Training in progress, step 3700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db0cf5a4ece07d5518df9b351a350822130f767b981f96a7b4d42d0a08e4587
+oid sha256:ee4d0e362935b12690a61f0d478a5b98a5a153ffc4f2cd0ed5ff8988dac962b7
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60772b5c6fb2cf3136edcb3b1211db1381f644a15efb8973b0b7c8df4b71c405
+oid sha256:5b4662e5629f5194b357369d4bc3c5c52910288f2f3d4ea85714127256f5db25
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df3b1a783378224e72061a0dd6a2c7409dcd465aeef53bc9c46e8f512f5d5a6b
+oid sha256:d1e78fca4663bc24e80d7e8f779d7b0c03678f0aafed4295ea283e96374bf926
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
+oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.096245765686035,
-  "best_model_checkpoint": "./outputs/checkpoint-3600",
-  "epoch": 2.6229508196721314,
+  "best_metric": 2.086164951324463,
+  "best_model_checkpoint": "./outputs/checkpoint-3700",
+  "epoch": 2.6958105646630237,
   "eval_steps": 100,
-  "global_step": 3600,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -511,13 +511,27 @@
       "eval_samples_per_second": 30.599,
       "eval_steps_per_second": 3.829,
       "step": 3600
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002,
+      "loss": 2.0508,
+      "step": 3700
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 2.086164951324463,
+      "eval_runtime": 206.1713,
+      "eval_samples_per_second": 30.431,
+      "eval_steps_per_second": 3.808,
+      "step": 3700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0251223767558144e+17,
+  "total_flos": 1.0533333313456128e+17,
   "trial_name": null,
   "trial_params": null
 }