Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101e467690e6cfc8a5d7aa80db7e412edf161b2e247ee642c0414ee35b486c8a
+oid sha256:3eb110544751599c957e4ec900fd2bc3a6fd62da2ac029bd4078a8954ca7480b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb322a6110cf667e2eefc7b1df48c6304b407597507bc57013aa2170f378b676
+oid sha256:25deb4b33095e0124e0d2c0a9488366f70b518a9b351967dc14aff6ad6b992ac
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb02ccd1192d7718ae1af09cd677fe41c23cc61772e1b6f0b39f71ad7e6f2935
+oid sha256:b597608731e9fda30cc7f58f49388742efa2b4e42761755355b7e670b12c553c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0868542194366455,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 2.074641227722168,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 30.371,
       "eval_steps_per_second": 3.8,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 2.0179,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 2.074641227722168,
+      "eval_runtime": 206.384,
+      "eval_samples_per_second": 30.4,
+      "eval_steps_per_second": 3.804,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.22130227265536e+16,
+  "total_flos": 8.514013463617536e+16,
   "trial_name": null,
   "trial_params": null
 }