Training in progress, epoch 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab885c8d2636478b9fd8af8e5f04b93f46c83262f3a98244172e1055bfede0c
+oid sha256:d31ff5b73762c4ae792ae7f3f219e10061f29a8f3b60e2fadee6b97cc45c1cdb
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d58c6900b70f0bb7ad3cb3fd1f72c827c80992dafe79096b4f3389aa22fbf8
+oid sha256:0b90890932f7fe71b0defece74b2b2f00c1fe185289d551d061a7932efbff82b
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257a1f1f5479cead68cf70d9af711ee0149b8e96cfaace5900f53644b78e311f
+oid sha256:fd22df0cd08ad15cc846a5018cba8d1f8ff40c8aa961fa9e9a7835026c44b248
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7e8408e8e5a0ed58cdde82e0e755570142c88ceb57101ce9f19ce52979f492
+oid sha256:70ccacca645aae41a4293a2aa37acee9e2b809b960d8056116131a8730010aef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 10689,
+  "global_step": 12216,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -749,6 +749,118 @@
       "learning_rate": 0.00013275632490013318,
       "loss": 0.2013,
       "step": 10600
+    },
+    {
+      "epoch": 7.007203667321545,
+      "grad_norm": 1.2111963033676147,
+      "learning_rate": 0.00013209054593874836,
+      "loss": 0.2092,
+      "step": 10700
+    },
+    {
+      "epoch": 7.072691552062868,
+      "grad_norm": 1.5347315073013306,
+      "learning_rate": 0.00013142476697736353,
+      "loss": 0.1873,
+      "step": 10800
+    },
+    {
+      "epoch": 7.138179436804191,
+      "grad_norm": 2.0928151607513428,
+      "learning_rate": 0.0001307589880159787,
+      "loss": 0.1778,
+      "step": 10900
+    },
+    {
+      "epoch": 7.203667321545514,
+      "grad_norm": 0.5348372459411621,
+      "learning_rate": 0.00013009320905459388,
+      "loss": 0.1842,
+      "step": 11000
+    },
+    {
+      "epoch": 7.269155206286837,
+      "grad_norm": 2.2082221508026123,
+      "learning_rate": 0.00012942743009320906,
+      "loss": 0.1813,
+      "step": 11100
+    },
+    {
+      "epoch": 7.33464309102816,
+      "grad_norm": 0.5544547438621521,
+      "learning_rate": 0.00012876165113182424,
+      "loss": 0.181,
+      "step": 11200
+    },
+    {
+      "epoch": 7.400130975769483,
+      "grad_norm": 2.8314151763916016,
+      "learning_rate": 0.0001280958721704394,
+      "loss": 0.19,
+      "step": 11300
+    },
+    {
+      "epoch": 7.465618860510806,
+      "grad_norm": 2.073094129562378,
+      "learning_rate": 0.0001274300932090546,
+      "loss": 0.1846,
+      "step": 11400
+    },
+    {
+      "epoch": 7.531106745252128,
+      "grad_norm": 0.7728668451309204,
+      "learning_rate": 0.00012676431424766976,
+      "loss": 0.1902,
+      "step": 11500
+    },
+    {
+      "epoch": 7.596594629993451,
+      "grad_norm": 0.958967387676239,
+      "learning_rate": 0.00012609853528628497,
+      "loss": 0.1943,
+      "step": 11600
+    },
+    {
+      "epoch": 7.662082514734774,
+      "grad_norm": 0.6349918842315674,
+      "learning_rate": 0.00012543275632490014,
+      "loss": 0.1911,
+      "step": 11700
+    },
+    {
+      "epoch": 7.727570399476097,
+      "grad_norm": 0.8367457985877991,
+      "learning_rate": 0.00012476697736351532,
+      "loss": 0.187,
+      "step": 11800
+    },
+    {
+      "epoch": 7.79305828421742,
+      "grad_norm": 1.9447026252746582,
+      "learning_rate": 0.0001241011984021305,
+      "loss": 0.1834,
+      "step": 11900
+    },
+    {
+      "epoch": 7.858546168958743,
+      "grad_norm": 1.063375473022461,
+      "learning_rate": 0.00012343541944074567,
+      "loss": 0.1945,
+      "step": 12000
+    },
+    {
+      "epoch": 7.9240340537000655,
+      "grad_norm": 0.40068888664245605,
+      "learning_rate": 0.00012276964047936085,
+      "loss": 0.186,
+      "step": 12100
+    },
+    {
+      "epoch": 7.9895219384413885,
+      "grad_norm": 0.7756742835044861,
+      "learning_rate": 0.00012210386151797602,
+      "loss": 0.1897,
+      "step": 12200
     }
   ],
   "logging_steps": 100,
@@ -768,7 +880,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.024368799049318e+16,
+  "total_flos": 4.599278634165862e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null