Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2ba720619fb301e48148cf6e0280c37fd098cf2841e4a9247206ddfb7f7014
+oid sha256:3e128a7edfa271a43ffc8c41ddd0f4cfd32a9ac9e4c27646b9c012155190eb3d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ff7107ee42cb326e90888bec3c9892b8d85baf15f02de28fa1b614bfc32447
+oid sha256:2e4b2bc23ae01039b99d48aac443ead16ed5a346948baebe98718d3b00235213
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8c6c81606f3a5435c7393e040ec358e739e8efa87ab189ad0ce9498834ba37
+oid sha256:ef4f0148473100f8de623d21a2f3a77049b961024f4e3e11ffc26313622990b0
 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": 0.0751597143930853,
+  "epoch": 0.1503194287861706,
   "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": 5.869,
       "eval_steps_per_second": 2.945,
       "step": 25
+    },
+    {
+      "epoch": 0.07816610296880872,
+      "grad_norm": 0.6408647298812866,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 1.2437,
+      "step": 26
+    },
+    {
+      "epoch": 0.08117249154453213,
+      "grad_norm": 0.558180570602417,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.1957,
+      "step": 27
+    },
+    {
+      "epoch": 0.08417888012025554,
+      "grad_norm": 0.5853379964828491,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 1.2865,
+      "step": 28
+    },
+    {
+      "epoch": 0.08718526869597895,
+      "grad_norm": 0.6303192973136902,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 1.263,
+      "step": 29
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "grad_norm": 0.6096851825714111,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.1928,
+      "step": 30
+    },
+    {
+      "epoch": 0.09319804584742578,
+      "grad_norm": 0.5614527463912964,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.1992,
+      "step": 31
+    },
+    {
+      "epoch": 0.09620443442314919,
+      "grad_norm": 0.5434235334396362,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 1.2538,
+      "step": 32
+    },
+    {
+      "epoch": 0.0992108229988726,
+      "grad_norm": 0.4981926381587982,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.1772,
+      "step": 33
+    },
+    {
+      "epoch": 0.10221721157459601,
+      "grad_norm": 0.5694061517715454,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.0769,
+      "step": 34
+    },
+    {
+      "epoch": 0.10522360015031942,
+      "grad_norm": 0.6556212902069092,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.173,
+      "step": 35
+    },
+    {
+      "epoch": 0.10822998872604284,
+      "grad_norm": 0.5893046855926514,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.1642,
+      "step": 36
+    },
+    {
+      "epoch": 0.11123637730176625,
+      "grad_norm": 0.5705428123474121,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.1736,
+      "step": 37
+    },
+    {
+      "epoch": 0.11424276587748966,
+      "grad_norm": 0.615963339805603,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.1204,
+      "step": 38
+    },
+    {
+      "epoch": 0.11724915445321307,
+      "grad_norm": 0.6671907901763916,
+      "learning_rate": 5e-05,
+      "loss": 1.1691,
+      "step": 39
+    },
+    {
+      "epoch": 0.12025554302893648,
+      "grad_norm": 0.5774475336074829,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.1567,
+      "step": 40
+    },
+    {
+      "epoch": 0.1232619316046599,
+      "grad_norm": 0.5467556118965149,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 1.1104,
+      "step": 41
+    },
+    {
+      "epoch": 0.1262683201803833,
+      "grad_norm": 0.5328946709632874,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1929,
+      "step": 42
+    },
+    {
+      "epoch": 0.12927470875610672,
+      "grad_norm": 0.5901719927787781,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.1005,
+      "step": 43
+    },
+    {
+      "epoch": 0.13228109733183013,
+      "grad_norm": 0.5560078024864197,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.1103,
+      "step": 44
+    },
+    {
+      "epoch": 0.13528748590755355,
+      "grad_norm": 0.6406859755516052,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1583,
+      "step": 45
+    },
+    {
+      "epoch": 0.13829387448327696,
+      "grad_norm": 0.7661237716674805,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 1.1796,
+      "step": 46
+    },
+    {
+      "epoch": 0.14130026305900037,
+      "grad_norm": 0.694031298160553,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.2414,
+      "step": 47
+    },
+    {
+      "epoch": 0.14430665163472378,
+      "grad_norm": 0.6730867624282837,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1871,
+      "step": 48
+    },
+    {
+      "epoch": 0.1473130402104472,
+      "grad_norm": 0.8268274664878845,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 1.0511,
+      "step": 49
+    },
+    {
+      "epoch": 0.1503194287861706,
+      "grad_norm": 0.9899184107780457,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 1.1512,
+      "step": 50
+    },
+    {
+      "epoch": 0.1503194287861706,
+      "eval_loss": 1.1183983087539673,
+      "eval_runtime": 47.4903,
+      "eval_samples_per_second": 5.917,
+      "eval_steps_per_second": 2.969,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.76735278343127e+16,
+  "total_flos": 7.49740504425431e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null