Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b527bbc9ea3f763409665e26a1b6103fd04fc8ac44a899b855dece4e7104c2
+oid sha256:df2a00d13ac023d7b1cc9cd7d6c9094952333fe41ce10848bdee5f889f7f7891
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea11c9904bb5f9f2d41fd4d00864e449c311d6a83517c2dbb500027075ec96a2
+oid sha256:aeba2fc3a0d52d465051424d71311cc4a1651f3cbd7b05aeacbd5829d5634ccd
 size 253144

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafa09013d7e03c30fb84370b3eee8b80b391a105e07953ffad87a16b39b8517
+oid sha256:15ed9b9dfb938bcc62b0eaed6cdf9495692fbfeef947ba4d2a8a9347a85f3208
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb5e7051a35c8474e9b296e968e978084b8284b1f07a139dec023b2df5d76b86
+oid sha256:4571433de0cba5d663839bfe32d4131227a79f7685c6daae2d84506343731435
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86827c3414e5a1fb5a88ad44faa1f0102da2ac4a4c4dec98e577a06631dfa315
+oid sha256:fe0cfddf34ab86918b62c933446077488ae04579749c367703771380770e0478
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c25f05740893886f81aec2241970cc3e1b265e7169b3cacc20519bacf0c76a
+oid sha256:5a600130eb891567f5668595eb4717fc689ca2110bc59c4621409a842451bf55
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.215311004784689,
+  "epoch": 0.2583732057416268,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 766.961,
       "eval_steps_per_second": 23.985,
       "step": 45
+    },
+    {
+      "epoch": 0.22966507177033493,
+      "grad_norm": 0.108404740691185,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3215,
+      "step": 48
+    },
+    {
+      "epoch": 0.24401913875598086,
+      "grad_norm": 0.10472545027732849,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3201,
+      "step": 51
+    },
+    {
+      "epoch": 0.2583732057416268,
+      "grad_norm": 0.10555419325828552,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3182,
+      "step": 54
+    },
+    {
+      "epoch": 0.2583732057416268,
+      "eval_loss": 10.317863464355469,
+      "eval_runtime": 1.8688,
+      "eval_samples_per_second": 752.905,
+      "eval_steps_per_second": 23.545,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 40158237818880.0,
+  "total_flos": 48189885382656.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null