Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c5ec15f84223b0454fad1686c66abb74e48a721b8aae07fc873f6d7362a795
+oid sha256:1bd253373d14792b1c72fb1f26a2d3c0c7f58984e6c01eef57ea13b2eb9056d0
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2cd2dafdb17e6a0bdc82605c0c2a15c7a1d2b8e95044ed00b6bf9d046f49dfe
+oid sha256:964ee8b98d3ada3b620642817a8e7ea24b88d32d6912af8dedff76fedac349f9
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fba7b3aa24187728c3eecfbdd90586f69803afe4ee661ac3d5463e4c2381ab0
+oid sha256:c3c89468324c1a809962ad3dc3aa38e4a778e3d65a72b8d32588df9de3b7b85a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b6afe9f4b9513bda96be941880d24726826d6e0d0960bca314ae3f1d65fc06
+oid sha256:512576cc203164442a0e0284b99a04b73f2839ef4315a8aea93837a11a880d8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014977767376550433,
+  "epoch": 0.019970356502067244,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -95,6 +95,28 @@
       "eval_samples_per_second": 9.397,
       "eval_steps_per_second": 4.699,
       "step": 24
+    },
+    {
+      "epoch": 0.016849988298619237,
+      "grad_norm": 0.40756919980049133,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.8186,
+      "step": 27
+    },
+    {
+      "epoch": 0.01872220922068804,
+      "grad_norm": 0.5308417081832886,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.8643,
+      "step": 30
+    },
+    {
+      "epoch": 0.019970356502067244,
+      "eval_loss": 0.7987203001976013,
+      "eval_runtime": 575.0353,
+      "eval_samples_per_second": 9.387,
+      "eval_steps_per_second": 4.694,
+      "step": 32
     }
   ],
   "logging_steps": 3,
@@ -114,7 +136,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2768461029638144e+17,
+  "total_flos": 1.7024614706184192e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null