Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1b16b748c6a7b5ea4f6ee7c5b4dc21ac3ece52e22b8375bcdbfadcda3560a1
+oid sha256:ed24e154de5566609e7cab9ff283141640a81cad49bf66869e6612084d097189
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765f8c0511f7ed625cfa1cf33f354a07a3e70c69b3f8fc19ed1233dfcf311c3d
+oid sha256:de879bb2e19f835b3e839a36fd87550256c10817dfb87d979207d61c87c69463
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27825f80e934c9a8d3c9b5a430cbea7a1b4ba4344dc4a816cbff7a8b52fb3a7
+oid sha256:38d31a0dc339240aaf93f937650507de96ef2bf626940e68c39c22a3f81eb87d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9602729082107544,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.2727272727272725,
+  "best_metric": 0.9569491744041443,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.4147727272727275,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 12.409,
       "eval_steps_per_second": 1.555,
       "step": 1600
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0002,
+      "loss": 1.062,
+      "step": 1700
+    },
+    {
+      "epoch": 2.41,
+      "eval_loss": 0.9569491744041443,
+      "eval_runtime": 120.1655,
+      "eval_samples_per_second": 12.416,
+      "eval_steps_per_second": 1.556,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.000052792141824e+16,
+  "total_flos": 9.559346065532928e+16,
   "trial_name": null,
   "trial_params": null
 }