Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e09d1d300d7dcd4e382ff72e7924ef6b9bca66b4e5d810a27cda3693e33de86
+oid sha256:dea19551b24c113501540d7808d079ffb1e7666d656f99340ef270b8dc39ed06
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7523714a9958ff8938294936bfd01d897220e490eb175cb7a3409c80733c21fe
+oid sha256:e3f967d19cce81e899639ae1d3d4d085d4f5f8e5f7ae3c1201fd45fbed525d8d
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b5265eca0f1b80fa74df31167c9740f8dbc34b19adfc7d5eefc35310f0a33a
+oid sha256:a5c481e576c17914176850df3536b890e82450a0d594ebd816a9f05f22a132bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025295109612141653,
+  "epoch": 0.03035413153456998,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 18.19,
       "eval_steps_per_second": 2.276,
       "step": 45
+    },
+    {
+      "epoch": 0.026981450252951095,
+      "grad_norm": 0.15612190961837769,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.7528,
+      "step": 48
+    },
+    {
+      "epoch": 0.02866779089376054,
+      "grad_norm": 0.15889355540275574,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.7408,
+      "step": 51
+    },
+    {
+      "epoch": 0.03035413153456998,
+      "grad_norm": 0.16103751957416534,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.7259,
+      "step": 54
+    },
+    {
+      "epoch": 0.03035413153456998,
+      "eval_loss": 0.7405259013175964,
+      "eval_runtime": 164.8345,
+      "eval_samples_per_second": 18.182,
+      "eval_steps_per_second": 2.275,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.351283906281472e+16,
+  "total_flos": 2.8215406875377664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null