Training in progress, step 5500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e709f2b6aff15184df51e230bda7cd95f138ebf307fb685e47bd4144fa60c4
+oid sha256:bac2b56ba43e7cf6e627c6d78ee2d8a54c6a9b8482738e4d0e5508b059244676
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0219dbbfa399b842520b5177ca95d1af828b294ca5f51a3bda075ca0414a6d70
+oid sha256:69973d0bdbecfdff6671addf5401d05a7990dd2a8e07167f9b28ddcc497207f6
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1d32a5240cd2bec4435f56208363b0d59e8bf8c99164c7cbee490171e7de00
+oid sha256:acc2d65074a2fcc8399dba6d3c0a62d0568496e8b5831e17319a7dcd95d56dc4
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d5326d5d920a3536b649f61851c1c782c12a52b22b2172b54973e7158a2031
+oid sha256:dbd3295a917ebbf1cf0429160bcb6ae7d8acc650fcf19c056fed23a32459f9c3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.760143527463428,
+  "epoch": 3.036157880209771,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,41 @@
       "learning_rate": 4.962412271614282e-05,
       "loss": 0.146,
       "step": 5000
+    },
+    {
+      "epoch": 2.8153463980126965,
+      "grad_norm": 0.671291172504425,
+      "learning_rate": 4.7697339933668414e-05,
+      "loss": 0.1483,
+      "step": 5100
+    },
+    {
+      "epoch": 2.870549268561965,
+      "grad_norm": 0.6203655004501343,
+      "learning_rate": 4.5773979049898455e-05,
+      "loss": 0.1451,
+      "step": 5200
+    },
+    {
+      "epoch": 2.9257521391112338,
+      "grad_norm": 0.8333371877670288,
+      "learning_rate": 4.385689830092801e-05,
+      "loss": 0.1437,
+      "step": 5300
+    },
+    {
+      "epoch": 2.9809550096605024,
+      "grad_norm": 0.725379467010498,
+      "learning_rate": 4.194894659017415e-05,
+      "loss": 0.1412,
+      "step": 5400
+    },
+    {
+      "epoch": 3.036157880209771,
+      "grad_norm": 0.4681724011898041,
+      "learning_rate": 4.005295925472484e-05,
+      "loss": 0.1206,
+      "step": 5500
     }
   ],
   "logging_steps": 100,
@@ -376,7 +411,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.650426442350461e+18,
+  "total_flos": 2.9148141046545777e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null