Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9b3c95015f06a6e50684c7d86ce654c9f75d6be3f626304d6acc791e9e1605
+oid sha256:4adb1c8f8b56ee50aa97d7ba230528c914fd94683df1aa17d6a63c84541eb731
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afedaeba718b4b505d11f00a82c4ab09323624763daecc251394962a67f1ca73
+oid sha256:2d1033a2be5be69441043806828dffbba91710d79f647e17e6e37e8cc2e8b186
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a53c8f742c7e589aef35625eb91430169408462122ef08e6057a865fba54c3
+oid sha256:17812da58821a9378ebc24a70d2a909be55cf6346ab49b39cc73bc804822d6bd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9950811266899109,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 0.9874381422996521,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 2.66,
       "eval_steps_per_second": 0.334,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.8091,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 0.9874381422996521,
+      "eval_runtime": 724.5381,
+      "eval_samples_per_second": 2.664,
+      "eval_steps_per_second": 0.334,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3315525439270912e+17,
+  "total_flos": 2.5910459214483456e+17,
   "trial_name": null,
   "trial_params": null
 }