Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbb5ec17dc6c745a0958083e2e6bc5416ecde6983c0851592cc9e25657db424
+oid sha256:331ae41f446d9853796b411bdfafd0b9a732ac28d6b08e7818e1408864ebff89
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef679d441414e6c33e453c66ea5f96401c07f2003d90fe960244ee38eb8d2246
+oid sha256:4ac473e3bd3cdc5172ed91f763a96f13cc8a67d453c9675bbb47dd050f881b55
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980556105c838238e4bff9f061afe997b1bb238013e8dd9a40bbbded893a0389
+oid sha256:0280e7fd33d37b1aeeef3952241543aba36153b8c4239484d3e5400cbb9284c8
 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": 1.730454921722412,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 1.691584587097168,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.0200364298724955,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,13 +189,27 @@
       "eval_samples_per_second": 11.316,
       "eval_steps_per_second": 1.416,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.691584587097168,
+      "eval_runtime": 554.1975,
+      "eval_samples_per_second": 11.321,
+      "eval_steps_per_second": 1.416,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.384096572941271e+17,
+  "total_flos": 3.651229330252923e+17,
   "trial_name": null,
   "trial_params": null
 }