Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea19551b24c113501540d7808d079ffb1e7666d656f99340ef270b8dc39ed06
+oid sha256:b05b517de513c6779c8a19034a68f842f09784089d4df2fe1201c64995083d3d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f967d19cce81e899639ae1d3d4d085d4f5f8e5f7ae3c1201fd45fbed525d8d
+oid sha256:346f5ae41ea0e9571fea16e8eb259c6a1f14901e23032287060cb42b4ae0c07c
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5c481e576c17914176850df3536b890e82450a0d594ebd816a9f05f22a132bf
+oid sha256:85446ac734307ad4c1e230db7d5d6a8d6dac6e2bec648ba2b41d25022bee9cdf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03035413153456998,
+  "epoch": 0.03541315345699832,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 18.182,
       "eval_steps_per_second": 2.275,
       "step": 54
+    },
+    {
+      "epoch": 0.03204047217537943,
+      "grad_norm": 0.16598886251449585,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.7398,
+      "step": 57
+    },
+    {
+      "epoch": 0.03372681281618887,
+      "grad_norm": 0.16655276715755463,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7534,
+      "step": 60
+    },
+    {
+      "epoch": 0.03541315345699832,
+      "grad_norm": 0.15536905825138092,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.7346,
+      "step": 63
+    },
+    {
+      "epoch": 0.03541315345699832,
+      "eval_loss": 0.7366407513618469,
+      "eval_runtime": 164.7935,
+      "eval_samples_per_second": 18.186,
+      "eval_steps_per_second": 2.276,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8215406875377664e+16,
+  "total_flos": 3.291797468794061e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null