Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29046213a991b5eadc248f90be681087b37e001bc4afc585a83f12d47f0233d7
+oid sha256:35b0db7d479601e21e8f0626e67fea9b826f418569abf03d4a42c25218d2bbb0
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b4f78d3c9e9f9d78df5489b3d6ab7f6417c6c47d6429bfeebc25047975ba6f
+oid sha256:3a5f9bb544edbf970e83de407f978f724ad3e44d97dcc88a78ab8d38478e9418
 size 7825914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ba9cb58552d57919ace8ff4e50292be4084136c7d5c3eed2aa84b64d8ad528
+oid sha256:5498bdb9b4323418be388590bc2e68008eff5e39569ec0e9c796f50445383dfc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08144796380090498,
+  "epoch": 0.09049773755656108,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 151.475,
       "eval_steps_per_second": 18.991,
       "step": 81
+    },
+    {
+      "epoch": 0.08446455505279035,
+      "grad_norm": 2.67712140083313,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 4.168,
+      "step": 84
+    },
+    {
+      "epoch": 0.08748114630467571,
+      "grad_norm": 2.538766860961914,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 4.1359,
+      "step": 87
+    },
+    {
+      "epoch": 0.09049773755656108,
+      "grad_norm": 2.631545305252075,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 4.1228,
+      "step": 90
+    },
+    {
+      "epoch": 0.09049773755656108,
+      "eval_loss": 4.152175426483154,
+      "eval_runtime": 11.1662,
+      "eval_samples_per_second": 150.007,
+      "eval_steps_per_second": 18.807,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6942710984343552.0,
+  "total_flos": 7714123315937280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null