Training in progress, step 7340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9207586f7a1d2ba4556ac81bf96016c6a6bdc9668c406e8e8639d19d9692cdd0
+oid sha256:00ce3f623d20bb63874635e9ab5549586003cb7bbe97de574a4d3b26fcade91b
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed2a524baac54ff9e8afed21d2b42af94fa038aef5ded6b599c9e972dd0477d
+oid sha256:fbff368016dd31d4c5854dfe282709681d4bc7645f54c79d0965534024463b19
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e665c9777fc69706bdf0b3707a06c85d4cb2b43fbb10521c503874813f13d69
+oid sha256:89e0026633dcf0577197d5da032bd4f6f6125e7e640e504383869bec01d526ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2282342021370a0027cf32dfaa491c0a05194df75cc08c2cc5453789cc6933
+oid sha256:325806e4aae5b821ce1ac956faabdb099b3ea0e4420f8dfcf52b72adab91eb65
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5856,
+  "epoch": 0.5872,
   "eval_steps": 500,
-  "global_step": 7320,
+  "global_step": 7340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2569,6 +2569,13 @@
       "learning_rate": 2.196091871970103e-05,
       "loss": 3.5508,
       "step": 7320
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 25.02892303466797,
+      "learning_rate": 2.1917848793399926e-05,
+      "loss": 3.395,
+      "step": 7340
     }
   ],
   "logging_steps": 20,
@@ -2576,7 +2583,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.7308825951961088e+16,
+  "total_flos": 1.7355049482780672e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null