Training in progress, step 6000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea91fb1ecf648cc0d9b1c34c231eeb11e493def8af1b24626b09ec699dcc574
+oid sha256:df13651e277a0c57568ab8ad1700485f28f93fce313b51d305bf49236a22d848
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0cba11636076b32b316427e9e0cc1651d3ec55ea03d8d1f601d48d89153db6
+oid sha256:3f6d8560b09a8acbd520a643f2c903a1b4abe534eed07f393b76e7e3b4383130
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98af83b6a2d5ccf06ac67101b7d27db5e186113101b0ca8f3d71a5ca34f809f8
+oid sha256:387d439f709c593f39d19f3e24beeef5450e32e99e883dfbed8c69aedc09f310
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b9669fdeac6f8ea3f9f111ac5b46d4674ad051ccbc5e8083a6ee1a8eb3361c0
+oid sha256:db17511cf40c553b235e796d2decd760897da6988ddf690cb68bdac8e17c1364
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0043132457546134996,
+  "epoch": 0.004461978366841551,
   "eval_steps": 2000,
-  "global_step": 5800,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -210,6 +210,13 @@
       "learning_rate": 1.9999963416130326e-05,
       "loss": 1.6067,
       "step": 5800
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.953801393508911,
+      "learning_rate": 1.999996084464646e-05,
+      "loss": 1.6252,
+      "step": 6000
     }
   ],
   "logging_steps": 200,
@@ -217,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 7.611114196832256e+16,
+  "total_flos": 7.88654619022295e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null