Training in progress, step 248, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a069365120e85adb14a02be1d6d1bcb7f57bd56552e43dae1279161a73ba747
+oid sha256:781893ab268a460d6c6281d7328238df1862c326fc57bc1a1cce25d4e4fca254
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038ad53f8bbc1f098ba079bddbf6a3f8098ff367610e685c65b90cc790e33514
+oid sha256:f6927a83945068a1faaa14b39736f3798ea663c353aa04ca6e7da7e5afc917be
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da25d38ebcf1dfe8351fa92f64b9a44da3c87afd204df29f93fba4ad49762fa
+oid sha256:5f5d3012cf842ae96026cfb7617d36b883980d38f99422e689133b1c4367194e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89729c98649b6d89eebc77276357ac5f2594b10fb1a49cf61a28a5fa2b4c3d3
+oid sha256:dd4195f21f3ab721f41e157ad5801251bc3ef7a33dc24988ba85a5ba8d1d1f0e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7606490872210954,
+  "epoch": 2.0121703853955375,
   "eval_steps": 31,
-  "global_step": 217,
+  "global_step": 248,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -575,6 +575,84 @@
       "eval_samples_per_second": 15.485,
       "eval_steps_per_second": 1.936,
       "step": 217
+    },
+    {
+      "epoch": 1.7768762677484786,
+      "grad_norm": 5.897202968597412,
+      "learning_rate": 3.748099979727792e-05,
+      "loss": 1.6029,
+      "step": 219
+    },
+    {
+      "epoch": 1.8012170385395536,
+      "grad_norm": 4.379933834075928,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.6497,
+      "step": 222
+    },
+    {
+      "epoch": 1.8255578093306288,
+      "grad_norm": 4.874183177947998,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 1.6421,
+      "step": 225
+    },
+    {
+      "epoch": 1.8498985801217038,
+      "grad_norm": 4.163862705230713,
+      "learning_rate": 3.372159227714218e-05,
+      "loss": 1.4842,
+      "step": 228
+    },
+    {
+      "epoch": 1.874239350912779,
+      "grad_norm": 4.190274238586426,
+      "learning_rate": 3.248963093702663e-05,
+      "loss": 1.6199,
+      "step": 231
+    },
+    {
+      "epoch": 1.898580121703854,
+      "grad_norm": 4.762985706329346,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.6452,
+      "step": 234
+    },
+    {
+      "epoch": 1.922920892494929,
+      "grad_norm": 5.081422805786133,
+      "learning_rate": 3.006254655373769e-05,
+      "loss": 1.6196,
+      "step": 237
+    },
+    {
+      "epoch": 1.947261663286004,
+      "grad_norm": 4.602591037750244,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 1.6198,
+      "step": 240
+    },
+    {
+      "epoch": 1.971602434077079,
+      "grad_norm": 4.777091026306152,
+      "learning_rate": 2.7690109344509563e-05,
+      "loss": 1.6883,
+      "step": 243
+    },
+    {
+      "epoch": 1.995943204868154,
+      "grad_norm": 5.713743209838867,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.5588,
+      "step": 246
+    },
+    {
+      "epoch": 2.0121703853955375,
+      "eval_loss": 0.48639488220214844,
+      "eval_runtime": 13.4291,
+      "eval_samples_per_second": 15.489,
+      "eval_steps_per_second": 1.936,
+      "step": 248
     }
   ],
   "logging_steps": 3,
@@ -594,7 +672,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.884265370640712e+17,
+  "total_flos": 3.293808601155502e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null