Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e7df6d4b8eea8d6ac6af17fdf98a1aa24af43cbc3e5c23fe54fa02a8999249
+oid sha256:c24e2b534df5e67fc41eb61be724e22bc2d020741a5f1846d0f04e3698db84bb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3c7a238b76f43dac71a8b57c12a69ee00df08f60ecff5d670e8d46604a7bd7
+oid sha256:311b5d2cdc93d0d12edc23b4d6c9f74886fa3b35bd1df3cd5d5e028a51bcd414
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1103a5a7efdfc12a1c696b0039f2dfaa719e8a4581e0c7de1b549e6ecbc6d49
+oid sha256:31a1cedd2475fc3bdc96246df17906b4d2a501b2eda44ead842ae9652eddac61
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.316821575164795,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 1.3105216026306152,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 12.716,
       "eval_steps_per_second": 1.594,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.0664,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3105216026306152,
+      "eval_runtime": 151.7617,
+      "eval_samples_per_second": 12.717,
+      "eval_steps_per_second": 1.595,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.928806920685568e+16,
+  "total_flos": 9.561751250300928e+16,
   "trial_name": null,
   "trial_params": null
 }