Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536a2d32fdb1cf190d2ab6a46cb586b2176b891f01f0d3e3d3f63ca983467fa8
+oid sha256:8e827f78889e02cb290d740ca48cf0ffc7d3009e222c44bf4227c31bf24586ed
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285fc0090986e3eee754a341aba064551b1eaca98bb57ff5651ae11b3d57255a
+oid sha256:da2dde23211f20127cc76c7d29250ba5a15939b0fdfda8347c7d090c38cdeab5
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07800c1453f3f8d96a204751f34b7af7bad25585c6b9ac42ed58a2462a5ab9b2
+oid sha256:e546ced227cdbcd028e39a6dd82c210da282c04c2410248a7e7ebf4303af3e90
 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": 0.9371617436408997,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 0.9326320290565491,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "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": 2.456,
       "eval_steps_per_second": 0.308,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 0.7635,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 0.9326320290565491,
+      "eval_runtime": 789.0027,
+      "eval_samples_per_second": 2.446,
+      "eval_steps_per_second": 0.307,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 5.1788857400991744e+17,
+  "total_flos": 5.4385953933225984e+17,
   "trial_name": null,
   "trial_params": null
 }