Training in progress, step 176, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5872be2126b15802eada500482cac157e1cd15f99b724a9f187dba5f99bafc9
+oid sha256:72ce63bf80e3fe75c543395c98fbe8e01a2544bd8150423346530c9da91f0ce1
 size 479769104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bc8c5c01889b8832eca2082109ae4436d43907021d6cf8390bfb7f695a25a9
+oid sha256:b509609cd98971e06b2049ce774579afe57b9760f48d07ecf58ba2c8524a8b17
 size 240728084

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300c8159d4f2286b17795d32870d10fc9b17bf00e3d175e60b6c67ddbb2ad949
+oid sha256:4add145129184e11af087cef41cfbbb05756226b865c01b02ddb6159cd74dc10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010344207546826733,
+  "epoch": 0.011378628301509406,
   "eval_steps": 500,
-  "global_step": 160,
+  "global_step": 176,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1127,6 +1127,118 @@
       "learning_rate": 9.999997369030074e-06,
       "loss": 1.3629,
       "step": 160
+    },
+    {
+      "epoch": 0.0104088588439944,
+      "grad_norm": 4.200235366821289,
+      "learning_rate": 9.999996211403454e-06,
+      "loss": 1.4429,
+      "step": 161
+    },
+    {
+      "epoch": 0.010473510141162067,
+      "grad_norm": 4.418542385101318,
+      "learning_rate": 9.999994843299381e-06,
+      "loss": 1.3971,
+      "step": 162
+    },
+    {
+      "epoch": 0.010538161438329734,
+      "grad_norm": 4.672099590301514,
+      "learning_rate": 9.999993264717911e-06,
+      "loss": 1.3352,
+      "step": 163
+    },
+    {
+      "epoch": 0.0106028127354974,
+      "grad_norm": 4.304332256317139,
+      "learning_rate": 9.999991475659115e-06,
+      "loss": 1.3116,
+      "step": 164
+    },
+    {
+      "epoch": 0.010667464032665068,
+      "grad_norm": 4.34376335144043,
+      "learning_rate": 9.999989476123067e-06,
+      "loss": 1.3822,
+      "step": 165
+    },
+    {
+      "epoch": 0.010732115329832734,
+      "grad_norm": 4.60739278793335,
+      "learning_rate": 9.999987266109848e-06,
+      "loss": 1.3655,
+      "step": 166
+    },
+    {
+      "epoch": 0.010796766627000402,
+      "grad_norm": 6.895850658416748,
+      "learning_rate": 9.999984845619553e-06,
+      "loss": 1.3699,
+      "step": 167
+    },
+    {
+      "epoch": 0.010861417924168068,
+      "grad_norm": 3.9377450942993164,
+      "learning_rate": 9.999982214652286e-06,
+      "loss": 1.4356,
+      "step": 168
+    },
+    {
+      "epoch": 0.010926069221335736,
+      "grad_norm": 4.687614440917969,
+      "learning_rate": 9.999979373208155e-06,
+      "loss": 1.3916,
+      "step": 169
+    },
+    {
+      "epoch": 0.010990720518503404,
+      "grad_norm": 4.686786651611328,
+      "learning_rate": 9.99997632128728e-06,
+      "loss": 1.3448,
+      "step": 170
+    },
+    {
+      "epoch": 0.01105537181567107,
+      "grad_norm": 4.827507495880127,
+      "learning_rate": 9.999973058889791e-06,
+      "loss": 1.3514,
+      "step": 171
+    },
+    {
+      "epoch": 0.011120023112838738,
+      "grad_norm": 4.3625617027282715,
+      "learning_rate": 9.999969586015824e-06,
+      "loss": 1.4232,
+      "step": 172
+    },
+    {
+      "epoch": 0.011184674410006404,
+      "grad_norm": 4.434966087341309,
+      "learning_rate": 9.999965902665524e-06,
+      "loss": 1.4217,
+      "step": 173
+    },
+    {
+      "epoch": 0.011249325707174072,
+      "grad_norm": 5.053067207336426,
+      "learning_rate": 9.99996200883905e-06,
+      "loss": 1.4709,
+      "step": 174
+    },
+    {
+      "epoch": 0.011313977004341738,
+      "grad_norm": 4.309473514556885,
+      "learning_rate": 9.999957904536562e-06,
+      "loss": 1.3668,
+      "step": 175
+    },
+    {
+      "epoch": 0.011378628301509406,
+      "grad_norm": 4.460648536682129,
+      "learning_rate": 9.999953589758235e-06,
+      "loss": 1.4512,
+      "step": 176
     }
   ],
   "logging_steps": 1,
@@ -1146,7 +1258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0243901698014413e+17,
+  "total_flos": 1.1276252815822848e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null