Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3027b828c0f3ecc1fc9b7b1154410dad23f738b5b6f4b9e7428f92e3cc44f264
+oid sha256:e8d22c13e591f6d8460c82e16915b4bdd7a515686bac1f94d27acd2d2d0d73e2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9ef3a9a61855b948e805d6a3b340d1a1e016ed8184d08eeab72383073728b7
+oid sha256:d43cdc2d6bcdeeaea9c85315481596e0d7f01e66978a04911e01a3d00a186c59
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3d9a196d0248e24a326cf43c578eb11e37554e1edaaa6a55990c552c3bb4de
+oid sha256:9f03fbef729f64ddf68b55e06f01e7bb1d8bf0494ed9ac87477f34ab984a1d9b
 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": 0.04456233421750663,
+  "epoch": 0.05092838196286472,
   "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": 7.525,
       "eval_steps_per_second": 0.942,
       "step": 63
+    },
+    {
+      "epoch": 0.04668435013262599,
+      "grad_norm": 0.22867415845394135,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2051,
+      "step": 66
+    },
+    {
+      "epoch": 0.04880636604774536,
+      "grad_norm": 0.18394522368907928,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.2023,
+      "step": 69
+    },
+    {
+      "epoch": 0.05092838196286472,
+      "grad_norm": 0.20804443955421448,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.205,
+      "step": 72
+    },
+    {
+      "epoch": 0.05092838196286472,
+      "eval_loss": 0.20696386694908142,
+      "eval_runtime": 316.3831,
+      "eval_samples_per_second": 7.526,
+      "eval_steps_per_second": 0.942,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6447804416825754e+17,
+  "total_flos": 1.8755111649647e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null