Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b250d0bd73621394bb1c58a18caf1aa200f519a9e76ecd4ec286be75f687b8ba
+oid sha256:15a1b4c886f4276cc230facd5fc439b32bb30afe2344e3f061a4a6ae7f2cd3fc
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4c243264041a03d844bd71e9e7a38bd03c72fe8516325850c8b29f7368e0fe
+oid sha256:01b46df13c075aef9c26ff6d87c3cb73ee59f2e63ddf4577653e799db3d24429
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979794a4a3185028b4f75463d82e4ab26027400d1e653ca29bde685c7d8d3488
+oid sha256:f65d33f8dbb303a0d5f68445f3c91506d6bca32bb2475114b5510685edbdcace
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10782029950083195,
+  "epoch": 0.11980033277870217,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 13.419,
       "eval_steps_per_second": 1.687,
       "step": 81
+    },
+    {
+      "epoch": 0.11181364392678869,
+      "grad_norm": 2.0179669857025146,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0702,
+      "step": 84
+    },
+    {
+      "epoch": 0.11580698835274543,
+      "grad_norm": 1.466431975364685,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0989,
+      "step": 87
+    },
+    {
+      "epoch": 0.11980033277870217,
+      "grad_norm": 1.6172847747802734,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1468,
+      "step": 90
+    },
+    {
+      "epoch": 0.11980033277870217,
+      "eval_loss": 0.07370365411043167,
+      "eval_runtime": 94.2945,
+      "eval_samples_per_second": 13.415,
+      "eval_steps_per_second": 1.686,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.09007175942144e+17,
+  "total_flos": 1.2111908438016e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null