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:b094796a3043040fc20becd553325e34a769103a7c5d10ae18b6158c1c1849f5
+oid sha256:a07dee49d799c7c4e594b277793ea8c2c44a124a650537f11e3afe2258bf9b52
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39557afe36d5e189e1e04d3e99f8bd45f3b28f96a8c1d63dc4f40cb53e95a33c
+oid sha256:8281e7a7c385c76306c3e004746a48faed6d6fc5dc06a058997a000d46c08896
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119fe715ac3c860103e8a9debc4f03af2063cfd89cb1715847cde9fb4c7fc469
+oid sha256:43b6f75817f48f21e99a60f7fdd4858dd8e6cf511942acb28532f05a198992fd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c871a29aafc4cc2e188c2a1192be10629a3367edb40bd6f57fc891f110c0b32
+oid sha256:1c4bec5f2ca6548158d067a427656c807f869711b2091a276a7aca2125ea8d69
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5505f1fb01d87dde14fc81379497ded1f5f974f64cedaf83d975d1311d82a953
+oid sha256:dec3fb92b10a22709bb248d99db74c3e5d2a3281e3681c398d8c43f78f024c67
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea6038eeb267887dcd89f798edd4e04b2ce9df9d4541d4f61f2a0a5c24c73a3
+oid sha256:c4d94cc971111c55703dacd86e4e6c559013000276fcee696a129b53ceb6f248
 size 15024

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": 0.9875898105813194,
+  "epoch": 1.0979751796211628,
   "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": 775.289,
       "eval_steps_per_second": 24.359,
       "step": 378
+    },
+    {
+      "epoch": 0.9954278249510125,
+      "grad_norm": 0.03160930424928665,
+      "learning_rate": 1.3860256808630428e-05,
+      "loss": 11.9168,
+      "step": 381
+    },
+    {
+      "epoch": 1.0039190071848465,
+      "grad_norm": 0.017380647361278534,
+      "learning_rate": 1.3202379370768252e-05,
+      "loss": 13.741,
+      "step": 384
+    },
+    {
+      "epoch": 1.0117570215545395,
+      "grad_norm": 0.0193234421312809,
+      "learning_rate": 1.2558115014363592e-05,
+      "loss": 12.1761,
+      "step": 387
+    },
+    {
+      "epoch": 1.0195950359242325,
+      "grad_norm": 0.02974247932434082,
+      "learning_rate": 1.1927702081543279e-05,
+      "loss": 11.7776,
+      "step": 390
+    },
+    {
+      "epoch": 1.0274330502939255,
+      "grad_norm": 0.014591868035495281,
+      "learning_rate": 1.1311373790174657e-05,
+      "loss": 12.203,
+      "step": 393
+    },
+    {
+      "epoch": 1.0352710646636185,
+      "grad_norm": 0.018022043630480766,
+      "learning_rate": 1.0709358147587884e-05,
+      "loss": 11.431,
+      "step": 396
+    },
+    {
+      "epoch": 1.0431090790333115,
+      "grad_norm": 0.019987676292657852,
+      "learning_rate": 1.0121877866225781e-05,
+      "loss": 12.1733,
+      "step": 399
+    },
+    {
+      "epoch": 1.0509470934030045,
+      "grad_norm": 0.022911233827471733,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9096,
+      "step": 402
+    },
+    {
+      "epoch": 1.0587851077726975,
+      "grad_norm": 0.019524535164237022,
+      "learning_rate": 8.991387270152201e-06,
+      "loss": 12.1372,
+      "step": 405
+    },
+    {
+      "epoch": 1.0666231221423905,
+      "grad_norm": 0.016502438113093376,
+      "learning_rate": 8.448795174344804e-06,
+      "loss": 11.5679,
+      "step": 408
+    },
+    {
+      "epoch": 1.0744611365120835,
+      "grad_norm": 0.015734922140836716,
+      "learning_rate": 7.921574722852343e-06,
+      "loss": 12.0084,
+      "step": 411
+    },
+    {
+      "epoch": 1.0822991508817765,
+      "grad_norm": 0.019688883796334267,
+      "learning_rate": 7.409920958039795e-06,
+      "loss": 11.8272,
+      "step": 414
+    },
+    {
+      "epoch": 1.0901371652514695,
+      "grad_norm": 0.016949467360973358,
+      "learning_rate": 6.9140231634602485e-06,
+      "loss": 12.0226,
+      "step": 417
+    },
+    {
+      "epoch": 1.0979751796211628,
+      "grad_norm": 0.015972912311553955,
+      "learning_rate": 6.43406479383053e-06,
+      "loss": 12.0123,
+      "step": 420
+    },
+    {
+      "epoch": 1.0979751796211628,
+      "eval_loss": 11.916641235351562,
+      "eval_runtime": 3.3258,
+      "eval_samples_per_second": 775.161,
+      "eval_steps_per_second": 24.355,
+      "step": 420
     }
   ],
   "logging_steps": 3,
@@ -988,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7292707799040.0,
+  "total_flos": 8102606929920.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null