Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe60f9ebcc51ae696c9eec1e29334ff463af49611750a78fadb6a50df7cc684
+oid sha256:21f512f9ad2a9aac7d0e1e510bb137e2ebb0fcf36ee0511b6f9da9d4752d8ded
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2057d4586b5d22cee35bc63f4124d6d9d464d5440c51be3d5e9f5d6472e5967f
+oid sha256:d05c9a3bb2429322dfe7ee59f64dbd4ef0a8649d8490e98dc6deb655cf9d8175
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d88d6bd1144768a9ee07bbcac748464e2993ae8055c7a7cd2413fcd5bf9456
+oid sha256:72e3379b97382001bdd566ec44641d53d705aadf1c63d214e37febd171c0679c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020930232558139535,
+  "epoch": 0.04186046511627907,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 69.605,
       "eval_steps_per_second": 8.749,
       "step": 9
+    },
+    {
+      "epoch": 0.027906976744186046,
+      "grad_norm": 0.8683664798736572,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 5.7731,
+      "step": 12
+    },
+    {
+      "epoch": 0.03488372093023256,
+      "grad_norm": 1.1061254739761353,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 5.4242,
+      "step": 15
+    },
+    {
+      "epoch": 0.04186046511627907,
+      "grad_norm": 0.99778813123703,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 5.2717,
+      "step": 18
+    },
+    {
+      "epoch": 0.04186046511627907,
+      "eval_loss": 5.513608932495117,
+      "eval_runtime": 10.4282,
+      "eval_samples_per_second": 69.427,
+      "eval_steps_per_second": 8.726,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 564420799365120.0,
+  "total_flos": 1128841598730240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null