Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb82b895769fac39bea732a9ba8c73d4af251575adb615b85e47f266dc077c5
+oid sha256:c9fcbf722fc3301ad671cbc7170346cf95a1ec7f9724fa560e1892d9da28c259
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ebaf6a2405689aa6334737965cba8b758affd0d4896538d79aa170dfab2538
+oid sha256:32acbb6fc91737018afd524414967a0c038312563109e13d6e5489ec6a0eac38
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64edf4072e9d9de433323939eb8f5c3fbe20486acfda2f65802e2e8a8a3efd1e
+oid sha256:0d2dd23330c7a6a241dea866f3a8d0da33f690b71da00f528527985b73751b8d
 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": 1.1482728719711304,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.143031358718872,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "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": 10.878,
       "eval_steps_per_second": 1.364,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.9396,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.143031358718872,
+      "eval_runtime": 177.3006,
+      "eval_samples_per_second": 10.885,
+      "eval_steps_per_second": 1.365,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.976702787313664e+16,
+  "total_flos": 6.726095314477056e+16,
   "trial_name": null,
   "trial_params": null
 }