Training in progress, step 238, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b11ec8052c5552f688ed9d416868cd53ddb56b5d87ead5a1ac28143162119f3
+oid sha256:94712826a7f2c0b7756c1d1754ed196d80b21d0e57551e1ca4f6dcd8cb62a183
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07cb456027b1e8133d5349eb14073d4e3f3071ed39e24a44c43b361c9a7e331
+oid sha256:c760d568f970c9090c6b12152f53f090933d3e37f77d860d804763cad359c610
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8513bc15602cc9778e1a951f5ade81824ac1d664cd10d25d7f7f817465e8501d
+oid sha256:914b1fa34e1d3c8a9975e1e5a238a3740456137dacecfe916285c613ce13f0db
 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": 0.05800398066533978,
+  "epoch": 0.06767131077622975,
   "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": 35.272,
       "eval_steps_per_second": 4.412,
       "step": 204
+    },
+    {
+      "epoch": 0.05885698038100654,
+      "grad_norm": 0.47230827808380127,
+      "learning_rate": 2.459724913431772e-05,
+      "loss": 0.5152,
+      "step": 207
+    },
+    {
+      "epoch": 0.059709980096673304,
+      "grad_norm": 0.5665333867073059,
+      "learning_rate": 2.399335149726463e-05,
+      "loss": 0.5736,
+      "step": 210
+    },
+    {
+      "epoch": 0.06056297981234006,
+      "grad_norm": 0.47652244567871094,
+      "learning_rate": 2.3390041714589514e-05,
+      "loss": 0.5006,
+      "step": 213
+    },
+    {
+      "epoch": 0.06141597952800682,
+      "grad_norm": 0.7172293663024902,
+      "learning_rate": 2.2787672102216042e-05,
+      "loss": 0.4619,
+      "step": 216
+    },
+    {
+      "epoch": 0.06226897924367358,
+      "grad_norm": 0.5251888036727905,
+      "learning_rate": 2.2186594427034864e-05,
+      "loss": 0.4852,
+      "step": 219
+    },
+    {
+      "epoch": 0.06312197895934035,
+      "grad_norm": 0.45427563786506653,
+      "learning_rate": 2.1587159701481716e-05,
+      "loss": 0.4936,
+      "step": 222
+    },
+    {
+      "epoch": 0.06397497867500711,
+      "grad_norm": 0.49813351035118103,
+      "learning_rate": 2.098971797855599e-05,
+      "loss": 0.5062,
+      "step": 225
+    },
+    {
+      "epoch": 0.06482797839067388,
+      "grad_norm": 0.510427713394165,
+      "learning_rate": 2.0394618147399713e-05,
+      "loss": 0.4742,
+      "step": 228
+    },
+    {
+      "epoch": 0.06568097810634063,
+      "grad_norm": 0.5860615372657776,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 0.5472,
+      "step": 231
+    },
+    {
+      "epoch": 0.06653397782200739,
+      "grad_norm": 0.45956236124038696,
+      "learning_rate": 1.921283267602643e-05,
+      "loss": 0.5065,
+      "step": 234
+    },
+    {
+      "epoch": 0.06738697753767416,
+      "grad_norm": 0.46069616079330444,
+      "learning_rate": 1.8626837165245165e-05,
+      "loss": 0.4309,
+      "step": 237
+    },
+    {
+      "epoch": 0.06767131077622975,
+      "eval_loss": 0.4809924364089966,
+      "eval_runtime": 167.8669,
+      "eval_samples_per_second": 35.29,
+      "eval_steps_per_second": 4.414,
+      "step": 238
     }
   ],
   "logging_steps": 3,
@@ -558,7 +643,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.532800359222477e+16,
+  "total_flos": 7.62160041909289e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null