Training in progress, step 4400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafc3f6442e5ba84431ff078caa6e69b3a936652a78ec4e062738afe5c219732
+oid sha256:78b3e09c4e01a30ef881735499660d4412e95b93c75556d23b1ed6810bcf64b8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e921e944e51dba181ad318d41576f8ac3157dc39c4bff064cdc6b4b895ad6d05
+oid sha256:ede9351d0e560e402f48b63d9ef5f99a54f6f3c33467860dc582674848a7dd81
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de92704bc3b6ffc2d27e74d056f93cc6b41e535e9e0201f0fa7c3b78e6075e90
+oid sha256:c980230c9b331cf755c313cb53fe86e70becec911cf990f83cc255f22cc4cb3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae6e4af65e99b8816fc6ca644da9b1cf355b8cdc1d577590a1d02007539bd66
+oid sha256:c019041ef3f15ade90caa60ec00bd9729de47047048dfbd8b528e52704018ac7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003123384856789086,
+  "epoch": 0.003272117469017138,
   "eval_steps": 2000,
-  "global_step": 4200,
+  "global_step": 4400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,6 +154,13 @@
       "learning_rate": 1.9999980825767474e-05,
       "loss": 1.5963,
       "step": 4200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.360860824584961,
+      "learning_rate": 1.999997896164907e-05,
+      "loss": 1.5837,
+      "step": 4400
     }
   ],
   "logging_steps": 200,
@@ -161,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 5.526240672691814e+16,
+  "total_flos": 5.776057087694438e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null