Training in progress, step 9200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c9055a738b9a9de575613a1a5580636f05db397ca77f53fdf338e8870afd3d
+oid sha256:1191e15f1f075f04e1758ba87cec35bdffa2da050944d1bbd85df57885868d03
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147d3fa875f4ec20c612e78f064b3f808bdb35a6690922445f61b72afc32af1d
+oid sha256:1a010ce7c172b0d1642d9d0d0c2e4c836b9098269d1f3df199282ff380452442
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bf8edf039f594951035ab5637656bd85129b21b01c61e9ca4cb4fb949b5b72
+oid sha256:267bfcd733ebdb94275f330516fcaee122db5c84d3b8dd0fa12ab600e130ce3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffeb4e9a55740f59ac2f34810ad1181abbaa2cb8f6beeff3a39a90a1c460800d
+oid sha256:fd1f9483d4afb3a72629e531d61449865b645ed3eea3223a993e49f084490f43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7344,
+  "epoch": 0.736,
   "eval_steps": 500,
-  "global_step": 9180,
+  "global_step": 9200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3220,6 +3220,13 @@
       "learning_rate": 1.77056634524951e-05,
       "loss": 3.5206,
       "step": 9180
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 29.5195369720459,
+      "learning_rate": 1.7657864873688343e-05,
+      "loss": 3.4515,
+      "step": 9200
     }
   ],
   "logging_steps": 20,
@@ -3227,7 +3234,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.1709115811692544e+16,
+  "total_flos": 2.1755437760249856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null