Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733955d7430626ad27e7cd21e8ca9ec50feb3dac00670eda54bf5b86a4d11bdc
+oid sha256:cc84d6633e49926ea714145b651a406d61ebd7ad5561eff4d11de1ce0fecf93e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923874c9454c21ebc45bc507bce206d6f533859e5ac02bbefaacff47b72d8291
+oid sha256:e6d56e75e152e0644a94d2eea40fc20ec9bc18614589b796bfe9d3fd290b174c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4d313fa7929ad810337d98d6b1442ab197c018fee0ba8eebf9b014126013f6
+oid sha256:07c7e644c47c62f5a31332d139d09f879e7b653da5cbc64fa55026f31d1123a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7fb3cac05a1696d562ac7b77dbf668b975c179419a621821b322c77a567759
+oid sha256:6a358404286a5e4f3258996b41c418ca8149d7be647bd8b06e725c0e87267272
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02938683243854196,
+  "epoch": 0.04408024865781294,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,49 @@
       "eval_samples_per_second": 6.627,
       "eval_steps_per_second": 0.832,
       "step": 26
+    },
+    {
+      "epoch": 0.030517095224639728,
+      "grad_norm": 1.757283091545105,
+      "learning_rate": 4.820287471297598e-05,
+      "loss": 0.6531,
+      "step": 27
+    },
+    {
+      "epoch": 0.033907883582933035,
+      "grad_norm": 1.2630192041397095,
+      "learning_rate": 4.752422169756048e-05,
+      "loss": 0.616,
+      "step": 30
+    },
+    {
+      "epoch": 0.03729867194122634,
+      "grad_norm": 1.2325754165649414,
+      "learning_rate": 4.674352832889239e-05,
+      "loss": 0.6141,
+      "step": 33
+    },
+    {
+      "epoch": 0.040689460299519635,
+      "grad_norm": 1.5199618339538574,
+      "learning_rate": 4.586433134303257e-05,
+      "loss": 0.6026,
+      "step": 36
+    },
+    {
+      "epoch": 0.04408024865781294,
+      "grad_norm": 1.2060375213623047,
+      "learning_rate": 4.489061372204453e-05,
+      "loss": 0.6114,
+      "step": 39
+    },
+    {
+      "epoch": 0.04408024865781294,
+      "eval_loss": 0.14285726845264435,
+      "eval_runtime": 224.8051,
+      "eval_samples_per_second": 6.628,
+      "eval_steps_per_second": 0.832,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -106,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.312555161472205e+16,
+  "total_flos": 1.0968832742208307e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null