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:dc3f6c4322397cd7ce8d3cd8d4eb8e67a6c7a6ccd774d613cbdb989dca0c8969
+oid sha256:b945277158c3965b904ba8fdd8d6f2302e0a95b667e2ab79ae3ed7f1c1f364ab
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005793bad7896d9a5668d1b2bc6de362745dabf9b3293bf8faca95fb2a2e5f23
+oid sha256:5451c6f238721b87ad1aad88e9dc4b4738e71deb9ae12cb94404dbd37fb1592e
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca663d2535b560c5e0dad431693bd4dc2f33c0f653e68bdef97a03c19ddca90a
+oid sha256:a56c658760e2ef8f6cbb02efa6401c15455f0289d8276eb8a09f01da7fb6aef7
 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": 0.02206848235397145,
+  "epoch": 0.025221122690253086,
   "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": 27.859,
       "eval_steps_per_second": 3.482,
       "step": 63
+    },
+    {
+      "epoch": 0.02311936246606533,
+      "grad_norm": 0.24828645586967468,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.0957,
+      "step": 66
+    },
+    {
+      "epoch": 0.02417024257815921,
+      "grad_norm": 0.24023310840129852,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.0662,
+      "step": 69
+    },
+    {
+      "epoch": 0.025221122690253086,
+      "grad_norm": 0.2469858080148697,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.1214,
+      "step": 72
+    },
+    {
+      "epoch": 0.025221122690253086,
+      "eval_loss": 1.083965539932251,
+      "eval_runtime": 172.5642,
+      "eval_samples_per_second": 27.862,
+      "eval_steps_per_second": 3.483,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.594009305527091e+16,
+  "total_flos": 2.964582063459533e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null