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:dc4de6f6d17658dd72f2461617aecfd024007cd1b93ea77683602c9f67a1563e
+oid sha256:fe276cff7439de5a3012a1a30604f44e7dc4c647d5bd217d1af62be59c77ca04
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d21ffa3e97cd7669bdaf259176923ad31db8ae2b57062353c134282870d316
+oid sha256:de5c2ad305932d3b5fd1b50fdbf1648d9021b597267456419ba7af2ce36c582a
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d88b02080a0ea2c4b84decc15320ceeac831f11b262b68b63536132f618e5a
+oid sha256:bbe97754e91c297ae31c4ec01cc8074d82add99e6b7d330de4b929c9322ec461
 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": 1.2557995319366455,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.250588297843933,
+  "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": 15.255,
       "eval_steps_per_second": 1.913,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 1.0845,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.250588297843933,
+      "eval_runtime": 125.971,
+      "eval_samples_per_second": 15.321,
+      "eval_steps_per_second": 1.921,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.608775905574502e+16,
+  "total_flos": 4.963918665952051e+16,
   "trial_name": null,
   "trial_params": null
 }