Training in progress, step 336, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc948873caa08921327726f20f406c613f84022f629a8b1be0e9b9d5c8d1f31
+oid sha256:c6c7a70d48890b36af3199b1750d7e5fd17b21aa11b89db9652dda5db64438a8
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ad83b8581d98d467b489581929046033ba13e2931665a83fafd2a14bfad6bf
+oid sha256:369e20b3070de99f6b2dbbf54cc6cbaa52f220bb8233b806b9dfba33eafacff4
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37abdf82049403a03d10ecacdbbeb17537569cc71638264b2a476090c2ddcbf8
+oid sha256:9f469bffe8acf737c47c0ff1bea10bc59a435d371a4846175c68c32944596f40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
+oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8316831683168316,
+  "epoch": 0.9504950495049505,
   "eval_steps": 42,
-  "global_step": 294,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,112 @@
       "eval_samples_per_second": 90.248,
       "eval_steps_per_second": 11.357,
       "step": 294
+    },
+    {
+      "epoch": 0.8401697312588402,
+      "grad_norm": 0.11685353517532349,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 11.8211,
+      "step": 297
+    },
+    {
+      "epoch": 0.8486562942008486,
+      "grad_norm": 0.10467521101236343,
+      "learning_rate": 3.5773620668448384e-05,
+      "loss": 11.8131,
+      "step": 300
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.08696059882640839,
+      "learning_rate": 3.48543465876014e-05,
+      "loss": 11.8151,
+      "step": 303
+    },
+    {
+      "epoch": 0.8656294200848657,
+      "grad_norm": 0.21422286331653595,
+      "learning_rate": 3.3940675559617724e-05,
+      "loss": 11.817,
+      "step": 306
+    },
+    {
+      "epoch": 0.8741159830268741,
+      "grad_norm": 0.09098684042692184,
+      "learning_rate": 3.303294559217063e-05,
+      "loss": 11.8177,
+      "step": 309
+    },
+    {
+      "epoch": 0.8826025459688827,
+      "grad_norm": 0.11003749072551727,
+      "learning_rate": 3.213149249506997e-05,
+      "loss": 11.8127,
+      "step": 312
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 0.10718018561601639,
+      "learning_rate": 3.12366497560313e-05,
+      "loss": 11.8152,
+      "step": 315
+    },
+    {
+      "epoch": 0.8995756718528995,
+      "grad_norm": 0.058545950800180435,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 11.8117,
+      "step": 318
+    },
+    {
+      "epoch": 0.9080622347949081,
+      "grad_norm": 0.15917275846004486,
+      "learning_rate": 2.9468116953203107e-05,
+      "loss": 11.816,
+      "step": 321
+    },
+    {
+      "epoch": 0.9165487977369166,
+      "grad_norm": 0.08903782814741135,
+      "learning_rate": 2.8595081148593738e-05,
+      "loss": 11.8119,
+      "step": 324
+    },
+    {
+      "epoch": 0.925035360678925,
+      "grad_norm": 0.10488823056221008,
+      "learning_rate": 2.772996397836704e-05,
+      "loss": 11.8185,
+      "step": 327
+    },
+    {
+      "epoch": 0.9335219236209336,
+      "grad_norm": 0.09897799789905548,
+      "learning_rate": 2.687308548795825e-05,
+      "loss": 11.8194,
+      "step": 330
+    },
+    {
+      "epoch": 0.942008486562942,
+      "grad_norm": 0.10232014954090118,
+      "learning_rate": 2.6024762674947313e-05,
+      "loss": 11.8139,
+      "step": 333
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.07098989188671112,
+      "learning_rate": 2.5185309371787513e-05,
+      "loss": 11.8159,
+      "step": 336
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "eval_loss": 11.817768096923828,
+      "eval_runtime": 6.6321,
+      "eval_samples_per_second": 89.866,
+      "eval_steps_per_second": 11.309,
+      "step": 336
     }
   ],
   "logging_steps": 3,
@@ -776,7 +882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1802989731840.0,
+  "total_flos": 2060904038400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null