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:ebcd56ecae3f56ec1b8e94d2dc7a00a4a049334e064007f096b9cc278ba21282
+oid sha256:fc05e6daf972781e703e2140ecb3c06c9c71a04b9abb65c66809f77fb37994f4
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1896c1cc252d8463f6b7fc743213578c3b18cfe469801ebf2a8ffc2f0241aa98
+oid sha256:9d06c4fe74c0d6bf8a7bf9b61ec521dc6a5cf47a5c76624ca2d89c236fa016a9
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ee4bdd7de760b82e132b6c2a923dfa3044fc52b2a20c9ec24faeaadc49fdef
+oid sha256:710431a140f057124dd396b0a76e6e61ac87cb5cf7412610c68c1f75a8f9cf46
 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": 1.8917897939682007,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 1.8584532737731934,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 11.344,
       "eval_steps_per_second": 1.419,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 1.8626,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 1.8584532737731934,
+      "eval_runtime": 554.4522,
+      "eval_samples_per_second": 11.316,
+      "eval_steps_per_second": 1.416,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0826998776253645e+17,
+  "total_flos": 2.3429063350124544e+17,
   "trial_name": null,
   "trial_params": null
 }