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:a5227e6151cea8b3a502805637c2eec55a5caaa66dfa55b60c22d921e6dccd5c
+oid sha256:b391bc01a8f50f402acf38dc3d1c24d82f8ac4e7f7d5de0430395172495c03b5
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312d388fdc45c70d5e646e092ec8e5e08d7c85aa2748d7b7d7fc97593de4089b
+oid sha256:de7dfca0fffc279fc8715a354cf9c9eff3b5a9b176cf7d45ef9ec72410919dbe
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc812a9a0585c12499e2e04e0fa9dc706fcccd59e7fbc41a4c4c31a095960052
+oid sha256:ebfecc11b02dbecb55cc6360d830479dd2fd45c002146a3a12209eac07ec47a1
 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": 1.3270059823989868,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.3173606395721436,
+  "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": 12.897,
       "eval_steps_per_second": 1.618,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.0921,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.3173606395721436,
+      "eval_runtime": 112.4585,
+      "eval_samples_per_second": 12.903,
+      "eval_steps_per_second": 1.618,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.628242252087296e+16,
+  "total_flos": 8.264308204486656e+16,
   "trial_name": null,
   "trial_params": null
 }