Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271e910b49bbc3a70bbece333bb98b8044250f5312389fc58f4477edee664bb4
+oid sha256:c3142e64384f75acec9c45bd7b92422ba34955c95125f8a1c8d3f89ec219e5a8
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9205d0be73afe8a749d60d92088051b9d1a742460111451262ff97efce9ec32
+oid sha256:ffbba6f1025defa039eab1fe6b4edcde71fee7996215a3e8f30fe5355f95dc32
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e0496dcdb9c09786e531fcb26e12c27114121c2227d15a22d343188a83ccc7
+oid sha256:2128e47ed2e40d2cfe486fec9abc63fcf3bab8260c2a57f50edbff5866f86c2f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a517b5553fd7c8042f9435a157576adf1654dadecdce942dd5274f1a6454ed0a
+oid sha256:ff1a0c1b98d79d09c35da987923f986273df828d842c838df3ce19795ef0c726
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26666666666666666,
+  "epoch": 0.5333333333333333,
   "eval_steps": 6,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 15.311,
       "eval_steps_per_second": 1.971,
       "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.7594890594482422,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 1.6572,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.4678586721420288,
+      "eval_runtime": 13.0056,
+      "eval_samples_per_second": 15.532,
+      "eval_steps_per_second": 1.999,
+      "step": 12
     }
   ],
   "logging_steps": 10,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.446197012824064e+16,
+  "total_flos": 4.892394025648128e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null