Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bf170a4262ebe1fff81baaeeb218372d2e30888e171ac702c009ebd68a8f4a
+oid sha256:f0364959151c84c34d4284db641d008637cca756cb9d5c66bb7a31bd8d457271
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1ee60a8dbf6dae548bd961ea1ca9672484fce9c8d9c1cae7edb3f72bdd270e
+oid sha256:d4231b80d9cdd7e85e75239e8b0268bb43acb57c30d109375602ba3fea01d501
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2976c6db6ebcdf9dabf12702a779e061718bd1c4ef8e49e51b66e2a5fcb97d74
+oid sha256:cb02ccd1192d7718ae1af09cd677fe41c23cc61772e1b6f0b39f71ad7e6f2935
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
+oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.094940423965454,
-  "best_model_checkpoint": "./outputs/checkpoint-2700",
-  "epoch": 1.9672131147540983,
+  "best_metric": 2.0859835147857666,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 2.040072859744991,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,13 +385,27 @@
       "eval_samples_per_second": 17.728,
       "eval_steps_per_second": 2.218,
       "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 2.0454,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 2.0859835147857666,
+      "eval_runtime": 352.6105,
+      "eval_samples_per_second": 17.793,
+      "eval_steps_per_second": 2.226,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.934011037632512e+16,
+  "total_flos": 8.22130227265536e+16,
   "trial_name": null,
   "trial_params": null
 }