Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3a7ecf8548da4406e9ea55db71c4ba9d763dc65c1b0d8b020322fa1609bf5f
+oid sha256:3fafa06afcfe8cb3f99cebccff70da442a3235613cee8e9d96f47868759eb184
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df4e2e26529b27e7458451c84f7822f9a4040ee3e8b145e1db05264e2e8ea3b
+oid sha256:74f72b21cf44bc2db86b7d92bea717d4306def78cf0bd626a77c89a1d0bdf449
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c100d41f6fd4b797068cc46b1116a533d330b6f880750742ac2da0a93865598
+oid sha256:2badf77de5f001fb7a6ec008eb08fb5ff6e56a3cfa119aeed3b9e33cc1691aac
 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": 1.960465431213379,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.1363636363636362,
+  "best_metric": 1.9468154907226562,
+  "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": 27.563,
       "eval_steps_per_second": 3.455,
       "step": 800
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002,
+      "loss": 2.0742,
+      "step": 900
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 1.9468154907226562,
+      "eval_runtime": 75.283,
+      "eval_samples_per_second": 19.819,
+      "eval_steps_per_second": 2.484,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.436531182862336e+16,
+  "total_flos": 2.739447726317568e+16,
   "trial_name": null,
   "trial_params": null
 }