Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe686a29014652850a0b3c527fbca499406bd1d5299925be3de3c5bd653523b
+oid sha256:d1082455398449d12ac8bbbfa6d63e461bfdbe800fbfb9316824abc14bad2c7a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e454caabc6b9a8add8ae75f29a8fb620ebcd90904c1d1ba7bf71f4e471856877
+oid sha256:90a5b6114bb835045b6ff37c42c41b54034ec598465948be93bd14aa9dd98e52
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7e70944ee032b710f184512939412d316802644141141a5b9b23e848841cc1
+oid sha256:8aa4be861121341cc53f3c40e98a1feeecc92876a32bb3dc6eb154e58726a8e8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.407381296157837,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.3997007608413696,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 15.294,
       "eval_steps_per_second": 1.918,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 1.1693,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.3997007608413696,
+      "eval_runtime": 93.3773,
+      "eval_samples_per_second": 15.539,
+      "eval_steps_per_second": 1.949,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.595995991076864e+16,
+  "total_flos": 8.182893825921024e+16,
   "trial_name": null,
   "trial_params": null
 }