Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3655fe9a9e98c3caac2cc33969712edee84b1fd55e5706fadeda2cb024b8cc8e
+oid sha256:0dbb01367f671944e9c6e9655a84db01999723494d0937bc1a89892aef6b45db
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e0ec8e40a120eda932450aa73b429890c5df137c4996b1ecc0f2df299a6833
+oid sha256:303d35bbb23dc6ed0336e81606e4782ec6e19b795af329b88d4e82830aa21b90
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110e6aa2d13c172c07d211ef5e0b299e4042a9ae85f51e78437b2380439da596
+oid sha256:12b75c47b564804b350765d160229fd697697b4a313f72348c86e82f4cef49df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4328358208955223,
+  "epoch": 1.6119402985074627,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 15.081,
       "eval_steps_per_second": 1.952,
       "step": 72
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 0.6062175035476685,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.9556,
+      "step": 75
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 0.6155171990394592,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.9589,
+      "step": 78
+    },
+    {
+      "epoch": 1.6119402985074627,
+      "grad_norm": 0.5605164766311646,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 0.8919,
+      "step": 81
+    },
+    {
+      "epoch": 1.6119402985074627,
+      "eval_loss": 0.9810183644294739,
+      "eval_runtime": 5.6412,
+      "eval_samples_per_second": 15.068,
+      "eval_steps_per_second": 1.95,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.405713993642803e+16,
+  "total_flos": 1.058193875706839e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null