Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81be4ab01e57bd8cb8f2a522bc64a253063c7d85ddfc87fed2efd0af5a0cc172
+oid sha256:2ab26f716dce81fcd46fbbb401e72f7fec4840a719574fdadeddcac2e0cd2ddf
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eddbf928186d9fb3d2143cbea680e738cbcfd171f6d970417efd58450c4cd3bc
+oid sha256:27fa6168a65573fa6f31f03cf5fab3acafcf74cd1a12a66f07ac1c66ec686cdc
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0c0ade96e49f1197c7e40ecd2fd9e91be217c89901880a014eccf43aa01f57
+oid sha256:48d9d5fa72253e3d11b2a7ce24a2ae523c1872f22a41c74e73e62af9955db1fe
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.989990234375,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 0.9865836501121521,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 5.445,
       "eval_steps_per_second": 0.683,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 0.846,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.9865836501121521,
+      "eval_runtime": 358.9224,
+      "eval_samples_per_second": 5.377,
+      "eval_steps_per_second": 0.674,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.6755826480358195e+17,
+  "total_flos": 3.958031986924831e+17,
   "trial_name": null,
   "trial_params": null
 }