Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec579228de33375bef3c021708802215d4a04652827a6f8c051e98faa86a4a30
+oid sha256:53f013c8a2c8bef97abb794e6a06b77a2e4147632cf2273758eca6f336e2f82f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3882deb1f77706d02be4f5b35744aae6ff1859c7fa25beb0cc12f83b8c1d253b
+oid sha256:2d5bf1a7d0bfb46b3a3dd1d3164d601e5d0acbf095447fb95f3aa1049e4f9c18
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c86d865b5f454c32bd8b51f5d37d59633a8c46276d5fa7f3794da39892d4027
+oid sha256:35e1a4b7f4cf5b6d8da788548ce2d5664e1ef7d1e94833e7402606e114248110
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ced696ae0a3d60fb2ccce1b7a31e63100064311d81188f38315caced36b56c
+oid sha256:6e6ba93e40726a23826255063f80deb5e022a089a3ff72f2cec37c66a0e303e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2304,
+  "epoch": 0.232,
   "eval_steps": 500,
-  "global_step": 2880,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1015,6 +1015,13 @@
       "learning_rate": 2.8989147084546335e-05,
       "loss": 3.501,
       "step": 2880
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 41.04441833496094,
+      "learning_rate": 2.8971541407162637e-05,
+      "loss": 3.5707,
+      "step": 2900
     }
   ],
   "logging_steps": 20,
@@ -1022,7 +1029,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6812114940493824.0,
+  "total_flos": 6859880349204480.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null