Training in progress, step 665, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ba22a6096b92b023229a978614f3a869f7cc3c516f563f57ce918a647f7222
+oid sha256:e343f4be4726d57248da858151d45c31e805e6b3ad9a7fa71b73b1ea4e9be755
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb1a3074c76236d44bced08558878eec1c346155d7c47db509852f94cf1aff3
+oid sha256:2c60fe7edf4324671acf40ae4d255f5fe04b5b2c203c38809ec1ad9b677ed7e1
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee245fe116539a0adb49d3e912e1f5e7580ebd77115e6394ab8ad18b2aad500
+oid sha256:327f54effce4451308283c7d25159d8624b283452013dadc78bd8e3f4eaf23f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4689dbc82c008a5e99716272c6c0bb1ecf3bb87b8bd8d946409720c292a988e6
+oid sha256:765a8680709d1ce853e9b5ed23f0d0a5b9c07dc800a1d0d7e4ffdc056361e829
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8540925266903915,
+  "epoch": 0.8605629246198642,
   "eval_steps": 386,
-  "global_step": 660,
+  "global_step": 665,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4643,6 +4643,41 @@
       "learning_rate": 9.380738687473272e-05,
       "loss": 0.9527,
       "step": 660
+    },
+    {
+      "epoch": 0.855386606276286,
+      "grad_norm": 0.7638357877731323,
+      "learning_rate": 9.378749820849642e-05,
+      "loss": 1.0131,
+      "step": 661
+    },
+    {
+      "epoch": 0.8566806858621805,
+      "grad_norm": 0.7495226263999939,
+      "learning_rate": 9.376757977081594e-05,
+      "loss": 0.8511,
+      "step": 662
+    },
+    {
+      "epoch": 0.857974765448075,
+      "grad_norm": 0.8003675937652588,
+      "learning_rate": 9.374763157523399e-05,
+      "loss": 0.9291,
+      "step": 663
+    },
+    {
+      "epoch": 0.8592688450339696,
+      "grad_norm": 0.7893322706222534,
+      "learning_rate": 9.372765363531351e-05,
+      "loss": 0.8206,
+      "step": 664
+    },
+    {
+      "epoch": 0.8605629246198642,
+      "grad_norm": 0.7351086735725403,
+      "learning_rate": 9.370764596463763e-05,
+      "loss": 0.7185,
+      "step": 665
     }
   ],
   "logging_steps": 1,
@@ -4662,7 +4697,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.378385333177549e+17,
+  "total_flos": 7.434282191762227e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null