Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845df672de51e2f5fa50b9ff6665844667ddcc24c0a2ae19a315aa98030f2c9e
+oid sha256:87197d74ca257c80e2929b57e1b56b510efda6553d9bfcd2dac9661ba4eb65e8
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6f052f9c11d4659a113bedaf733471f594b91455fd7a6781d61178caf58f9f
+oid sha256:5a1897b95b0853ae3bca8766ff691c75a11ffbf677858864d37481c2dffd3c03
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321a2c9e4ec3ff5ef7b65a473523bb974a19b15f29b73590813a9ace23443c6c
+oid sha256:037eb42ee2bf8daa9ffaf5f72a6ace0549662a52669f37379d45f07ff7e6ccc7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa382b905f4dad34ebe7abd59235e43278cf8532f9270f8693e820e99473115
+oid sha256:2248de37d2320ddbb576171cc6b8d719f7febfba0a31c5797625bd8cfe79c5ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003600110772639158,
+  "epoch": 0.007200221545278316,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 13.199,
       "eval_steps_per_second": 1.651,
       "step": 13
+    },
+    {
+      "epoch": 0.004153973968429798,
+      "grad_norm": 18.268274307250977,
+      "learning_rate": 9.968561049466214e-05,
+      "loss": 6.9041,
+      "step": 15
+    },
+    {
+      "epoch": 0.004984768762115757,
+      "grad_norm": 9.425353050231934,
+      "learning_rate": 9.919647942993148e-05,
+      "loss": 3.1179,
+      "step": 18
+    },
+    {
+      "epoch": 0.005815563555801717,
+      "grad_norm": 13.245735168457031,
+      "learning_rate": 9.848447601883435e-05,
+      "loss": 2.4225,
+      "step": 21
+    },
+    {
+      "epoch": 0.006646358349487676,
+      "grad_norm": 7.058098793029785,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.7562,
+      "step": 24
+    },
+    {
+      "epoch": 0.007200221545278316,
+      "eval_loss": 0.40671274065971375,
+      "eval_runtime": 461.0952,
+      "eval_samples_per_second": 13.19,
+      "eval_steps_per_second": 1.65,
+      "step": 26
     }
   ],
   "logging_steps": 3,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0622684501049344e+16,
+  "total_flos": 4.290848871992525e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null