Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381ba267a6fb7496a42f9673a08951d36a0764b519407444ad882435b1612fc0
+oid sha256:084fcf06bd9b2e592bc463f1b54c0559939a189266f43cca220e6901c11e4679
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1169c6677314aadae773a944d37d6e260863567974a606b5aa511e2f86838efe
+oid sha256:5763c3425fe64a8eedda8ec8a51a4a3ad64de061fb19f1f5c66810ed3e284cff
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698b952a591b7d2ac2c70d59d97f86b4919406853787a50a73af35231642c0c7
+oid sha256:f3018835e80dd6bd46c30978d9432c2bc483d2fe9412e52895528777da2e15b0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9575291275978088,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.840909090909091,
+  "best_metric": 0.9542251825332642,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.9829545454545454,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 16.609,
       "eval_steps_per_second": 2.082,
       "step": 2000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002,
+      "loss": 1.0721,
+      "step": 2100
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 0.9542251825332642,
+      "eval_runtime": 89.9742,
+      "eval_samples_per_second": 16.583,
+      "eval_steps_per_second": 2.078,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1118912902350848e+17,
+  "total_flos": 1.1673223042295808e+17,
   "trial_name": null,
   "trial_params": null
 }