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:f81ae6dd394d35239345242bc20037af9607f513c30dc981f4722107525c1104
+oid sha256:78a17e242a38b1c1b535d1ab7f8acd6f0e89e590d0dd05d7a8c6ca3bfe79737f
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e61d43316e4574b9841d323d9e912fc4cdac3841c1be6cb96cefedc3e21a2f8
+oid sha256:e31ddf03c3777472a31e31670697557906db3af94488f56103c697b428faa0a0
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833fe5b29460120b30d654b8d8e5a195800f3178213521632f9a22f37b5510d4
+oid sha256:8a6d9423c3bde5a7a81310841d28d1f29cb3fad4e24fc19d65fe9bef28aa5e0a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ca7013ee7fd0ff939eff4c2f3425fa837a24771519d8017e892c2a7c72e562
+oid sha256:2f06e3d830720388931a8699bc8d1538e8099b6318aeb0190a81f1bf411eb11e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc71ac30b2d9738f99e554b5e34e6ef214b1342d3ab86f73941ffd22cc2df2d8
+oid sha256:721e9aa82bd50a80e9fff36b309e0ebecd20573ba4ae8833d6b174ccc5ee9b91
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9af6f1571ae999a29c4513b022b2e66401c171e8251ebb168e66e222402d6de
+oid sha256:b37d8acd327d0a504e80fcf6257af9ab13af948e572aa9a98348538b86643f15
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1134846210479736,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.026549847338377803,
+  "best_metric": 1.0646418333053589,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.053099694676755606,
   "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": 9.644,
       "eval_steps_per_second": 2.508,
       "step": 25
+    },
+    {
+      "epoch": 0.027611841231912918,
+      "grad_norm": 16.71857261657715,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 36.6123,
+      "step": 26
+    },
+    {
+      "epoch": 0.02867383512544803,
+      "grad_norm": 10.87404727935791,
+      "learning_rate": 7.75e-05,
+      "loss": 37.5371,
+      "step": 27
+    },
+    {
+      "epoch": 0.02973582901898314,
+      "grad_norm": 56.00872039794922,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 64.4314,
+      "step": 28
+    },
+    {
+      "epoch": 0.030797822912518254,
+      "grad_norm": 22.56377601623535,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 35.6372,
+      "step": 29
+    },
+    {
+      "epoch": 0.03185981680605336,
+      "grad_norm": 12.734387397766113,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 32.3161,
+      "step": 30
+    },
+    {
+      "epoch": 0.03292181069958848,
+      "grad_norm": 14.141098976135254,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 34.3303,
+      "step": 31
+    },
+    {
+      "epoch": 0.03398380459312359,
+      "grad_norm": 9.78072738647461,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 32.2263,
+      "step": 32
+    },
+    {
+      "epoch": 0.0350457984866587,
+      "grad_norm": 12.632477760314941,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 33.7613,
+      "step": 33
+    },
+    {
+      "epoch": 0.036107792380193814,
+      "grad_norm": 14.908531188964844,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 36.611,
+      "step": 34
+    },
+    {
+      "epoch": 0.037169786273728925,
+      "grad_norm": 22.300689697265625,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 36.3684,
+      "step": 35
+    },
+    {
+      "epoch": 0.038231780167264036,
+      "grad_norm": 22.755752563476562,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 37.6983,
+      "step": 36
+    },
+    {
+      "epoch": 0.03929377406079915,
+      "grad_norm": 22.28518295288086,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 37.6341,
+      "step": 37
+    },
+    {
+      "epoch": 0.040355767954334265,
+      "grad_norm": 29.46213150024414,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 41.3437,
+      "step": 38
+    },
+    {
+      "epoch": 0.041417761847869376,
+      "grad_norm": 9.17482852935791,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 36.185,
+      "step": 39
+    },
+    {
+      "epoch": 0.04247975574140449,
+      "grad_norm": 11.093894004821777,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 38.199,
+      "step": 40
+    },
+    {
+      "epoch": 0.0435417496349396,
+      "grad_norm": 48.82663345336914,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 52.5876,
+      "step": 41
+    },
+    {
+      "epoch": 0.04460374352847471,
+      "grad_norm": 14.177578926086426,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 33.7556,
+      "step": 42
+    },
+    {
+      "epoch": 0.04566573742200982,
+      "grad_norm": 12.167204856872559,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 31.3788,
+      "step": 43
+    },
+    {
+      "epoch": 0.04672773131554494,
+      "grad_norm": 14.164153099060059,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 30.4894,
+      "step": 44
+    },
+    {
+      "epoch": 0.04778972520908005,
+      "grad_norm": 13.399406433105469,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 32.0962,
+      "step": 45
+    },
+    {
+      "epoch": 0.04885171910261516,
+      "grad_norm": 15.352862358093262,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 34.1184,
+      "step": 46
+    },
+    {
+      "epoch": 0.04991371299615027,
+      "grad_norm": 15.30873966217041,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 33.8862,
+      "step": 47
+    },
+    {
+      "epoch": 0.050975706889685383,
+      "grad_norm": 14.761381149291992,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 33.5394,
+      "step": 48
+    },
+    {
+      "epoch": 0.052037700783220495,
+      "grad_norm": 18.559497833251953,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 37.7572,
+      "step": 49
+    },
+    {
+      "epoch": 0.053099694676755606,
+      "grad_norm": 29.4871826171875,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 37.6346,
+      "step": 50
+    },
+    {
+      "epoch": 0.053099694676755606,
+      "eval_loss": 1.0646418333053589,
+      "eval_runtime": 5.2151,
+      "eval_samples_per_second": 9.587,
+      "eval_steps_per_second": 2.493,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.017220982551347e+16,
+  "total_flos": 1.204505434610729e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null