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:ab0b40fda3650c97f3be0ac3839e36438b5dfac0c2575d73e215055b08a142e2
+oid sha256:678cd4a3014a877ff21395e05934b6f49dd0ebc505320dcc0274f31abf64d4a3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb2b73965992471a64e10f2abe37521959dd84f7ffdc425fed02e7e2321e9a5
+oid sha256:ae1974dbd096f996b5e33bd907a834ba0dba458174726f51c52ab6a59249a4f0
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81dcba0e4b479b247d04028b523e2476c45b2a75dfdecaf64971d23daaffc32d
+oid sha256:72c1a7b4a57fedf2afe8ff834be9a632020edb94be4f264ec2e8e70252aa7978
 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": 1.116977572441101,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.1136090755462646,
+  "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": 10.853,
       "eval_steps_per_second": 1.361,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 0.9175,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.1136090755462646,
+      "eval_runtime": 177.225,
+      "eval_samples_per_second": 10.89,
+      "eval_steps_per_second": 1.365,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.716923536703488e+16,
+  "total_flos": 1.0464609713209344e+17,
   "trial_name": null,
   "trial_params": null
 }