Training in progress, step 1287, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fdbec43e6fa950e2e28fec369fbc7e6afda2c8a6ef7857c58dc274c3d44be47
+oid sha256:6e6fbb2bfd52561e812f1aaae0e7d2b6e891b87409d7b7b89600d1c8b2267b0c
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce8bfa584ec65856ed81ede74f7cd3af67d756485502d635be4211c2a356797
+oid sha256:7254b162fe674b1b20ce0ba3b325760b2d39b436c59e27fa7b1d165a3d4f5466
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2a6648d5c8b23327e8d1f662519d5894824fc7116ea346279bb3aa64630b00
+oid sha256:32223ff90a7bc618a7d1a841a4f8d951e3cfafa282efaa7185e0e1a176562652
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eecbb16e7e277dafd1bed98ea8f56d1ce9159960beb5608b0892ff3835974c8a
+oid sha256:1748cfd64f75de15bebd10f07006b82775ac37a6afa9eedcdb3abb9f08211cb6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 107.0,
+  "epoch": 107.25,
   "eval_steps": 3,
-  "global_step": 1284,
+  "global_step": 1287,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12427,6 +12427,35 @@
       "eval_samples_per_second": 4.971,
       "eval_steps_per_second": 2.982,
       "step": 1284
+    },
+    {
+      "epoch": 107.08333333333333,
+      "grad_norm": 0.00019312536460347474,
+      "learning_rate": 3.8142304491339276e-05,
+      "loss": 0.0,
+      "step": 1285
+    },
+    {
+      "epoch": 107.16666666666667,
+      "grad_norm": 0.00016591262829024345,
+      "learning_rate": 3.800449896988535e-05,
+      "loss": 0.0,
+      "step": 1286
+    },
+    {
+      "epoch": 107.25,
+      "grad_norm": 0.0002106752071995288,
+      "learning_rate": 3.786688441341778e-05,
+      "loss": 0.0,
+      "step": 1287
+    },
+    {
+      "epoch": 107.25,
+      "eval_loss": 0.5604909062385559,
+      "eval_runtime": 1.004,
+      "eval_samples_per_second": 4.98,
+      "eval_steps_per_second": 2.988,
+      "step": 1287
     }
   ],
   "logging_steps": 1,
@@ -12446,7 +12475,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.16062558486528e+16,
+  "total_flos": 9.182254213890048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null