Training in progress, step 238, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c931d5dcab4934d664c86b7b9f1cc7cd35a706b9856206ace9d697eb010c61d
+oid sha256:2197374a33c735028aa536e5fe3af5bc9dc788ab33b4fdcd1ffde4b50ce69bbb
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b3f55f7dbe9de2ff2648d336ff782d60d2eaf477c10452e4200763918493d8
+oid sha256:0c2cf7495a13cc47c2d3a8e0b35e97a8a7aa07a0004cdc17b247f3a74ecf175a
 size 67487892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6936f48172630f3b195d633d05bbdd084bbd64378cb9f0296e98ae7438be100
+oid sha256:0d67ee95f12db6e88f171eb80bca0d2075b72de13453defea2104a6a62511134
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9839d107756d9c8815de9164f2ebf92c05b3536704a349ca5892084df7663e
+oid sha256:bbcef9424696e41c7961bd91f0570d39d59ef33af28ed19a0eb9e4f50ed1b09a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11336482356210058,
+  "epoch": 0.13225896082245067,
   "eval_steps": 34,
-  "global_step": 204,
+  "global_step": 238,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,6 +539,91 @@
       "eval_samples_per_second": 7.822,
       "eval_steps_per_second": 0.978,
       "step": 204
+    },
+    {
+      "epoch": 0.11503195332036677,
+      "grad_norm": 2.1243629455566406,
+      "learning_rate": 2.459724913431772e-05,
+      "loss": 5.1268,
+      "step": 207
+    },
+    {
+      "epoch": 0.11669908307863296,
+      "grad_norm": 1.8287479877471924,
+      "learning_rate": 2.399335149726463e-05,
+      "loss": 4.8911,
+      "step": 210
+    },
+    {
+      "epoch": 0.11836621283689913,
+      "grad_norm": 1.827951431274414,
+      "learning_rate": 2.3390041714589514e-05,
+      "loss": 5.0788,
+      "step": 213
+    },
+    {
+      "epoch": 0.12003334259516532,
+      "grad_norm": 1.9181324243545532,
+      "learning_rate": 2.2787672102216042e-05,
+      "loss": 5.2716,
+      "step": 216
+    },
+    {
+      "epoch": 0.12170047235343151,
+      "grad_norm": 2.334996461868286,
+      "learning_rate": 2.2186594427034864e-05,
+      "loss": 5.4529,
+      "step": 219
+    },
+    {
+      "epoch": 0.1233676021116977,
+      "grad_norm": 2.042280673980713,
+      "learning_rate": 2.1587159701481716e-05,
+      "loss": 4.8902,
+      "step": 222
+    },
+    {
+      "epoch": 0.1250347318699639,
+      "grad_norm": 1.9080718755722046,
+      "learning_rate": 2.098971797855599e-05,
+      "loss": 4.933,
+      "step": 225
+    },
+    {
+      "epoch": 0.12670186162823005,
+      "grad_norm": 1.7101670503616333,
+      "learning_rate": 2.0394618147399713e-05,
+      "loss": 5.0186,
+      "step": 228
+    },
+    {
+      "epoch": 0.12836899138649624,
+      "grad_norm": 2.011359453201294,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 4.7936,
+      "step": 231
+    },
+    {
+      "epoch": 0.13003612114476243,
+      "grad_norm": 2.302273750305176,
+      "learning_rate": 1.921283267602643e-05,
+      "loss": 5.1487,
+      "step": 234
+    },
+    {
+      "epoch": 0.13170325090302862,
+      "grad_norm": 2.4797189235687256,
+      "learning_rate": 1.8626837165245165e-05,
+      "loss": 5.2862,
+      "step": 237
+    },
+    {
+      "epoch": 0.13225896082245067,
+      "eval_loss": 1.303543210029602,
+      "eval_runtime": 387.3037,
+      "eval_samples_per_second": 7.826,
+      "eval_steps_per_second": 0.979,
+      "step": 238
     }
   ],
   "logging_steps": 3,
@@ -558,7 +643,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.07623549249536e+17,
+  "total_flos": 4.75512659152896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null