Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f142acaede1be2422aede5788f05bee242598d8861a6bb82f7d3b6f612a4e22
+oid sha256:de645c28b69a642ff1176deb2a3a8b9775702ec1b0f2c6b42dddc77244dffbdf
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020d7152f7ba96de02be62f9c8c4e036a12fd0b1c60077143c25b33cd2ab527a
+oid sha256:2fb7df52928f5c1e2469aee7d66626263914ba90a069b55041698ceae7938181
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3261a0429b7b1953b82adcaaa9f9e26f9a23ece6dcda65cdd3932732766f2d1
+oid sha256:bd508c77427815f687ed47941e9cf24e319c9494028636e8747f46c4b44b3e81
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9583721160888672,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2784090909090908,
+  "best_metric": 1.9483006000518799,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.4204545454545454,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 27.759,
       "eval_steps_per_second": 3.479,
       "step": 900
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002,
+      "loss": 2.0848,
+      "step": 1000
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.9483006000518799,
+      "eval_runtime": 53.6139,
+      "eval_samples_per_second": 27.829,
+      "eval_steps_per_second": 3.488,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.726008577316864e+16,
+  "total_flos": 3.029034838136832e+16,
   "trial_name": null,
   "trial_params": null
 }