Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace6e7e157675ddb18cef8c2951882b93f89a34d405eeab04e4fb83591c1c9f4
+oid sha256:101e467690e6cfc8a5d7aa80db7e412edf161b2e247ee642c0414ee35b486c8a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc358b2e7198a6f67dba7083025e594930a7cb2cc283e4eb8f1e334ca87bfbe6
+oid sha256:bb322a6110cf667e2eefc7b1df48c6304b407597507bc57013aa2170f378b676
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759e77ccf458a889b7b5189552587bc5a6060b4a877912775f82bf425e75e65c
+oid sha256:cb02ccd1192d7718ae1af09cd677fe41c23cc61772e1b6f0b39f71ad7e6f2935
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
+oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1102426052093506,
-  "best_model_checkpoint": "./outputs/checkpoint-2600",
-  "epoch": 1.8943533697632058,
+  "best_metric": 2.0868542194366455,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 2.040072859744991,
   "eval_steps": 100,
-  "global_step": 2600,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,13 +371,41 @@
       "eval_samples_per_second": 28.787,
       "eval_steps_per_second": 3.602,
       "step": 2600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0002,
+      "loss": 2.0912,
+      "step": 2700
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 2.0947265625,
+      "eval_runtime": 732.5061,
+      "eval_samples_per_second": 8.565,
+      "eval_steps_per_second": 1.072,
+      "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 2.0451,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 2.0868542194366455,
+      "eval_runtime": 206.5812,
+      "eval_samples_per_second": 30.371,
+      "eval_steps_per_second": 3.8,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.639893171800064e+16,
+  "total_flos": 8.22130227265536e+16,
   "trial_name": null,
   "trial_params": null
 }