Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df16ce8b561b352d3312652c40d477fbb877cd56ea970096f2dbaffa07fb552
+oid sha256:a7b375ea6f5e70ef64e4641abb6a08df506c86a9a7bb439340b989e59fe64c0c
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6d76fc568477d34da53d466b9db1022be4baaf30111fac5d0d9a5be4fdbc49
+oid sha256:033fa7ccae359fb38b200fbf2e73770b5a80ea7b2b9e5686853f4c0453109b9b
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66230a2c3a0a8fe730262d29372e7febdc116b90ed069ff519fa96f8d1b53e9a
+oid sha256:f17d400e8d0a3279d48c33167ab70e99da7e17a6d2f06962e7ee39cc165c3506
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3939cbd2421a0d3e4ed3c12b3cceaa472fcdb8fe6c9b60b2d2c772cdc28de91f
+oid sha256:2f0d32846dc851291d36978371f88c4a2e97295576d6f59868838a673ab4bcbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0624,
+  "epoch": 0.064,
   "eval_steps": 500,
-  "global_step": 780,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -280,6 +280,13 @@
       "learning_rate": 2.999362805807425e-05,
       "loss": 3.7586,
       "step": 780
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 30.289432525634766,
+      "learning_rate": 2.9992133535682725e-05,
+      "loss": 3.6919,
+      "step": 800
     }
   ],
   "logging_steps": 20,
@@ -287,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1847858637668352.0,
+  "total_flos": 1896312970543104.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null