Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92be3b4d71a6b157bb854f2d9d492578975172c42dd2f84d60f25a51aa4d3d2b
+oid sha256:55a7459821c827275f51100532709eb460edac80de190c63d06b8492233aad25
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4ada95a49520b94bc4a8f5822f3ea1d4fe1de59cd69fedde387aaed81167c0
+oid sha256:e1de446c56a2d213fcbb7ded6a2f85dc54d7adb883c23a85d1d1a2247d82244c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f988a87c292524c83b21ea4c41795c72510e2df27e6988755709c4cf8287a8ef
+oid sha256:7361b3863934982b557e96c725dc20b5e201445559e466db7d62a9238b31024b
 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": 1.4467251300811768,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.4370195865631104,
+  "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": 15.55,
       "eval_steps_per_second": 1.95,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.1922,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.4370195865631104,
+      "eval_runtime": 93.2407,
+      "eval_samples_per_second": 15.562,
+      "eval_steps_per_second": 1.952,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.677188212150272e+16,
+  "total_flos": 5.26073066072064e+16,
   "trial_name": null,
   "trial_params": null
 }