Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a8588f303560416dc6ac7978e949a2e994a770d8713b2c2430ebd48bc92b9d
+oid sha256:b3c640cec8e45c2c2a3a67c2ad8fbe397b4323a2d9d24327def8e3830cb6c35e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d32c720a9aafb7e90df761c566cc6272013213fb381ca06833dd34cbb79a35
+oid sha256:a6921e0460bab0880b2cd1e37cc02fdf15ce6a7d0101180ac51463d6f169ed46
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33aa1ec500d684fb1fdc58c5b0a24d5d7f978ce714c4fb6b371ee377a90400a8
+oid sha256:a37b20fb123df82ce7439a8a4fe878c98f20fd90e4b8f892214d734f93311746
 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": 0.9716654419898987,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.8465909090909092,
+  "best_metric": 0.9676819443702698,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.9886363636363638,
   "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": 12.474,
       "eval_steps_per_second": 1.563,
       "step": 1300
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0002,
+      "loss": 1.1021,
+      "step": 1400
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 0.9676819443702698,
+      "eval_runtime": 119.9473,
+      "eval_samples_per_second": 12.439,
+      "eval_steps_per_second": 1.559,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.307569918236672e+16,
+  "total_flos": 7.869951653566464e+16,
   "trial_name": null,
   "trial_params": null
 }