Training in progress, step 7500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f779b104df13d2ef3ff238b794639a37aa0d0cd2cee827abc5589fa06152b0
+oid sha256:f5868ba587c3a824bc63fc899fdaeb6194618d48e020066ab2d114a4922121e1
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8923f264cdf21bc1f05bbec9aea66273c2a073b140852d3ef36be0f3c2033b55
+oid sha256:1a7d4f1caf511e7340b15cbbb3b6dc53b6d076d036358b828129c1ff3e45f7d3
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc2d65074a2fcc8399dba6d3c0a62d0568496e8b5831e17319a7dcd95d56dc4
+oid sha256:56ada7a9076e894e38e63b2e547d8bfe564d09412403a53a9fd4f37e79358b8d
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d9009edd34a178308b9e0582a661bb8622860498c029764cf1c8060b2e3cee
+oid sha256:16a4fdf7915d781b2a36593733c87afb8e5ce6e3d04384acc5dc1d5c1959abad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8642009384487994,
+  "epoch": 4.140215291195142,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,41 @@
       "learning_rate": 1.4887421946651437e-05,
       "loss": 0.1058,
       "step": 7000
+    },
+    {
+      "epoch": 3.919403808998068,
+      "grad_norm": 0.451486200094223,
+      "learning_rate": 1.354154177409932e-05,
+      "loss": 0.1057,
+      "step": 7100
+    },
+    {
+      "epoch": 3.9746066795473363,
+      "grad_norm": 0.4829927384853363,
+      "learning_rate": 1.224984117967648e-05,
+      "loss": 0.1034,
+      "step": 7200
+    },
+    {
+      "epoch": 4.029809550096605,
+      "grad_norm": 0.29708752036094666,
+      "learning_rate": 1.1014239712279945e-05,
+      "loss": 0.0977,
+      "step": 7300
+    },
+    {
+      "epoch": 4.0850124206458736,
+      "grad_norm": 0.4131404459476471,
+      "learning_rate": 9.83657355395079e-06,
+      "loss": 0.09,
+      "step": 7400
+    },
+    {
+      "epoch": 4.140215291195142,
+      "grad_norm": 0.3377688229084015,
+      "learning_rate": 8.718592791191299e-06,
+      "loss": 0.0907,
+      "step": 7500
     }
   ],
   "logging_steps": 100,
@@ -516,7 +551,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.711467098590806e+18,
+  "total_flos": 3.9786029952435487e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null