Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc4dcb6870b8dfb1e72854d9ce0d6d3b0b59fe959d8d9ae71397d7f0714b197
+oid sha256:c17e36c580ec55b7a0ff935294df3fe68f8c9ffc689792f3aff4cb9471ba456f
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26da2c4ba4214a90ab657c905cfbfd039af1814df4d226a0eb9b74ca2b2cdb82
+oid sha256:5cf43bcf58ab6c923744dc9f5ccfa3d49ad33b1f4749d4ee9918213545432704
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8a0b15cc60e402856638fe304e89124d12a81f450e3a5c51c7743b7e29a913
+oid sha256:399f12128758c20f45f058a67599e1b9a2d9cd495e1ccd71687a907821c8d121
 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": 0.00010470930080364388,
+  "epoch": 0.00020941860160728776,
   "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": 423.409,
       "eval_steps_per_second": 211.704,
       "step": 3
+    },
+    {
+      "epoch": 0.00013961240107152517,
+      "grad_norm": 0.49404385685920715,
+      "learning_rate": 8e-05,
+      "loss": 6.9545,
+      "step": 4
+    },
+    {
+      "epoch": 0.00017451550133940646,
+      "grad_norm": 0.48088663816452026,
+      "learning_rate": 0.0001,
+      "loss": 6.9399,
+      "step": 5
+    },
+    {
+      "epoch": 0.00020941860160728776,
+      "grad_norm": 0.5026301145553589,
+      "learning_rate": 0.00012,
+      "loss": 6.9608,
+      "step": 6
+    },
+    {
+      "epoch": 0.00020941860160728776,
+      "eval_loss": 6.946343898773193,
+      "eval_runtime": 28.6679,
+      "eval_samples_per_second": 420.819,
+      "eval_steps_per_second": 210.41,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5273321472.0,
+  "total_flos": 9887477760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null