Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1011ccee280f4d387b7dd49c756a3b568ea07513b6f0af636d7377d45f5a1c64
+oid sha256:96c2643c948e8c26b7915122497df4ae83b2431b99ef269d2d4d0a8ef6631cdf
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c047531f5a9dc02e0b0a4ba57131ef7a75564a628a8ae0f4f2c224ba61b708
+oid sha256:7ea28045dbb6354fdb95725f985f2e38a5208180a9cae044b1a856afbe37f579
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49486dec9d2a122c787933aef8bb6360b19f8df93705d5491661116da481a185
+oid sha256:5ca9c04f6b7646a0509be2acc7ecfafb1dcb2d23d1ea2918a0e476af152e1e5d
 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": 1.319887638092041,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.3168717622756958,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "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": 30.86,
       "eval_steps_per_second": 3.871,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 1.3969,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.3168717622756958,
+      "eval_runtime": 47.2245,
+      "eval_samples_per_second": 30.726,
+      "eval_steps_per_second": 3.854,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.364740266131456e+16,
+  "total_flos": 5.700115136249856e+16,
   "trial_name": null,
   "trial_params": null
 }