Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6372e923148b87547b0b2a912f49f561a174b99227e3e8948ae01f521dff3a8c
+oid sha256:466a8551b073981a6f0ec7a00be1eac50b5c9793ce873fb6581fa2e67a331c77
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78475f77d2d0952a94f63d9bbb6217d08c9cad180f250f8d2571d739a97a3018
+oid sha256:deb4a3e3269a052aadc9a1f1de60d2dc30533769f693b4b002b99a7c4c67a18c
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5af4843563639e31994cfd1ddd0f7cdf98dd7ca1ff3693b235dde4ed21ecd00
+oid sha256:0ed35cbf543f36a580a139da6bcc1e610cc110a46122a95130e54e6b31626588
 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": 1.2201733589172363,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.2122855186462402,
+  "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": 4.224,
       "eval_steps_per_second": 0.53,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.9925,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.2122855186462402,
+      "eval_runtime": 457.7214,
+      "eval_samples_per_second": 4.217,
+      "eval_steps_per_second": 0.529,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.993638976897024e+16,
+  "total_flos": 4.32763510039511e+16,
   "trial_name": null,
   "trial_params": null
 }