Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c37938cff20d54f16e6948cecb14f8c4783ab1d9e48182740d90cef0de9a93d
+oid sha256:8f8279604d6f3bdedbb72ea3bb2fb304238bf3b9d1e58f5fe0e8fc7cb717449b
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c720e85a3f8fd1239aaf56505d6eb47048d4bc5e153156b7cabba6b932b87c89
+oid sha256:c421210b563ea618e06514034f817fa83b71693191d887bf758ec5f4ff46ba5b
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba5775fb29fb09291b5e6bcf51baeda39785b02c1c8894577139a1a6b19271b
+oid sha256:0e8d30ac278885d187ff1df21b81d65abded18f128ab26e671908f44d2491301
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005931784478497282,
+  "epoch": 0.011863568956994563,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 133.285,
       "eval_steps_per_second": 66.955,
       "step": 3
+    },
+    {
+      "epoch": 0.007909045971329708,
+      "grad_norm": 3.0225830078125,
+      "learning_rate": 8e-05,
+      "loss": 9.2969,
+      "step": 4
+    },
+    {
+      "epoch": 0.009886307464162136,
+      "grad_norm": 3.809354066848755,
+      "learning_rate": 0.0001,
+      "loss": 10.1611,
+      "step": 5
+    },
+    {
+      "epoch": 0.011863568956994563,
+      "grad_norm": 3.082827568054199,
+      "learning_rate": 0.00012,
+      "loss": 8.5074,
+      "step": 6
+    },
+    {
+      "epoch": 0.011863568956994563,
+      "eval_loss": 2.512053966522217,
+      "eval_runtime": 1.6415,
+      "eval_samples_per_second": 129.755,
+      "eval_steps_per_second": 65.182,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12206969192448.0,
+  "total_flos": 23883200593920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null