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:c872e5083d4b5508500a3ebb619633583e1791cbd57a7599edc1fd5b44625d06
+oid sha256:a0e59dff9775d0c98ba9d6624c5427cb0e2272b6f3226907c2f0dc95800d008f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f209691fb7e29d678970f15fdc8deb69657bb928c047f5c8782645b35280e1
+oid sha256:83056bfb54bd306db6f4f3662b00b5d3faa94a811c20d2fdb626fa40639fd7f7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf8a592a4e3de99a8e7bfdb0e13d9b050b0ac937f15ce1cbdb3906cf7ba692e
+oid sha256:33d0b48a8cae2e325fd3674077c1140034bb2089e3367f6296e12753d18b64ac
 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": 1.3770211935043335,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.3670101165771484,
+  "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": 30.771,
       "eval_steps_per_second": 3.86,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.4685,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.3670101165771484,
+      "eval_runtime": 47.4079,
+      "eval_samples_per_second": 30.607,
+      "eval_steps_per_second": 3.839,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.682370133065728e+16,
+  "total_flos": 3.017745003184128e+16,
   "trial_name": null,
   "trial_params": null
 }