Training in progress, step 83, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d0f2a632229e3200310f0089e387dda91ea6cbdfb42dcf22d2a65a0c16503b
+oid sha256:3343b023a82806d5e302c99a2b8f879b99addb60ce17ba6ac6c44f4d689d1bbc
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ab5c219ffac36a999635f941c11d3de77d27320896e9ca1bca7e80f68a635e
+oid sha256:5bf72fdb256ee460c269a2ef92128bd443f37d9e9db95e35ec0002e48b56f387
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd60aa48ff4b0c5681667e4bac1eda701a82305811fa88b41f02f39447f3e79
+oid sha256:65f047353f5ee09e16f21ce9336a8410cb538b6a0d98e0dfff2ce2ff5af26c48
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43588fda80d961cb4666ec04fcbe5427d597b97b08c9c6ace0b5419fa71de599
+oid sha256:f5e9702c50a0713ada5f38b5e1e87fe9f8fe4cabcfa98fc9a65c9c491f51226a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0185dc93a4892f7deb203c00b7d00a4b84b4e35d61b0005c10e564ac482dd90c
+oid sha256:e09f8f070e6ba322b6856908fabd4eadaeb3e8040782a2129aaba24a0fc1b3bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d419dea6ea4da3fe80fcd20962b77c9210609eca6f0cfcc90b338570bd4ba4
+oid sha256:cce67a5dfa98d2792e50ac3bc450bd2a97114da14a3637058a2c4cac9c103211
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0925e9b4a1c852b6b439be21a6791f6589a1c819669446d27fb3f562a9d12d34
+oid sha256:de625b9c46b02e26c7087167b584f523763df8c1700128401bca00e401a1eac6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.645294189453125,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.008535017576801822,
+  "epoch": 0.014168129177491025,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 83,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,245 @@
       "eval_samples_per_second": 13.967,
       "eval_steps_per_second": 3.631,
       "step": 50
+    },
+    {
+      "epoch": 0.008705717928337858,
+      "grad_norm": 0.2589752972126007,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.5807,
+      "step": 51
+    },
+    {
+      "epoch": 0.008876418279873895,
+      "grad_norm": 0.2531092166900635,
+      "learning_rate": 3.942473243151281e-05,
+      "loss": 0.6016,
+      "step": 52
+    },
+    {
+      "epoch": 0.009047118631409931,
+      "grad_norm": 0.2799888253211975,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6611,
+      "step": 53
+    },
+    {
+      "epoch": 0.009217818982945969,
+      "grad_norm": 0.2377174347639084,
+      "learning_rate": 3.616031181081575e-05,
+      "loss": 0.6311,
+      "step": 54
+    },
+    {
+      "epoch": 0.009388519334482004,
+      "grad_norm": 0.30469128489494324,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 0.6666,
+      "step": 55
+    },
+    {
+      "epoch": 0.009559219686018042,
+      "grad_norm": 0.21915645897388458,
+      "learning_rate": 3.301204413263704e-05,
+      "loss": 0.7322,
+      "step": 56
+    },
+    {
+      "epoch": 0.009729920037554077,
+      "grad_norm": 0.2494356781244278,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 0.7055,
+      "step": 57
+    },
+    {
+      "epoch": 0.009900620389090113,
+      "grad_norm": 0.24379698932170868,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7207,
+      "step": 58
+    },
+    {
+      "epoch": 0.01007132074062615,
+      "grad_norm": 0.2400536686182022,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 0.659,
+      "step": 59
+    },
+    {
+      "epoch": 0.010242021092162186,
+      "grad_norm": 0.2639144957065582,
+      "learning_rate": 2.7140772281057468e-05,
+      "loss": 0.7007,
+      "step": 60
+    },
+    {
+      "epoch": 0.010412721443698224,
+      "grad_norm": 0.2899046540260315,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 0.7335,
+      "step": 61
+    },
+    {
+      "epoch": 0.01058342179523426,
+      "grad_norm": 0.32616889476776123,
+      "learning_rate": 2.445396645101762e-05,
+      "loss": 0.6132,
+      "step": 62
+    },
+    {
+      "epoch": 0.010754122146770295,
+      "grad_norm": 0.30279648303985596,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5414,
