Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbd50b96568d4df4efd40372e81667dc70d2afa4a1c11fff8a9f3a9a8ea54eb
+oid sha256:f2a5c29abd879857e94133216062f2304e9e5f3d67f8387577bfafc61dea2ae7
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60af44d701bafdb02cc7ffe946c25640cd2d2a96cac8ed77c7755ce77362d423
+oid sha256:5ee8cd479cfc025554e76f9ffe951b91d46c5257670871fb8d956f9c01127244
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d26adabab8044b9f565c81e512feb8a78443fda90b855252c9b6238b058d3ef7
+oid sha256:748f1340fd9b0d57811f59fe041f609e22a6ddf5e0bc7260681bf17e3d449b1b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.05438232421875,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 2.0523083209991455,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477231329690346,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 30.471,
       "eval_steps_per_second": 3.812,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 2.0032,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 2.0523083209991455,
+      "eval_runtime": 205.5591,
+      "eval_samples_per_second": 30.522,
+      "eval_steps_per_second": 3.819,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.629167658213376e+16,
+  "total_flos": 9.919903936610304e+16,
   "trial_name": null,
   "trial_params": null
 }