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:da9482da44187fb4ba4f3b8d514a336795d06ddb7ea1d6e25f326cc913a5ce7f
+oid sha256:62a52e0a3ee95ef8a4cc2fa1c61bb51f9c51f78af0df5dcb38c1a3cbe4d0ecf2
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae31359390ebd44baeca72772348828cbb370f33737791b739de72f9d91a9c2
-size 2280
+oid sha256:8664f27bf3189214229ace05c258dfc6b2e1af745b06cc63e3d29bae99b2a67c
+size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
+oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008762961881115817,
+  "epoch": 0.0017525923762231634,
   "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": 3.98,
       "eval_steps_per_second": 3.98,
       "step": 3
+    },
+    {
+      "epoch": 0.0011683949174821088,
+      "grad_norm": 106.46147918701172,
+      "learning_rate": 2e-05,
+      "loss": 10.6612,
+      "step": 4
+    },
+    {
+      "epoch": 0.0014604936468526361,
+      "grad_norm": 46.043792724609375,
+      "learning_rate": 4e-05,
+      "loss": 9.5607,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017525923762231634,
+      "grad_norm": 42.20634841918945,
+      "learning_rate": 6e-05,
+      "loss": 8.2951,
+      "step": 6
+    },
+    {
+      "epoch": 0.0017525923762231634,
+      "eval_loss": 2.274749994277954,
+      "eval_runtime": 304.0635,
+      "eval_samples_per_second": 2.371,
+      "eval_steps_per_second": 2.371,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2109388496044032.0,
+  "total_flos": 4218776992088064.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null