Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59eaacff7d5070762d45bdd45efbb6b228c686c1e112dbafc0c104f49216ec3e
+oid sha256:8136d419b8890434688f361ff9055f226cad86b60136d37a16ab511ecdb95732
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e2fd24d0533b528ed874a6637c5f5d7e738f41677f210a597f6771befa3753
+oid sha256:8ae7ca943292c1885fd2fa8fc4a0d7048e58e847fa6978c2dee6a1669f1d7daf
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c5c75ca0c47c9e8bfa47c24c3071bf0748801b48fbacbc60bea500a545e48d
+oid sha256:450d4161861142b0c607b082cb7975db64bce31f3c9c4ed471faa6a87cc3c651
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e8eaec8b57dfb6cb3597040aca1e3875096e994226b7c8aa538ca79c87ebaa
+oid sha256:cf6116349e1acbc51c06feeb07eabf38596d13779c8b6455b06cf034d85b895b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0034208500812451894,
+  "epoch": 0.003569582693473241,
   "eval_steps": 2000,
-  "global_step": 4600,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -168,6 +168,13 @@
       "learning_rate": 1.9999977001049872e-05,
       "loss": 1.5586,
       "step": 4600
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.3270204067230225,
+      "learning_rate": 1.9999974953119e-05,
+      "loss": 1.597,
+      "step": 4800
     }
   ],
   "logging_steps": 200,
@@ -175,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 6.036713823478579e+16,
+  "total_flos": 6.297651302741606e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null