Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f6f3c753a3035760918fca3c3e3f09845a62303af671236b3ea0fdcd5081f5
+oid sha256:5d6affddafb027f979e5a98ea70b4b1b21e85006acbbe885523686d811c218ca
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9fbb28d48ad94ba22a169ded797086a9d5c888323227d3f7f10bcec0fb1f6b
+oid sha256:aac7d3c59473e8ee26003b67c8e31b742d174b20ca944462e467ad412908791b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
+oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.049429657794676805,
+  "epoch": 0.09885931558935361,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 14.643,
       "eval_steps_per_second": 7.388,
       "step": 10
+    },
+    {
+      "epoch": 0.057034220532319393,
+      "grad_norm": 4.337152004241943,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.7037,
+      "step": 15
+    },
+    {
+      "epoch": 0.07604562737642585,
+      "grad_norm": 4.381193161010742,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.4531,
+      "step": 20
+    },
+    {
+      "epoch": 0.07604562737642585,
+      "eval_loss": 0.44711190462112427,
+      "eval_runtime": 7.5968,
+      "eval_samples_per_second": 14.611,
+      "eval_steps_per_second": 7.372,
+      "step": 20
+    },
+    {
+      "epoch": 0.09505703422053231,
+      "grad_norm": 3.5168604850769043,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.2719,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null