Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365cb56c31e75ba2d93b92e523ff2b41ef30cbe8b35a4281a0ba0dae02713a48
+oid sha256:afd9a17ecfc6dd571be8b178ef014ecacf7c03eb9fa56076ec69f6dc444bfbc6
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88ee7bf1a4f8afad068b633acbb1f55ab26c488991d0a4f91e60a3682dbd7c1
+oid sha256:d036a4b7d97aa453a173b443096d706f0f1ddd42fa5ae36d779b59baa4ed2ae3
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176b5f7c8c5709a1b112b6a38d5b74f578a857aeda04052f8a5e247ab8150858
+oid sha256:d79a0ac751cbc94760fe76ed12d4dbacb7ab37b5aad6ba68e1b9f106650a089c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7660272717475891,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 1.6,
+  "best_metric": 0.7408167123794556,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 8.408,
       "eval_steps_per_second": 1.054,
       "step": 300
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 0.8076,
+      "step": 400
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 0.7408167123794556,
+      "eval_runtime": 229.5926,
+      "eval_samples_per_second": 8.406,
+      "eval_steps_per_second": 1.054,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.10987888611328e+17,
+  "total_flos": 2.81295203475456e+17,
   "trial_name": null,
   "trial_params": null
 }