Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87197d74ca257c80e2929b57e1b56b510efda6553d9bfcd2dac9661ba4eb65e8
+oid sha256:955ee48fa44fbd547a69a17e32f27b4906e3dbf00d84babd8e3d9ea83598276a
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1897b95b0853ae3bca8766ff691c75a11ffbf677858864d37481c2dffd3c03
+oid sha256:21c9361a80a2d599be762356ad296eb8f3d22e72b304e2c586b2e9f1a3633354
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037eb42ee2bf8daa9ffaf5f72a6ace0549662a52669f37379d45f07ff7e6ccc7
+oid sha256:0bd48ab963ce214f47ac10c51eb718536f51b1a5f4605ab693a533222db0cdb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2248de37d2320ddbb576171cc6b8d719f7febfba0a31c5797625bd8cfe79c5ab
+oid sha256:b06606e40b3f01ec7202acbfd1d0145e551b0842ff237681a6bdde0b316ef9b5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007200221545278316,
+  "epoch": 0.010800332317917475,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,49 @@
       "eval_samples_per_second": 13.19,
       "eval_steps_per_second": 1.65,
       "step": 26
+    },
+    {
+      "epoch": 0.007477153143173636,
+      "grad_norm": 5.528973579406738,
+      "learning_rate": 9.640574942595196e-05,
+      "loss": 1.6548,
+      "step": 27
+    },
+    {
+      "epoch": 0.008307947936859596,
+      "grad_norm": 5.370375156402588,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 1.6354,
+      "step": 30
+    },
+    {
+      "epoch": 0.009138742730545555,
+      "grad_norm": 4.518975257873535,
+      "learning_rate": 9.348705665778478e-05,
+      "loss": 1.5657,
+      "step": 33
+    },
+    {
+      "epoch": 0.009969537524231515,
+      "grad_norm": 3.3204827308654785,
+      "learning_rate": 9.172866268606513e-05,
+      "loss": 1.445,
+      "step": 36
+    },
+    {
+      "epoch": 0.010800332317917475,
+      "grad_norm": 5.033892631530762,
+      "learning_rate": 8.978122744408906e-05,
+      "loss": 1.8423,
+      "step": 39
+    },
+    {
+      "epoch": 0.010800332317917475,
+      "eval_loss": 0.37738242745399475,
+      "eval_runtime": 460.9405,
+      "eval_samples_per_second": 13.195,
+      "eval_steps_per_second": 1.651,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -106,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.290848871992525e+16,
+  "total_flos": 6.220067744671334e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null