Training in progress, step 3600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88adee23a7e35b2cf4aebcd8c81faec7b932abea1a3d19cf7a8d36adbdbc169d
+oid sha256:1f67821ac1225d4d6ddda4314d6a5229d5d7e025037b4629626781330dcd8ba7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c08ba3cc41f312df74a4897f9862543590396f79d1f28fccf1aaa0e2d0a62e
+oid sha256:36c6cf5fc78cecc2d7df7b5890bb7f1585faa029834b2a8424b07945ae424657
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8533a46f2820d296dd8dd66497b3038b4c8cd3388b495350dff5037c2a4c3482
+oid sha256:9291966c403e7bde3e2744cb48c547f09f71e192a421d27ace1f464288c63654
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715607d045c48cb60eaa3afa895318c1f98eb549c11762cb3cadd29ed207b42b
+oid sha256:d5ef771961ae1ef92dd7080688347888d76bf3cdf936856cea7f523a48bc1bee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0025284544078768793,
+  "epoch": 0.002677187020104931,
   "eval_steps": 2000,
-  "global_step": 3400,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -126,6 +126,13 @@
       "learning_rate": 1.9999987447266877e-05,
       "loss": 1.5533,
       "step": 3400
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.193918466567993,
+      "learning_rate": 1.9999985922889644e-05,
+      "loss": 1.5725,
+      "step": 3600
     }
   ],
   "logging_steps": 200,
@@ -133,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.438400445092659e+16,
+  "total_flos": 4.69863606565847e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null