Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4375ae8aadc16b556de34b02a8e085a757e5a891b6eb953bfe02e279c56d7c6
+oid sha256:97b55733a1680a3856188a0784564a3672e1b23f298481b76a58a6c2bfb6dc6e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c985495e73d0a2fa5cf429a43c1c23d3cca231e8b5118d44750a33669fc2cd42
+oid sha256:6922b3cc91be5a7d9adb82e4b31e92c9031b6eda94de10432d94bf5db39943f9
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819d8aab5577048c315241284cdebd9e8c6c2ee8bace6bcaa1a1d8d8d97f77b1
+oid sha256:60391f039986d463d1b8eae9b77fcda050ab137f474c9c67cf4fe317d8dc171a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14461315979754158,
+  "epoch": 0.28922631959508316,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 8.959,
       "eval_steps_per_second": 4.479,
       "step": 25
+    },
+    {
+      "epoch": 0.15039768618944324,
+      "grad_norm": 5.868927001953125,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 3.1901,
+      "step": 26
+    },
+    {
+      "epoch": 0.1561822125813449,
+      "grad_norm": 2.6448488235473633,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 3.1779,
+      "step": 27
+    },
+    {
+      "epoch": 0.16196673897324657,
+      "grad_norm": 1.8636095523834229,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 3.1947,
+      "step": 28
+    },
+    {
+      "epoch": 0.16775126536514823,
+      "grad_norm": 4.58578634262085,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 3.5627,
+      "step": 29
+    },
+    {
+      "epoch": 0.1735357917570499,
+      "grad_norm": 21.534526824951172,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.68,
+      "step": 30
+    },
+    {
+      "epoch": 0.17932031814895155,
+      "grad_norm": 8.905357360839844,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 3.7521,
+      "step": 31
+    },
+    {
+      "epoch": 0.18510484454085321,
+      "grad_norm": 4.796418190002441,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 3.2734,
+      "step": 32
+    },
+    {
+      "epoch": 0.19088937093275488,
+      "grad_norm": 2.0651814937591553,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 3.0878,
+      "step": 33
+    },
+    {
+      "epoch": 0.19667389732465654,
+      "grad_norm": 3.3176019191741943,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 3.186,
+      "step": 34
+    },
+    {
+      "epoch": 0.2024584237165582,
+      "grad_norm": 2.418898344039917,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.0962,
+      "step": 35
+    },
+    {
+      "epoch": 0.20824295010845986,
+      "grad_norm": 4.730885028839111,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 3.1704,
+      "step": 36
+    },
+    {
+      "epoch": 0.21402747650036152,
+      "grad_norm": 4.24273681640625,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 3.2574,
+      "step": 37
+    },
+    {
+      "epoch": 0.2198120028922632,
+      "grad_norm": 9.04359245300293,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 3.4872,
+      "step": 38
+    },
+    {
+      "epoch": 0.22559652928416485,
+      "grad_norm": 0.8422988653182983,
+      "learning_rate": 5e-05,
+      "loss": 3.0299,
+      "step": 39
+    },
+    {
+      "epoch": 0.2313810556760665,
+      "grad_norm": 8.053430557250977,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 3.4567,
+      "step": 40
+    },
+    {
+      "epoch": 0.23716558206796817,
+      "grad_norm": 0.7461191415786743,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 3.0264,
+      "step": 41
+    },
+    {
+      "epoch": 0.24295010845986983,
+      "grad_norm": 0.6736895442008972,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.0185,
+      "step": 42
+    },
+    {
+      "epoch": 0.24873463485177152,
+      "grad_norm": 0.15485769510269165,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.0018,
+      "step": 43
+    },
+    {
+      "epoch": 0.2545191612436732,
+      "grad_norm": 5.6190338134765625,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 3.7042,
+      "step": 44
+    },
+    {
+      "epoch": 0.2603036876355748,
+      "grad_norm": 17.187482833862305,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.8073,
+      "step": 45
+    },
+    {
+      "epoch": 0.2660882140274765,
+      "grad_norm": 2.7848260402679443,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 3.3303,
+      "step": 46
+    },
+    {
+      "epoch": 0.27187274041937814,
+      "grad_norm": 7.332921504974365,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.6265,
+      "step": 47
+    },
+    {
+      "epoch": 0.27765726681127983,
+      "grad_norm": 6.031116962432861,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.26,
+      "step": 48
+    },
+    {
+      "epoch": 0.28344179320318147,
+      "grad_norm": 5.31016206741333,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 3.4005,
+      "step": 49
+    },
+    {
+      "epoch": 0.28922631959508316,
+      "grad_norm": 6.793763160705566,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 3.6388,
+      "step": 50
+    },
+    {
+      "epoch": 0.28922631959508316,
+      "eval_loss": NaN,
+      "eval_runtime": 16.2685,
+      "eval_samples_per_second": 8.974,
+      "eval_steps_per_second": 4.487,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.73005226082304e+16,
+  "total_flos": 7.46010452164608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null