Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7081a0138a5a6607d5d779a29fb6a362bf282f4a1f6dba345f9cbdae40743331
+oid sha256:771b15c515fd4922f4c738739267ec977c065e97feb13ca07dd2c16c5a6df1a4
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21820119f05928026f693bc389cb44eda04bf237424f6955cacebb062da0ff2
+oid sha256:4541c665033f7c8539d62d4bce4646ae9f5cb11eb7e2305aa0e941951b30de0c
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6764dc3e1fe015624f31dc2613389c8754599510448c4c64c983ace14a8916
+oid sha256:d1f72808257b7991b65ff818e20797b3f6b14292cda5605f27fdf86fe5e6da4c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9784607887268066,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 0.9710213541984558,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 2.472,
       "eval_steps_per_second": 0.31,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.7983,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 0.9710213541984558,
+      "eval_runtime": 787.7479,
+      "eval_samples_per_second": 2.45,
+      "eval_steps_per_second": 0.307,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 3.108344477177856e+17,
+  "total_flos": 3.3683016270053376e+17,
   "trial_name": null,
   "trial_params": null
 }