Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3871051763abd6a8381dee94c1ae48a4a887407d559443cb3b7302fadc4f12d5
+oid sha256:6c331626b184f08fed5487535192256ea96faad90adefe4e1ad46eb3f553696d
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0fa50c406a6d06d50cd4584d17c79ff46d09eed2a5fe5d8cae7044a79eb40a
+oid sha256:3fb06be01e5059ac8d0974d478720be53ed4482478b2f64e5094b6b15e6c0831
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24dbb7eec220c13de71bffe99dff5438a1f594ce18e2886e93e45665b8ac914f
+oid sha256:17e1f0fd2d004d6caaae844aa17b92356b2e2f60ef5bfaf5353e49ccd0051ffa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f7e1e2b46d20cd957e0e95bcb2e067d758e535289dbb0bf8ff56fe10e1df41
+oid sha256:981bbea8034bbbae85baf44fc3a7f5bd1463eae4931e71f483cdca42e7a37e82
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06215c771b27617bf1429ea562d72f5914b0ae3cab53c2da36b5aa306d7c747e
+oid sha256:1793234b26d0e6ac7ecfc78a9a7d47b949a0319dc3c10c322d5f7a878592c6c9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ec17834f290c890763449aed1337a9467d9173b2ddc32416f4f24d4954a63b
+oid sha256:ce143f3192cb1b2e626d251c64dac68350718e07c33521f586159568d189c078
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01426126640045636,
+  "epoch": 0.02852253280091272,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 3.0422,
       "step": 25
+    },
+    {
+      "epoch": 0.014831717056474614,
+      "grad_norm": 0.9183709621429443,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.9668,
+      "step": 26
+    },
+    {
+      "epoch": 0.01540216771249287,
+      "grad_norm": 0.8766528367996216,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 3.0137,
+      "step": 27
+    },
+    {
+      "epoch": 0.01540216771249287,
+      "eval_loss": 2.9818027019500732,
+      "eval_runtime": 8.1382,
+      "eval_samples_per_second": 725.47,
+      "eval_steps_per_second": 22.732,
+      "step": 27
+    },
+    {
+      "epoch": 0.015972618368511125,
+      "grad_norm": 0.8579592108726501,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.9181,
+      "step": 28
+    },
+    {
+      "epoch": 0.01654306902452938,
+      "grad_norm": 0.8335272073745728,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.8452,
+      "step": 29
+    },
+    {
+      "epoch": 0.017113519680547633,
+      "grad_norm": 0.7539997696876526,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.9104,
+      "step": 30
+    },
+    {
+      "epoch": 0.017683970336565887,
+      "grad_norm": 0.7295988202095032,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.738,
+      "step": 31
+    },
+    {
+      "epoch": 0.01825442099258414,
+      "grad_norm": 0.745151162147522,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.845,
+      "step": 32
+    },
+    {
+      "epoch": 0.018824871648602397,
+      "grad_norm": 0.7539723515510559,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.9025,
+      "step": 33
+    },
+    {
+      "epoch": 0.01939532230462065,
+      "grad_norm": 0.7784116864204407,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.8647,
+      "step": 34
+    },
+    {
+      "epoch": 0.019965772960638905,
+      "grad_norm": 0.7879242897033691,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.8638,
+      "step": 35
+    },
+    {
+      "epoch": 0.02053622361665716,
+      "grad_norm": 0.8056729435920715,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.7922,
+      "step": 36
+    },
+    {
+      "epoch": 0.02053622361665716,
+      "eval_loss": 2.719639778137207,
+      "eval_runtime": 8.0538,
+      "eval_samples_per_second": 733.071,
+      "eval_steps_per_second": 22.971,
+      "step": 36
+    },
+    {
+      "epoch": 0.021106674272675412,
+      "grad_norm": 0.7197538018226624,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.7332,
+      "step": 37
+    },
+    {
+      "epoch": 0.02167712492869367,
+      "grad_norm": 0.6454269289970398,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.6288,
+      "step": 38
+    },
+    {
+      "epoch": 0.022247575584711923,
+      "grad_norm": 0.9242546558380127,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.8319,
+      "step": 39
+    },
+    {
+      "epoch": 0.022818026240730177,
+      "grad_norm": 0.7071914076805115,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.7255,
+      "step": 40
+    },
+    {
+      "epoch": 0.02338847689674843,
+      "grad_norm": 0.6768962144851685,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.6548,
+      "step": 41
+    },
+    {
+      "epoch": 0.023958927552766685,
+      "grad_norm": 0.7336259484291077,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.5842,
+      "step": 42
+    },
+    {
+      "epoch": 0.02452937820878494,
+      "grad_norm": 0.6378612518310547,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.6391,
+      "step": 43
+    },
+    {
+      "epoch": 0.025099828864803195,
+      "grad_norm": 0.6894816756248474,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.5276,
+      "step": 44
+    },
+    {
+      "epoch": 0.02567027952082145,
+      "grad_norm": 0.6339684724807739,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.5678,
+      "step": 45
+    },
+    {
+      "epoch": 0.02567027952082145,
+      "eval_loss": 2.5278868675231934,
+      "eval_runtime": 8.0833,
+      "eval_samples_per_second": 730.395,
+      "eval_steps_per_second": 22.887,
+      "step": 45
+    },
+    {
+      "epoch": 0.026240730176839703,
+      "grad_norm": 0.6821937561035156,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.6051,
+      "step": 46
+    },
+    {
+      "epoch": 0.026811180832857957,
+      "grad_norm": 0.625619113445282,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.512,
+      "step": 47
+    },
+    {
+      "epoch": 0.027381631488876214,
+      "grad_norm": 0.6462172865867615,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.4584,
+      "step": 48
+    },
+    {
+      "epoch": 0.027952082144894468,
+      "grad_norm": 0.6954731941223145,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.4418,
+      "step": 49
+    },
+    {
+      "epoch": 0.02852253280091272,
+      "grad_norm": 0.6652643084526062,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.3786,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1388375860838400.0,
+  "total_flos": 2783693600980992.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null