Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab393f4f69f7faaabe6f587203b80b002df4d5f4deae60531d079471b2398fc8
+oid sha256:558e7465d377687eb906881916031bb1770d9f488fd320ade113fd07f17be5ec
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e59f4a5b952f7de2d14a1e4b442c685ddc19d1b6bc6935e00e1543052f0fb70
+oid sha256:63f1cd45b4034a774ef2ca6e975653b6fcdc049dfa5015dc213aedce891c9798
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21aa1eccb5e955300605eaedabdcacad3b7d7bb554f435899e349bc600e218c1
+oid sha256:31a89d946f018ae8ec20d21727f52890ae76d42d310519e1cdbe88caf957c76d
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bf86c7fa8dba501e212e7598dda77a96d03d446ef6d6602ce4549cab5e3433
+oid sha256:30fd428f7bdf69c6a307942278387977cf61df71ce4ee17c9f88ecc741d4d27f
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8d82289e709d88ce7e11eb2264d463e2f06559bce8de2ea8ceb1dbbcb140b2
+oid sha256:e1b5d142a2deb2b73e20bb2da7a287c14a081ee94b2a941cdf309d0a52aa227f
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7b39a43c9ddd21a784391ab651b996fc397e7948ea3728b6ed347349c25d39
+oid sha256:37b56cd327e6b3bbf22866fe109916c5fff8e24df311a4796dc622f41325bcb1
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8a9a69d2dbc37c276dc9c8c7976215efb5abec82bd5195d35a812f476169bf
+oid sha256:ee5138f9712ddacabb18b6e3fd50dbc9ef1d9b8b1d38a429995c36b6b1c2c379
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44513e8231963edc00282df0e974dd9749cbf03c12b1b03956513bba3c710161
+oid sha256:bd650cd588215a7fcb18601c400c576475be3c92c9a335908c7a02b961ee6dbe
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac6ff5012ef5c64bf048bf14aebbcc7c73af1661afaa8649ba1da43ff351099
+oid sha256:1d4c311558118cba7d04ccc2074d321bcd21ba9f9ca2b7e6154d605d9b537319
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0729ea6e854f6f2b1f006e69856f7968414c8a3b4a87e6a62ddbc50d669878de
+oid sha256:fd8e4609702d6766bcbd3a051f57a5f7b2bace94fb33f3d8503770baa1ea8ed3
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02054794520547945,
+  "epoch": 0.0410958904109589,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 36.675,
       "eval_steps_per_second": 4.622,
       "step": 3
+    },
+    {
+      "epoch": 0.0273972602739726,
+      "grad_norm": 1.4228770732879639,
+      "learning_rate": 6e-05,
+      "loss": 3.3901,
+      "step": 4
+    },
+    {
+      "epoch": 0.03424657534246575,
+      "grad_norm": 1.194941520690918,
+      "learning_rate": 8e-05,
+      "loss": 3.1024,
+      "step": 5
+    },
+    {
+      "epoch": 0.0410958904109589,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 2.7753,
+      "step": 6
+    },
+    {
+      "epoch": 0.0410958904109589,
+      "eval_loss": 4.003295421600342,
+      "eval_runtime": 6.7529,
+      "eval_samples_per_second": 36.429,
+      "eval_steps_per_second": 4.591,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5821535310774272e+16,
+  "total_flos": 3.1643070621548544e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null