Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389eed975d12b564fd874d90814d179fa92a08af2629545d4296c32813c23ddf
+oid sha256:5d20cee39caf43703c8024676b789cdadc98f6cf23116817700812f717a43279
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af6fbfa9e6decd5896a2bd0853612084b67590060f11f0648066d1a02c4fa2e
+oid sha256:1521ef46262ab3a76177dd7ec70fc94a84b31e490ecaed14885ea2f8d5512838
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005d9a86e0834fe0802ab2e1c3fa9eca806e3cae26d1cbb14ab848a758219c13
+oid sha256:a4faae14a1aa6472da1e35d90c3eeeb0dd65ba4a4be7087c6d32cacd0c607e1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6140350877192983,
+  "epoch": 0.7017543859649122,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 565.089,
       "eval_steps_per_second": 70.636,
       "step": 35
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.13146649301052094,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 10.3615,
+      "step": 36
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.12355206906795502,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 10.3609,
+      "step": 39
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "eval_loss": 10.355828285217285,
+      "eval_runtime": 0.1665,
+      "eval_samples_per_second": 576.456,
+      "eval_steps_per_second": 72.057,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3904273121280.0,
+  "total_flos": 4462026424320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null