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:fbe4fc7be1ccba8daef25bd61f44ef5a75698422cc2183612d0124c6997dd256
+oid sha256:75f1d892b2366386761f0a72e1416c3a2e5e8a2c42705893fa8dc14c92a4967e
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac3e41769b66c1f194991218d9b55e721a05e01a8a0d058dec38ac038faeb25
+oid sha256:7fce9ad8826004310c683743744f592950aa99030e99c0a773d97fb67c7cc572
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8aabd519abc495ccb535c004724ef30a212d44ae05909dc43f853b8ee289e02
+oid sha256:0a124254e9255126713591c1f59a9c70d9b2a575d52070bed3b63df36570aa65
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd3dc831fa3d1edd6228ac25fb0b3524842e9bb646e369c883e51e64a29c94b
+oid sha256:4cf20479de077e1f12a1a0a2558891d641a7cd7f83617558364eb5fab3cecf50
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fead0c274db93260b4c1d4d18d91d2c90573a8fd7b91cf7923ae8bb2130a922
+oid sha256:2d32bbee8c1a3203e5781cafb76382ca878bef03f828d2544598d5b9e442e046
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d85a19b48d8f01ee180cf08c27ad1e5bd30f3bb9466da21da8d2f31fda9284
+oid sha256:44022d716771debca474b8d0807aaa6d48fb5a1f2aa65fce603e5767b76f790b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:521ae5e3fe83cd3ae02d0637923203760021afa02676b0d5217193cc127d4bfe
+oid sha256:92c40e70c89071663742fb7f45e3d35ba3e327e558255bec76dafa8c4bde0527
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7543859649122808,
+  "epoch": 2.6315789473684212,
   "eval_steps": 8,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,6 +413,205 @@
       "learning_rate": 4.5871032726383386e-05,
       "loss": 10.4802,
       "step": 50
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.03883575648069382,
+      "learning_rate": 4.381536843653262e-05,
+      "loss": 10.0867,
+      "step": 51
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 0.04744650423526764,
+      "learning_rate": 4.17702704859633e-05,
+      "loss": 10.9924,
+      "step": 52
+    },
+    {
+      "epoch": 1.8596491228070176,
+      "grad_norm": 0.046235229820013046,
+      "learning_rate": 3.973923289021829e-05,
+      "loss": 9.8877,
+      "step": 53
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.05214040353894234,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 10.369,
+      "step": 54
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.041679393500089645,
+      "learning_rate": 3.5733188787544745e-05,
+      "loss": 11.1291,
+      "step": 55
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 0.04238257557153702,
+      "learning_rate": 3.3765026539765834e-05,
+      "loss": 9.99,
+      "step": 56
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "eval_loss": 10.36238956451416,
+      "eval_runtime": 0.0482,
+      "eval_samples_per_second": 1990.632,
+      "eval_steps_per_second": 62.207,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.07189306616783142,
+      "learning_rate": 3.18246014718085e-05,
+      "loss": 15.2056,
+      "step": 57
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.041363537311553955,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 10.3649,
+      "step": 58
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.04258178174495697,
+      "learning_rate": 2.804017055763149e-05,
+      "loss": 10.3674,
+      "step": 59
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.0516861192882061,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 10.3673,
+      "step": 60
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.0398215688765049,
+      "learning_rate": 2.4405747545519963e-05,
+      "loss": 10.3627,
+      "step": 61
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.052411239594221115,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 10.3681,
+      "step": 62
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.04860823601484299,
+      "learning_rate": 2.094615922990309e-05,
+      "loss": 10.3668,
+      "step": 63
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.04707632586359978,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 10.3688,
+      "step": 64
+    },
+    {
+      "epoch": 2.245614035087719,
+      "eval_loss": 10.361990928649902,
+      "eval_runtime": 0.0503,
+      "eval_samples_per_second": 1907.875,
+      "eval_steps_per_second": 59.621,
+      "step": 64
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.047561973333358765,
+      "learning_rate": 1.768503810695295e-05,
+      "loss": 10.3625,
+      "step": 65
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.0470132939517498,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 10.3681,
+      "step": 66
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.0447855144739151,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3667,
+      "step": 67
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.04761236160993576,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 10.3676,
+      "step": 68
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.04890201613306999,
+      "learning_rate": 1.1845796590009683e-05,
+      "loss": 10.3666,
+      "step": 69
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.055010754615068436,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 10.3671,
+      "step": 70
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.04802040010690689,
+      "learning_rate": 9.307564136490254e-06,
+      "loss": 10.3659,
+      "step": 71
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.0498974546790123,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 10.3678,
+      "step": 72
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_loss": 10.361777305603027,
+      "eval_runtime": 0.0479,
+      "eval_samples_per_second": 2002.244,
+      "eval_steps_per_second": 62.57,
+      "step": 72
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.052232056856155396,
+      "learning_rate": 7.047302281505736e-06,
+      "loss": 10.3665,
+      "step": 73
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.045570556074380875,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 10.3654,
+      "step": 74
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.050531383603811264,
+      "learning_rate": 5.080450905401057e-06,
+      "loss": 10.364,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -432,7 +631,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10460489318400.0,
+  "total_flos": 15690733977600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null