Training in progress, step 3700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef5ea8b79738fa0b1afc11d4b2107af60cdd8cb8f1d9e425e3dbf9f968e4c88
+oid sha256:7e2c0dc419e1f7070f9dc393b5340f37fcaf738a53c6ac2d643bb408e102a2cd
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde1575d56a414a2045e8dbdaca0d2f623d7e43dfc4fc696b88d5f3e863f7170
+oid sha256:e5ab135925a27708e675b58180a1351f6a104d5da582e4191d068831249b7681
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ad82d08ebc1302cfaf16005dda10850453ff7fda97e1c6c54c3d6aaca32ef8
+oid sha256:a12c3712becdb7818ac8dc0ccaaef9e208d98ed01119d15eee2dd3122b064042
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07985d480aea598ad66efeed57f22e38607f1040692f61ddafbb1ee20e27674
+oid sha256:7234d0c9a81177e50f7ca4cc8a1b00d514de119abb6b5593dfe07e220d3a0326
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2944,
+  "epoch": 0.296,
   "eval_steps": 500,
-  "global_step": 3680,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1295,6 +1295,13 @@
       "learning_rate": 2.8172585936822056e-05,
       "loss": 3.5127,
       "step": 3680
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 30.359540939331055,
+      "learning_rate": 2.814927828953022e-05,
+      "loss": 3.4761,
+      "step": 3700
     }
   ],
   "logging_steps": 20,
@@ -1302,7 +1309,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8695239934181376.0,
+  "total_flos": 8740807346749440.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null