Training in progress, epoch 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba61d1259d3a166794e85bf13638446970059851ee9d372affb1e473f2809a8
+oid sha256:8b9aa1b8dd561b3532c2cee11a9ab1f870b7fab4f88da9d8bd00a315725767fa
 size 146815928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f24799c769ec928c84290e0f7676a0ed8f6c5c46215c2de29c869d7d34e5e5
+oid sha256:32d97124676388812689aaff12813c3cb87b60d9ba5017aa3c5486ee93777bbd
 size 74680890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd028caa5142b17a0b8979386893f3c02081255179b70983a3b19232b3b5706a
+oid sha256:876c7b123b02733054d972c2a3db02d81afa062c436ce960bc75792ef3b498a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa4bcc8a211b0b4d0d438488c7be8218bdc07991923d557342d812a16a0576f
+oid sha256:4fcf471afb5b0fd74cb32d95bb5d2b1d9ce9a833cd0f6de74279c0517625efe7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 2800,
+  "global_step": 3150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,35 @@
       "eval_samples_per_second": 2.11,
       "eval_steps_per_second": 0.528,
       "step": 2800
+    },
+    {
+      "epoch": 8.285714285714286,
+      "grad_norm": 0.2690626382827759,
+      "learning_rate": 4e-05,
+      "loss": 0.1336,
+      "step": 2900
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 0.3065795600414276,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.1424,
+      "step": 3000
+    },
+    {
+      "epoch": 8.857142857142858,
+      "grad_norm": 0.3088241517543793,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1376,
+      "step": 3100
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.2503173053264618,
+      "eval_runtime": 331.8022,
+      "eval_samples_per_second": 2.11,
+      "eval_steps_per_second": 0.527,
+      "step": 3150
     }
   ],
   "logging_steps": 100,
@@ -286,7 +315,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.862976795541504e+16,
+  "total_flos": 7.71343643658158e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null