Training in progress, epoch 11, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ed9d910865c040bb4e8228d8f17e050d4abd7fa4567fae0f618649423c3459
+oid sha256:be885acd1b623d184f6d21505f665bb48cdc90bb4f5ee078a8d6f1215d1e77fc
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f62a3434f2b8e8744dc25ea578e1b6786d5d9dab5d6a0b654cb08f8e0804d1
+oid sha256:4284e23f27cd81f019157a0ce26a7fcc3e95c3fce5557e16ef80f2d18736d10f
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0009e9c2bcc220e59267f52f8156b8d01b9e750bb5f6a74945612a1026990d89
+oid sha256:25f6571e80d696acb1f8fb4a87dde9dfb44c3e4b0276ab88f688ae9a992aa9cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f661b61f73b13b74450e15d45c319ce94ca9d3f4730beaaa9e2ebd1092cf2c
+oid sha256:2b7254df380501aa4b47fcd34bcc64f4edea336cec9c1bc437117f0d650ecf31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 11.0,
   "eval_steps": 500,
-  "global_step": 15270,
+  "global_step": 16797,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1071,6 +1071,111 @@
       "learning_rate": 0.00010213049267643142,
       "loss": 0.1606,
       "step": 15200
+    },
+    {
+      "epoch": 10.019646365422396,
+      "grad_norm": 2.236553192138672,
+      "learning_rate": 0.0001014647137150466,
+      "loss": 0.1476,
+      "step": 15300
+    },
+    {
+      "epoch": 10.08513425016372,
+      "grad_norm": 0.3063783645629883,
+      "learning_rate": 0.0001007989347536618,
+      "loss": 0.1373,
+      "step": 15400
+    },
+    {
+      "epoch": 10.150622134905042,
+      "grad_norm": 2.75140118598938,
+      "learning_rate": 0.00010013315579227697,
+      "loss": 0.1552,
+      "step": 15500
+    },
+    {
+      "epoch": 10.216110019646365,
+      "grad_norm": 0.556614339351654,
+      "learning_rate": 9.946737683089215e-05,
+      "loss": 0.1372,
+      "step": 15600
+    },
+    {
+      "epoch": 10.281597904387688,
+      "grad_norm": 0.4766944348812103,
+      "learning_rate": 9.880159786950732e-05,
+      "loss": 0.1383,
+      "step": 15700
+    },
+    {
+      "epoch": 10.347085789129011,
+      "grad_norm": 0.2531126141548157,
+      "learning_rate": 9.813581890812251e-05,
+      "loss": 0.1524,
+      "step": 15800
+    },
+    {
+      "epoch": 10.412573673870334,
+      "grad_norm": 0.5934678316116333,
+      "learning_rate": 9.747003994673769e-05,
+      "loss": 0.1428,
+      "step": 15900
+    },
+    {
+      "epoch": 10.478061558611657,
+      "grad_norm": 0.7293221950531006,
+      "learning_rate": 9.680426098535287e-05,
+      "loss": 0.144,
+      "step": 16000
+    },
+    {
+      "epoch": 10.54354944335298,
+      "grad_norm": 2.1880910396575928,
+      "learning_rate": 9.613848202396804e-05,
+      "loss": 0.1467,
+      "step": 16100
+    },
+    {
+      "epoch": 10.609037328094303,
+      "grad_norm": 3.2338201999664307,
+      "learning_rate": 9.547270306258322e-05,
+      "loss": 0.1438,
+      "step": 16200
+    },
+    {
+      "epoch": 10.674525212835626,
+      "grad_norm": 6.8729634284973145,
+      "learning_rate": 9.480692410119841e-05,
+      "loss": 0.1401,
+      "step": 16300
+    },
+    {
+      "epoch": 10.740013097576949,
+      "grad_norm": 1.1812797784805298,
+      "learning_rate": 9.414114513981358e-05,
+      "loss": 0.1451,
+      "step": 16400
+    },
+    {
+      "epoch": 10.805500982318271,
+      "grad_norm": 2.1439294815063477,
+      "learning_rate": 9.347536617842877e-05,
+      "loss": 0.1554,
+      "step": 16500
+    },
+    {
+      "epoch": 10.870988867059594,
+      "grad_norm": 0.730587363243103,
+      "learning_rate": 9.280958721704395e-05,
+      "loss": 0.1477,
+      "step": 16600
+    },
+    {
+      "epoch": 10.936476751800917,
+      "grad_norm": 0.5725963711738586,
+      "learning_rate": 9.214380825565913e-05,
+      "loss": 0.1529,
+      "step": 16700
     }
   ],
   "logging_steps": 100,
@@ -1090,7 +1195,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.749098290977178e+16,
+  "total_flos": 6.324008120221696e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null