Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f4a570afa965aac1e4b10e6e715afbe220c270be7ca5803e189d3b30457290
+oid sha256:aca3777dc11dfa9bf88d8cc6d00ba6310cb5d9fe808e281c945e383848b6e8ca
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c05738dbdb695545f24d369ab8808165d6aa7780c236424018795e6b65c0321
+oid sha256:25da41f8396bcb2e1bcf53e9d8725c15ff2bbc31ebf343f000dea35d8994c7b5
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afbbeff9c2106aa6747a9a6b6d1f2974325978cb30b288d183425c5cf2062c3
+oid sha256:997b37e8e4d4313266e5aafe8f4d418b086633a9c94b4c13db86ae839aa09b15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
+oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04402377283733216,
+  "epoch": 0.06603565925599823,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 4.04,
       "eval_steps_per_second": 2.024,
       "step": 50
+    },
+    {
+      "epoch": 0.044904248294078804,
+      "grad_norm": 2.4015002250671387,
+      "learning_rate": 0.00011391731009600654,
+      "loss": 0.8285,
+      "step": 51
+    },
+    {
+      "epoch": 0.04578472375082544,
+      "grad_norm": 1.8211569786071777,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.7426,
+      "step": 52
+    },
+    {
+      "epoch": 0.04666519920757209,
+      "grad_norm": 1.4902381896972656,
+      "learning_rate": 0.00010697564737441252,
+      "loss": 0.4468,
+      "step": 53
+    },
+    {
+      "epoch": 0.047545674664318735,
+      "grad_norm": 1.00511634349823,
+      "learning_rate": 0.00010348994967025012,
+      "loss": 0.4147,
+      "step": 54
+    },
+    {
+      "epoch": 0.048426150121065374,
+      "grad_norm": 2.31351637840271,
+      "learning_rate": 0.0001,
+      "loss": 0.5817,
+      "step": 55
+    },
+    {
+      "epoch": 0.04930662557781202,
+      "grad_norm": 2.334179162979126,
+      "learning_rate": 9.651005032974994e-05,
+      "loss": 0.3195,
+      "step": 56
+    },
+    {
+      "epoch": 0.05018710103455866,
+      "grad_norm": 1.681875228881836,
+      "learning_rate": 9.302435262558747e-05,
+      "loss": 0.7227,
+      "step": 57
+    },
+    {
+      "epoch": 0.051067576491305305,
+      "grad_norm": 2.5601327419281006,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.6287,
+      "step": 58
+    },
+    {
+      "epoch": 0.05194805194805195,
+      "grad_norm": 2.3683104515075684,
+      "learning_rate": 8.608268990399349e-05,
+      "loss": 0.7883,
+      "step": 59
+    },
+    {
+      "epoch": 0.05282852740479859,
+      "grad_norm": 1.4547897577285767,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.5512,
+      "step": 60
+    },
+    {
+      "epoch": 0.05370900286154524,
+      "grad_norm": 2.2935614585876465,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 0.5621,
+      "step": 61
+    },
+    {
+      "epoch": 0.054589478318291876,
+      "grad_norm": 1.791729211807251,
+      "learning_rate": 7.580781044003324e-05,
+      "loss": 0.5211,
+      "step": 62
+    },
+    {
+      "epoch": 0.05546995377503852,
+      "grad_norm": 1.9423251152038574,
+      "learning_rate": 7.243626441830009e-05,
+      "loss": 0.5148,
+      "step": 63
+    },
+    {
+      "epoch": 0.05635042923178516,
+      "grad_norm": 1.6972748041152954,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5665,
+      "step": 64
+    },
+    {
+      "epoch": 0.05723090468853181,
+      "grad_norm": 1.5219111442565918,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.4329,
+      "step": 65
+    },
+    {
+      "epoch": 0.05811138014527845,
+      "grad_norm": 3.782133102416992,
+      "learning_rate": 6.25393406584088e-05,
+      "loss": 0.5416,
+      "step": 66
+    },
+    {
+      "epoch": 0.05899185560202509,
+      "grad_norm": 3.464118719100952,
+      "learning_rate": 5.9326335692419995e-05,
+      "loss": 0.6234,
+      "step": 67
+    },
+    {
+      "epoch": 0.05987233105877174,
+      "grad_norm": 5.132722854614258,
+      "learning_rate": 5.616288532109225e-05,
+      "loss": 0.7638,
+      "step": 68
+    },
+    {
+      "epoch": 0.06075280651551838,
+      "grad_norm": 2.7802538871765137,
+      "learning_rate": 5.305284372141095e-05,
+      "loss": 0.4478,
+      "step": 69
+    },
+    {
+      "epoch": 0.061633281972265024,
+      "grad_norm": 2.032424211502075,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4982,
+      "step": 70
+    },
+    {
+      "epoch": 0.06251375742901166,
+      "grad_norm": 1.9181748628616333,
+      "learning_rate": 4.700807357667952e-05,
+      "loss": 0.4599,
+      "step": 71
+    },
+    {
+      "epoch": 0.06339423288575831,
+      "grad_norm": 2.8431079387664795,
+      "learning_rate": 4.4080709652925336e-05,
+      "loss": 0.5564,
+      "step": 72
+    },
+    {
+      "epoch": 0.06427470834250495,
+      "grad_norm": 2.748572587966919,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5392,
+      "step": 73
+    },
+    {
+      "epoch": 0.0651551837992516,
+      "grad_norm": 3.2076663970947266,
+      "learning_rate": 3.843385246743417e-05,
+      "loss": 0.7945,
+      "step": 74
+    },
+    {
+      "epoch": 0.06603565925599823,
+      "grad_norm": 0.9875300526618958,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.388,
+      "step": 75
+    },
+    {
+      "epoch": 0.06603565925599823,
+      "eval_loss": 0.4547451436519623,
+      "eval_runtime": 118.536,
+      "eval_samples_per_second": 4.041,
+      "eval_steps_per_second": 2.025,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -400,7 +583,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.59230637948928e+16,
+  "total_flos": 9.88845956923392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null