484cb0edca6cc0ff200c0812a830ef214b46cb45114940c28935
+oid sha256:5c3a4721245d83ba50e56827d18e3d66a9b9fcfa5b05cf816b8ca34a1be752f4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b323dd365ec8a50c2c6aa9ac906c55d4a861361a74d3a27128ec86929ff62683
+oid sha256:b7860d5a216d8d6a340c97d1bcede04512bf8ee775d3b5ee94a030d874d3af37
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a21ac96cc961bc988d3aac3b97db6d0e39b74e0a1266bc6081c1b18bb3a681
+oid sha256:32ff2d6227757e01b6d880feb74e36cde96a036b80d761664553ea7c0a3b3a81
 size 15024

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": 0.3014354066985646,
+  "epoch": 0.3444976076555024,
   "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": 763.116,
       "eval_steps_per_second": 23.864,
       "step": 63
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.0888906717300415,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3144,
+      "step": 66
+    },
+    {
+      "epoch": 0.33014354066985646,
+      "grad_norm": 0.08958574384450912,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3132,
+      "step": 69
+    },
+    {
+      "epoch": 0.3444976076555024,
+      "grad_norm": 0.08907806128263474,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.313,
+      "step": 72
+    },
+    {
+      "epoch": 0.3444976076555024,
+      "eval_loss": 10.312495231628418,
+      "eval_runtime": 1.8465,
+      "eval_samples_per_second": 761.964,
+      "eval_steps_per_second": 23.828,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 56221532946432.0,
+  "total_flos": 64253180510208.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null