Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eece020ae8c00cd45b64e3adbbabbd4d7fc88050fc9c743fb1ce1f92a32858d
+oid sha256:f1a0640a688e8ecad6a1dc0f7dac5e04369e5866f8019d013056c2b49a1d92da
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dafe72fc84b7e2ab614a2d4b0ed5ac30cad72a718a8daab974f53fa409724e
+oid sha256:5a052c1554594789f6a27283a03b1edfc293303e67af51aa759549db71ec295b
 size 40131268

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123bf0512ee7e92d318f0df765024002679fa6c8d9772a1133e0845594f76a35
+oid sha256:5f5e5695fa7542edff8994f19e9aaae56bcda8213c0fe73a8aefebd39c185b1e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d26c135a3ab88ceff8afaebade3eca6236181282cfa27b13d7c78cfc7e5660
+oid sha256:6834c48e54755b6053cf2981d162510749689fe7667c5ba1b206bfb8c1e53278
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d376ae8798f4665b5771f699e3266fe3c29018fd2b9fbef975810586bff4b6bb
+oid sha256:4e79d34310f72a541db31128103499d25f09b09edbc24630786fd81613b4f18b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a2ae5b55351193f6ed73aaecedbcc2045d8e0e97e1e5282428f7201ef51993
+oid sha256:eb38218cb3dca9ff5224fe64700d834a6e097149d7060b864d3addda702df953
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.055299539170506916,
+  "epoch": 0.08294930875576037,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 37.007,
       "eval_steps_per_second": 4.651,
       "step": 6
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 10.15619945526123,
+      "learning_rate": 0.00014,
+      "loss": 3.9804,
+      "step": 7
+    },
+    {
+      "epoch": 0.07373271889400922,
+      "grad_norm": 5.944631576538086,
+      "learning_rate": 0.00016,
+      "loss": 2.7903,
+      "step": 8
+    },
+    {
+      "epoch": 0.08294930875576037,
+      "grad_norm": 5.762338638305664,
+      "learning_rate": 0.00018,
+      "loss": 2.8695,
+      "step": 9
+    },
+    {
+      "epoch": 0.08294930875576037,
+      "eval_loss": 2.5336620807647705,
+      "eval_runtime": 4.8033,
+      "eval_samples_per_second": 38.098,
+      "eval_steps_per_second": 4.788,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9444243315621888.0,
+  "total_flos": 1.4166364973432832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null