Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d063cd2f43da55fad1cd08c0ec68730795948d509943ac12d0989fc1b042902a
+oid sha256:2c65f2723695d55c4676894a4cc573fa60c43c6f9d8e6b10a5f8338a48cb5495
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307011717607beb98059ae3e6c8abc5c930ba32f7ed58acaee35a67539119e6e
+oid sha256:9d0f7e9bc2d46e8ee5840e716e44a1192336abc75f777e9c4ef214dc13e626af
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb8f50440c4f92407ced559dfc13a069c63b86644238d589ef96192341f8039
+oid sha256:2cdfe269170b74b584fdf82fb7f4fe475adef4c7006c041ed6cb8c1885b4ecaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac207b57c6cefba3838e335ba7ebf320ffdaee8162f1c0afc72ea9ad9f0725f
+oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0693069306930694,
+  "epoch": 1.188118811881188,
   "eval_steps": 42,
-  "global_step": 378,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -969,6 +969,112 @@
       "eval_samples_per_second": 89.851,
       "eval_steps_per_second": 11.307,
       "step": 378
+    },
+    {
+      "epoch": 1.0777934936350777,
+      "grad_norm": 0.12858428061008453,
+      "learning_rate": 1.3860256808630428e-05,
+      "loss": 11.8168,
+      "step": 381
+    },
+    {
+      "epoch": 1.0862800565770863,
+      "grad_norm": 0.1034870445728302,
+      "learning_rate": 1.3202379370768252e-05,
+      "loss": 11.8184,
+      "step": 384
+    },
+    {
+      "epoch": 1.0947666195190948,
+      "grad_norm": 0.19289083778858185,
+      "learning_rate": 1.2558115014363592e-05,
+      "loss": 11.8211,
+      "step": 387
+    },
+    {
+      "epoch": 1.1032531824611032,
+      "grad_norm": 0.15419146418571472,
+      "learning_rate": 1.1927702081543279e-05,
+      "loss": 11.8142,
+      "step": 390
+    },
+    {
+      "epoch": 1.1117397454031117,
+      "grad_norm": 0.15567056834697723,
+      "learning_rate": 1.1311373790174657e-05,
+      "loss": 11.8155,
+      "step": 393
+    },
+    {
+      "epoch": 1.1202263083451203,
+      "grad_norm": 0.13290712237358093,
+      "learning_rate": 1.0709358147587884e-05,
+      "loss": 11.8208,
+      "step": 396
+    },
+    {
+      "epoch": 1.1287128712871288,
+      "grad_norm": 0.09749293327331543,
+      "learning_rate": 1.0121877866225781e-05,
+      "loss": 11.8177,
+      "step": 399
+    },
+    {
+      "epoch": 1.1371994342291372,
+      "grad_norm": 0.120842345058918,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.8156,
+      "step": 402
+    },
+    {
+      "epoch": 1.1456859971711457,
+      "grad_norm": 0.09248703718185425,
+      "learning_rate": 8.991387270152201e-06,
+      "loss": 11.8186,
+      "step": 405
+    },
+    {
+      "epoch": 1.154172560113154,
+      "grad_norm": 0.12557213008403778,
+      "learning_rate": 8.448795174344804e-06,
+      "loss": 11.8199,
+      "step": 408
+    },
+    {
+      "epoch": 1.1626591230551626,
+      "grad_norm": 0.17817071080207825,
+      "learning_rate": 7.921574722852343e-06,
+      "loss": 11.8154,
+      "step": 411
+    },
+    {
+      "epoch": 1.1711456859971712,
+      "grad_norm": 0.10258757323026657,
+      "learning_rate": 7.409920958039795e-06,
+      "loss": 11.8124,
+      "step": 414
+    },
+    {
+      "epoch": 1.1796322489391797,
+      "grad_norm": 0.16313178837299347,
+      "learning_rate": 6.9140231634602485e-06,
+      "loss": 11.815,
+      "step": 417
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.10050709545612335,
+      "learning_rate": 6.43406479383053e-06,
+      "loss": 11.8149,
+      "step": 420
+    },
+    {
+      "epoch": 1.188118811881188,
+      "eval_loss": 11.817734718322754,
+      "eval_runtime": 6.4421,
+      "eval_samples_per_second": 92.516,
+      "eval_steps_per_second": 11.642,
+      "step": 420
     }
   ],
   "logging_steps": 3,
@@ -988,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2328761303040.0,
+  "total_flos": 2580649574400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null