Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0946544a4ebe4b59e3e20ab43e037aa8a01235640c960d5cbc90988976b2f55
+oid sha256:88f19e5a98866d1e53c73b92867835fd0c553a4e58a4c0201ab3cd151e02da0e
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcfa097a298aee8c2f262ac8d0031f0c130df42269acec9788aea6deb5f457a
+oid sha256:ba183d8ded2015b81efa9d7441de368f391c44f0936c3fd74bec30e46276c15e
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf42ca78ac9a2a869327647eb0aa34446bbb0172e0928c2c921de691f4649efa
+oid sha256:45b89f1d21ac5ec72cdfce399d780202939bf44dd3aee81661aa2a5f164aaf9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015561174868702586,
+  "epoch": 0.002334176230305388,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 56.919,
       "eval_steps_per_second": 28.459,
       "step": 6
+    },
+    {
+      "epoch": 0.0018154704013486351,
+      "grad_norm": 4.396174907684326,
+      "learning_rate": 0.00014,
+      "loss": 16.8671,
+      "step": 7
+    },
+    {
+      "epoch": 0.0020748233158270116,
+      "grad_norm": 5.884392261505127,
+      "learning_rate": 0.00016,
+      "loss": 19.9732,
+      "step": 8
+    },
+    {
+      "epoch": 0.002334176230305388,
+      "grad_norm": 5.952862739562988,
+      "learning_rate": 0.00018,
+      "loss": 19.1747,
+      "step": 9
+    },
+    {
+      "epoch": 0.002334176230305388,
+      "eval_loss": 4.522780418395996,
+      "eval_runtime": 28.5558,
+      "eval_samples_per_second": 56.871,
+      "eval_steps_per_second": 28.436,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 194174112497664.0,
+  "total_flos": 291261168746496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null