Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8beebd62d38be4e8658cf307d203e03f5539e778053c98c07f79c9ed350a4d
+oid sha256:d5e69eec906ecf92691e076f0971963d96fa69925ac5a5c87a6929b86e50191c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a5e684c860203a862401230f1e6a4d59c25bebc43621b7e1b446e46537e329
+oid sha256:3d8c3c6245fa3653ac643bb72548ebf45c679cc50a323273290f3d8e67d58599
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935e93c17fec955cdc1873761997edd06c6d8451e1eced9e4c0a038e0347bdf6
+oid sha256:ea144843cccdece32ec0f026dd4d791a6e6fe2e253a9e96ebc9c92f0b6d28734
 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": 0.04096228868660598,
+  "epoch": 0.04681404421326398,
   "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": 11.047,
       "eval_steps_per_second": 1.381,
       "step": 63
+    },
+    {
+      "epoch": 0.04291287386215865,
+      "grad_norm": 0.9039548635482788,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.6048,
+      "step": 66
+    },
+    {
+      "epoch": 0.044863459037711315,
+      "grad_norm": 0.9454875588417053,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 4.46,
+      "step": 69
+    },
+    {
+      "epoch": 0.04681404421326398,
+      "grad_norm": 1.141798973083496,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 4.5007,
+      "step": 72
+    },
+    {
+      "epoch": 0.04681404421326398,
+      "eval_loss": 1.1424474716186523,
+      "eval_runtime": 234.554,
+      "eval_samples_per_second": 11.046,
+      "eval_steps_per_second": 1.381,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.233654518861005e+16,
+  "total_flos": 9.409890878698291e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null