Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2085afabcc8603cadcaa31b244d07e69fb3454ee29aee7230098b904c129aafc
+oid sha256:456c8071bb121d182d702081fbb4e6910a4c9546a8c06902bb5b5f22166cb4de
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16d851a52d02b98de7f43aacd3a878e51fd8767ec4b4c183d7d35e179bb655d
+oid sha256:0d24a12ccdde3348ad8f6d549d50c65136112300282d9ae5c9c73f4f2ceea4a8
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf766ab7ef9d49860555347a36c059234d6eb124336b64a64b99fa4b6999389
+oid sha256:377ae46bc3cd5d05f1bb24b1b87ddef28bf7ad3d4f889ed296fbea929728c889
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0012787580490112,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.1363636363636362,
+  "best_metric": 0.9947501420974731,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2784090909090908,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 12.002,
       "eval_steps_per_second": 1.504,
       "step": 800
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002,
+      "loss": 1.1154,
+      "step": 900
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.9947501420974731,
+      "eval_runtime": 124.3492,
+      "eval_samples_per_second": 11.998,
+      "eval_steps_per_second": 1.504,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.49771803278336e+16,
+  "total_flos": 5.058277149800448e+16,
   "trial_name": null,
   "trial_params": null
 }