+      "step": 63
+    },
+    {
+      "epoch": 0.010924822498306333,
+      "grad_norm": 0.2519175112247467,
+      "learning_rate": 2.195548707539416e-05,
+      "loss": 0.6703,
+      "step": 64
+    },
+    {
+      "epoch": 0.011095522849842368,
+      "grad_norm": 0.21244360506534576,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 0.5964,
+      "step": 65
+    },
+    {
+      "epoch": 0.011266223201378406,
+      "grad_norm": 0.2293308675289154,
+      "learning_rate": 1.966073811036649e-05,
+      "loss": 0.6564,
+      "step": 66
+    },
+    {
+      "epoch": 0.011436923552914442,
+      "grad_norm": 0.18684785068035126,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.6622,
+      "step": 67
+    },
+    {
+      "epoch": 0.011607623904450479,
+      "grad_norm": 0.26187664270401,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6883,
+      "step": 68
+    },
+    {
+      "epoch": 0.011778324255986515,
+      "grad_norm": 0.21371006965637207,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 0.6552,
+      "step": 69
+    },
+    {
+      "epoch": 0.01194902460752255,
+      "grad_norm": 0.2545989453792572,
+      "learning_rate": 1.573767968172413e-05,
+      "loss": 0.7118,
+      "step": 70
+    },
+    {
+      "epoch": 0.012119724959058588,
+      "grad_norm": 0.28586864471435547,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 0.7135,
+      "step": 71
+    },
+    {
+      "epoch": 0.012290425310594624,
+      "grad_norm": 0.23768320679664612,
+      "learning_rate": 1.413355717787134e-05,
+      "loss": 0.694,
+      "step": 72
+    },
+    {
+      "epoch": 0.012461125662130661,
+      "grad_norm": 0.25697755813598633,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6622,
+      "step": 73
+    },
+    {
+      "epoch": 0.012631826013666697,
+      "grad_norm": 0.3061913847923279,
+      "learning_rate": 1.2781389883488218e-05,
+      "loss": 0.6913,
+      "step": 74
+    },
+    {
+      "epoch": 0.012802526365202732,
+      "grad_norm": 0.4278731048107147,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 0.5699,
+      "step": 75
+    },
+    {
+      "epoch": 0.012802526365202732,
+      "eval_loss": 0.6324164271354675,
+      "eval_runtime": 3.5838,
+      "eval_samples_per_second": 13.952,
+      "eval_steps_per_second": 3.627,
+      "step": 75
+    },
+    {
+      "epoch": 0.01297322671673877,
+      "grad_norm": 0.23458966612815857,
+      "learning_rate": 1.168951435958588e-05,
+      "loss": 0.57,
+      "step": 76
+    },
+    {
+      "epoch": 0.013143927068274806,
+      "grad_norm": 0.34405991435050964,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 0.6836,
+      "step": 77
+    },
+    {
+      "epoch": 0.013314627419810843,
+      "grad_norm": 0.19349469244480133,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6502,
+      "step": 78
+    },
+    {
+      "epoch": 0.013485327771346879,
+      "grad_norm": 0.20770883560180664,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 0.6849,
+      "step": 79
+    },
+    {
+      "epoch": 0.013656028122882916,
+      "grad_norm": 0.2296224683523178,
+      "learning_rate": 1.0311919437028318e-05,
+      "loss": 0.6785,
+      "step": 80
+    },
+    {
+      "epoch": 0.013826728474418952,
+      "grad_norm": 0.2047092616558075,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 0.6602,
+      "step": 81
+    },
+    {
+      "epoch": 0.013997428825954988,
+      "grad_norm": 0.2236960083246231,
+      "learning_rate": 1.003469336916747e-05,
+      "loss": 0.6941,
+      "step": 82
+    },
+    {
+      "epoch": 0.014168129177491025,
+      "grad_norm": 0.2223822921514511,
+      "learning_rate": 1e-05,
+      "loss": 0.6962,
+      "step": 83
     }
   ],
   "logging_steps": 1,
@@ -404,12 +643,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.980206280621425e+17,
+  "total_flos": 9.921006493174333e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null