Training in progress, step 83, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c2d294e85b0ae32deab70c3aa5243cb11c08e1d82d08535ae2e035f16391e0
+oid sha256:efca5ac27a0c8656909a7422ee16335311a7f780e8c61b6d317d60ac53edc071
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae4363572d84b5ed37ece23cab768d11baae80a27e64eb7a0233c8dbedb1084
+oid sha256:e0aa6cc1d46f55508da995acdcb8eb065722938b81e5160de4ea1e1e3d6afec8
 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 sha256:3b75b6145f802aceb9618ccad7b159de053a94ee8d0cde6c3217554c60dafc8d
+oid sha256:4e3c37b6be47040b31f073b29367472651092aec12d5294822a8aad973c54d5a
 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": 0.6395394802093506,
   "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": 13.999,
       "eval_steps_per_second": 3.64,
       "step": 50
+    },
+    {
+      "epoch": 0.008705717928337858,
+      "grad_norm": 0.1751696616411209,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.5759,
+      "step": 51
+    },
+    {
+      "epoch": 0.008876418279873895,
+      "grad_norm": 0.20063109695911407,
+      "learning_rate": 3.942473243151281e-05,
+      "loss": 0.5943,
+      "step": 52
+    },
+    {
+      "epoch": 0.009047118631409931,
+      "grad_norm": 0.21948301792144775,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.657,
+      "step": 53
+    },
+    {
+      "epoch": 0.009217818982945969,
+      "grad_norm": 0.21699479222297668,
+      "learning_rate": 3.616031181081575e-05,
+      "loss": 0.6304,
+      "step": 54
+    },
+    {
+      "epoch": 0.009388519334482004,
+      "grad_norm": 0.24316714704036713,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 0.6608,
+      "step": 55
+    },
+    {
+      "epoch": 0.009559219686018042,
+      "grad_norm": 0.22694571316242218,
+      "learning_rate": 3.301204413263704e-05,
+      "loss": 0.733,
+      "step": 56
+    },
+    {
+      "epoch": 0.009729920037554077,
+      "grad_norm": 0.2339209020137787,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 0.7035,
+      "step": 57
+    },
+    {
+      "epoch": 0.009900620389090113,
+      "grad_norm": 0.2564551532268524,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7208,
+      "step": 58
+    },
+    {
+      "epoch": 0.01007132074062615,
+      "grad_norm": 0.23558856546878815,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 0.6608,
+      "step": 59
+    },
+    {
+      "epoch": 0.010242021092162186,
+      "grad_norm": 0.27021926641464233,
+      "learning_rate": 2.7140772281057468e-05,
+      "loss": 0.7057,
+      "step": 60
+    },
+    {
+      "epoch": 0.010412721443698224,
+      "grad_norm": 0.3034929633140564,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 0.7375,
+      "step": 61
+    },
+    {
+      "epoch": 0.01058342179523426,
+      "grad_norm": 0.35034218430519104,
+      "learning_rate": 2.445396645101762e-05,
+      "loss": 0.6164,
+      "step": 62
+    },
+    {
+      "epoch": 0.010754122146770295,
+      "grad_norm": 0.34496256709098816,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5483,
+      "step": 63
+    },
+    {
+      "epoch": 0.010924822498306333,
+      "grad_norm": 0.222571462392807,
+      "learning_rate": 2.195548707539416e-05,
+      "loss": 0.6643,
+      "step": 64
+    },
+    {
+      "epoch": 0.011095522849842368,
+      "grad_norm": 0.2034004181623459,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 0.5942,
+      "step": 65
+    },
+    {
+      "epoch": 0.011266223201378406,
+      "grad_norm": 0.24817276000976562,
+      "learning_rate": 1.966073811036649e-05,
+      "loss": 0.6528,
+      "step": 66
+    },
+    {
+      "epoch": 0.011436923552914442,
+      "grad_norm": 0.18400932848453522,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.6657,
+      "step": 67
+    },
+    {
+      "epoch": 0.011607623904450479,
+      "grad_norm": 0.2996188998222351,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6882,
+      "step": 68
+    },
+    {
+      "epoch": 0.011778324255986515,
+      "grad_norm": 0.23361016809940338,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 0.6577,
+      "step": 69
+    },
+    {
+      "epoch": 0.01194902460752255,
+      "grad_norm": 0.26406583189964294,
+      "learning_rate": 1.573767968172413e-05,
+      "loss": 0.7139,
+      "step": 70
+    },
+    {
+      "epoch": 0.012119724959058588,
+      "grad_norm": 0.3076748251914978,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 0.7219,
+      "step": 71
+    },
+    {
+      "epoch": 0.012290425310594624,
+      "grad_norm": 0.2459680140018463,
+      "learning_rate": 1.413355717787134e-05,
+      "loss": 0.6901,
+      "step": 72
+    },
+    {
+      "epoch": 0.012461125662130661,
+      "grad_norm": 0.2629689872264862,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6635,
+      "step": 73
+    },
+    {
+      "epoch": 0.012631826013666697,
+      "grad_norm": 0.3097344636917114,
+      "learning_rate": 1.2781389883488218e-05,
+      "loss": 0.6936,
+      "step": 74
+    },
+    {
+      "epoch": 0.012802526365202732,
+      "grad_norm": 0.423374205827713,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 0.5756,
+      "step": 75
+    },
+    {
+      "epoch": 0.012802526365202732,
+      "eval_loss": 0.6261041760444641,
+      "eval_runtime": 3.5774,
+      "eval_samples_per_second": 13.977,
+      "eval_steps_per_second": 3.634,
+      "step": 75
+    },
+    {
+      "epoch": 0.01297322671673877,
+      "grad_norm": 0.25061461329460144,
+      "learning_rate": 1.168951435958588e-05,
+      "loss": 0.5687,
+      "step": 76
+    },
+    {
+      "epoch": 0.013143927068274806,
+      "grad_norm": 0.2536349296569824,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 0.6822,
+      "step": 77
+    },
+    {
+      "epoch": 0.013314627419810843,
+      "grad_norm": 0.1962866485118866,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.649,
+      "step": 78
+    },
+    {
+      "epoch": 0.013485327771346879,
+      "grad_norm": 0.1990254670381546,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 0.6856,
+      "step": 79
+    },
+    {
+      "epoch": 0.013656028122882916,
+      "grad_norm": 0.2070581167936325,
+      "learning_rate": 1.0311919437028318e-05,
+      "loss": 0.6754,
+      "step": 80
+    },
+    {
+      "epoch": 0.013826728474418952,
+      "grad_norm": 0.21576634049415588,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 0.6654,
+      "step": 81
+    },
+    {
+      "epoch": 0.013997428825954988,
+      "grad_norm": 0.2243759036064148,
+      "learning_rate": 1.003469336916747e-05,
+      "loss": 0.6967,
+      "step": 82
+    },
+    {
+      "epoch": 0.014168129177491025,
+      "grad_norm": 0.22119440138339996,
+      "learning_rate": 1e-05,
+      "loss": 0.7006,
+      "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": 5.978341255497646e+17,
+  "total_flos": 9.919141468050555e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null