Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b391bc01a8f50f402acf38dc3d1c24d82f8ac4e7f7d5de0430395172495c03b5
+oid sha256:4374d344de0ba51b7d2da3fa14ad1ef770c2570cfe6e34a52ffdf5406cb05aec
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7dfca0fffc279fc8715a354cf9c9eff3b5a9b176cf7d45ef9ec72410919dbe
+oid sha256:8490cb2546fb02532974d34abd0a68c1d70d1cc5d3cd76fdc4149e7ffc1369c1
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfecc11b02dbecb55cc6360d830479dd2fd45c002146a3a12209eac07ec47a1
+oid sha256:1bf486cfe029ef0ab8a98b96c403d9e9430e33b47c3ce9bc8a9e6c2e5289a2e4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3173606395721436,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.3096227645874023,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 12.903,
       "eval_steps_per_second": 1.618,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 1.0799,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.3096227645874023,
+      "eval_runtime": 112.3567,
+      "eval_samples_per_second": 12.914,
+      "eval_steps_per_second": 1.62,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.264308204486656e+16,
+  "total_flos": 8.902643832520704e+16,
   "trial_name": null,
   "trial_params": null
 }