Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0042f02600a8eac977dd9874deade488adf87be69b882d4413e34b523811946
+oid sha256:040a5e9a1139967d63e8780736b9e02ba4505f07efc590995875aa207f1b310d
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0903f025bb1f924ff814f0ba871b8954a018e154a5471eec323a4ffd557d4e5
+oid sha256:0a9788a292cb1c6a3cd380e4403312823977981d4ed056afb4b25c3e4597942c
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:010413cb75d937c2e81eafe41424c781768b0a5c18bbffd4b2047ef215a522a3
+oid sha256:65aff41284df3bb03394cbdcf4e3b2890e7e5a16910233362baef91ee578828c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008040946976140037,
+  "epoch": 0.0016081893952280073,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 7.027,
       "eval_steps_per_second": 3.513,
       "step": 10
+    },
+    {
+      "epoch": 0.0009278015741700042,
+      "grad_norm": 3.517625331878662,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.5198,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012370687655600056,
+      "grad_norm": 4.388193607330322,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.4901,
+      "step": 20
+    },
+    {
+      "epoch": 0.0012370687655600056,
+      "eval_loss": 2.343156337738037,
+      "eval_runtime": 968.5965,
+      "eval_samples_per_second": 7.029,
+      "eval_steps_per_second": 3.514,
+      "step": 20
+    },
+    {
+      "epoch": 0.001546335956950007,
+      "grad_norm": 4.974583625793457,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.2323,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4682173969858560.0,
+  "total_flos": 9268793368903680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null