Training in progress, step 560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8e941e5c7588fbc5cab26786881bb5e357ec1562a118646bc389224d60a45a
+oid sha256:cdcb8e5e7c548a56cd0a35a2c9bb10ad791d3828eed0c063e5a6d352374c517d
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d65945072135b85c2df9ab1f2183dceaa4884df6149d34e86ba3b5291e5289d
+oid sha256:61a19135443e44dedc426550bf9883c5626a874a708b9a836625a70bf1db005e
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2892548ae9c9c42bac9274716154c6f511e3242c31db918587a29bba4aed7b3f
+oid sha256:ce764d34a7f8f42ea0e1eeb92ce016727a74857ee03f898e45301c13248fe7f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb205f512e2dbedc6e9149b55b4f69ad4c7795b9c876b3eb5aa8d8b727bca50e
+oid sha256:5863424f0312bb85e67d22274e1da6de21abafad54b7c797160a5bf5abd89083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7182141701714655,
+  "epoch": 0.7246845681009382,
   "eval_steps": 386,
-  "global_step": 555,
+  "global_step": 560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3908,6 +3908,41 @@
       "learning_rate": 9.572744019753752e-05,
       "loss": 0.9516,
       "step": 555
+    },
+    {
+      "epoch": 0.71950824975736,
+      "grad_norm": 0.7633935213088989,
+      "learning_rate": 9.571074883435496e-05,
+      "loss": 0.8415,
+      "step": 556
+    },
+    {
+      "epoch": 0.7208023293432546,
+      "grad_norm": 0.7996200919151306,
+      "learning_rate": 9.569402639209589e-05,
+      "loss": 0.9336,
+      "step": 557
+    },
+    {
+      "epoch": 0.7220964089291492,
+      "grad_norm": 0.879639208316803,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.9479,
+      "step": 558
+    },
+    {
+      "epoch": 0.7233904885150437,
+      "grad_norm": 0.7905813455581665,
+      "learning_rate": 9.566048831584826e-05,
+      "loss": 0.7692,
+      "step": 559
+    },
+    {
+      "epoch": 0.7246845681009382,
+      "grad_norm": 0.7934820055961609,
+      "learning_rate": 9.564367270466247e-05,
+      "loss": 0.8735,
+      "step": 560
     }
   ],
   "logging_steps": 1,
@@ -3927,7 +3962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.204551302899302e+17,
+  "total_flos": 6.260448161483981e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null