Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24e2b534df5e67fc41eb61be724e22bc2d020741a5f1846d0f04e3698db84bb
+oid sha256:9dab9bda75617893936d1029f5198f90eb16acd337ae685b3ae1785d29eb3377
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311b5d2cdc93d0d12edc23b4d6c9f74886fa3b35bd1df3cd5d5e028a51bcd414
+oid sha256:609895c2334e5b0ede08844fc13fb79f5340a2efde198c292f0c91f33afee687
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a1cedd2475fc3bdc96246df17906b4d2a501b2eda44ead842ae9652eddac61
+oid sha256:447f4e5e01c0be926e916558e05968f8dccd3ae815e436a13fca4d71927a76d5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3105216026306152,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 1.307134985923767,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 12.717,
       "eval_steps_per_second": 1.595,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 1.0539,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.307134985923767,
+      "eval_runtime": 151.6647,
+      "eval_samples_per_second": 12.725,
+      "eval_steps_per_second": 1.596,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.561751250300928e+16,
+  "total_flos": 1.0197592855252992e+17,
   "trial_name": null,
   "trial_params": null
 }