Training in progress, step 3720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2c0dc419e1f7070f9dc393b5340f37fcaf738a53c6ac2d643bb408e102a2cd
+oid sha256:f13d441278584800305f9e26da4273dad6d7875090921b28e26b45c6774d333c
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ab135925a27708e675b58180a1351f6a104d5da582e4191d068831249b7681
+oid sha256:649594190d4a72c9cfb02a6d63322d7c898194d9e59c41bc49d7da475d2a0c87
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12c3712becdb7818ac8dc0ccaaef9e208d98ed01119d15eee2dd3122b064042
+oid sha256:c91443f3ba02f1daf1ad9b67315df20b52be0e5bd1e6256f5526e1158a26ea37
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7234d0c9a81177e50f7ca4cc8a1b00d514de119abb6b5593dfe07e220d3a0326
+oid sha256:ccbe4cbbe78988717a93eeb711aa1df5c2d1ab7d6064c8a0774ed1c855a9c67d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.296,
+  "epoch": 0.2976,
   "eval_steps": 500,
-  "global_step": 3700,
+  "global_step": 3720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1302,6 +1302,13 @@
       "learning_rate": 2.814927828953022e-05,
       "loss": 3.4761,
       "step": 3700
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 29.243453979492188,
+      "learning_rate": 2.812583271253125e-05,
+      "loss": 3.6265,
+      "step": 3720
     }
   ],
   "logging_steps": 20,
@@ -1309,7 +1316,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8740807346749440.0,
+  "total_flos": 8783028556234752.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null