Training in progress, step 3700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385b9b5f02bffd7fc21b5b6099caf720ae559e7d2c40f610dadf97aa98914ee6
+oid sha256:5f06162344b40957e521890c301c56c53e411f04474a1aca28dc6dd39453b506
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38e59bc166d16c5098bd04f0c12f6dd5bc1d2edb5232c6c8d36feee70c1003a
+oid sha256:6df414f5c7b97a56c9cb37d3bc904f290836e534eb0dff8b7f067ba424f6c92b
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7212374cd916676c44e1c9a2f0614a7d23ee62995154c5af0a7ae8272789312
+oid sha256:e2e0246f703b8ebd52285fe73ff6bd35088e8b0139d5d47de98b5c490afb9d42
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
+oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8900671601295471,
-  "best_model_checkpoint": "./outputs/checkpoint-3600",
-  "epoch": 4.8,
+  "best_metric": 0.8880813121795654,
+  "best_model_checkpoint": "./outputs/checkpoint-3700",
+  "epoch": 4.933333333333334,
   "eval_steps": 100,
-  "global_step": 3600,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -511,6 +511,20 @@
       "eval_samples_per_second": 2.484,
       "eval_steps_per_second": 0.312,
       "step": 3600
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.0002,
+      "loss": 0.6917,
+      "step": 3700
+    },
+    {
+      "epoch": 4.93,
+      "eval_loss": 0.8880813121795654,
+      "eval_runtime": 792.6123,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.305,
+      "step": 3700
     }
   ],
   "logging_steps": 100,
@@ -518,7 +532,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 9.323259516653568e+17,
+  "total_flos": 9.582968034571469e+17,
   "trial_name": null,
   "trial_params": null
 }