Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf77cb4ff4081a992fcf1dae69c126e806763557a75008415a70e77c97cc5696
+oid sha256:b65ee7cf6d8c97ea4ee9843b0cae16809eac5c0c505f3dd03de60e375e4d1df4
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9be606d592580935ac71d7bbcd9dca72cdb42d5875144e12418a79ac45172e
+oid sha256:b3b4fcdad32b16acade432b8220d715dfa0da9b091d98cde05df0e539b747bf3
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0656e9afd23988e47c65b323e07581be25b21ac41767c4c71d73b44d12051a45
+oid sha256:f93292737c9b3622781f965f35a1be3c2a3bda5386bf87bfe6d4bc7d9d491b19
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d21664c9d5f8dfeaf6f6dc45ce8b272694b2a8b336da2db1358ab7398d1b9b20
+oid sha256:1075063a001cbce989cccb281b55bdeaab184047442a2dd05cab5e22a44c3b07
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ab66591a435956440f940ed333bc8f4242131d343a362510cf590c99bcec05
+oid sha256:a69861c3d0c9a6632cd5a6f4bceaff58950404a3717eec316019121e7fa91e20
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb53ff07a9146960fd3083194be8a315712ffa16c26a6fbeb7dd1024158da0f
+oid sha256:cf910f9a1e2934289c6dd4501453de890a6520226fec3f01ec4b1241dc9401ab
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370cee31176b8bff781da8f054b9870dc93c63a8623674218a84718aa7abd3af
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6430225968360901,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.48115477145148355,
+  "best_metric": 0.642619788646698,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.6415396952686447,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 81.594,
       "eval_steps_per_second": 21.214,
       "step": 75
+    },
+    {
+      "epoch": 0.48757016840417,
+      "grad_norm": 0.4953598082065582,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6817,
+      "step": 76
+    },
+    {
+      "epoch": 0.49398556535685645,
+      "grad_norm": 0.4927740693092346,
+      "learning_rate": 2.215611672859741e-05,
+      "loss": 0.682,
+      "step": 77
+    },
+    {
+      "epoch": 0.5004009623095429,
+      "grad_norm": 0.43795329332351685,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6808,
+      "step": 78
+    },
+    {
+      "epoch": 0.5068163592622293,
+      "grad_norm": 0.3758513331413269,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.6739,
+      "step": 79
+    },
+    {
+      "epoch": 0.5132317562149158,
+      "grad_norm": 0.36797139048576355,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6806,
+      "step": 80
+    },
+    {
+      "epoch": 0.5196471531676022,
+      "grad_norm": 0.22872480750083923,
+      "learning_rate": 1.842189919337732e-05,
+      "loss": 0.6321,
+      "step": 81
+    },
+    {
+      "epoch": 0.5260625501202887,
+      "grad_norm": 0.3100925087928772,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6276,
+      "step": 82
+    },
+    {
+      "epoch": 0.5324779470729751,
+      "grad_norm": 0.2795657515525818,
+      "learning_rate": 1.6785901831303956e-05,
+      "loss": 0.6272,
+      "step": 83
+    },
+    {
+      "epoch": 0.5388933440256616,
+      "grad_norm": 0.2867531180381775,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6252,
+      "step": 84
+    },
+    {
+      "epoch": 0.545308740978348,
+      "grad_norm": 0.2775162160396576,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.6234,
+      "step": 85
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.28582143783569336,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6208,
+      "step": 86
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.2738381624221802,
+      "learning_rate": 1.4011127878547087e-05,
+      "loss": 0.621,
+      "step": 87
+    },
+    {
+      "epoch": 0.5645549318364074,
+      "grad_norm": 0.3022683262825012,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6623,
+      "step": 88
+    },
+    {
+      "epoch": 0.5709703287890938,
+      "grad_norm": 0.47619500756263733,
+      "learning_rate": 1.2884233295920353e-05,
+      "loss": 0.6799,
+      "step": 89
+    },
+    {
+      "epoch": 0.5773857257417803,
+      "grad_norm": 0.4414108395576477,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6761,
+      "step": 90
+    },
+    {
+      "epoch": 0.5838011226944667,
+      "grad_norm": 0.33427977561950684,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.674,
+      "step": 91
+    },
+    {
+      "epoch": 0.5902165196471532,
+      "grad_norm": 0.34479114413261414,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6744,
+      "step": 92
+    },
+    {
+      "epoch": 0.5966319165998396,
+      "grad_norm": 0.2519044280052185,
+      "learning_rate": 1.1175535932519987e-05,
+      "loss": 0.6564,
+      "step": 93
+    },
+    {
+      "epoch": 0.603047313552526,
+      "grad_norm": 0.30342552065849304,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6273,
+      "step": 94
+    },
+    {
+      "epoch": 0.6094627105052125,
+      "grad_norm": 0.3491989076137543,
+      "learning_rate": 1.0601050056180447e-05,
+      "loss": 0.6293,
+      "step": 95
+    },
+    {
+      "epoch": 0.615878107457899,
+      "grad_norm": 0.3126583695411682,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6279,
+      "step": 96
+    },
+    {
+      "epoch": 0.6222935044105854,
+      "grad_norm": 0.3132149279117584,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.6209,
+      "step": 97
+    },
+    {
+      "epoch": 0.6287089013632718,
+      "grad_norm": 0.30020031332969666,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6219,
+      "step": 98
+    },
+    {
+      "epoch": 0.6351242983159583,
+      "grad_norm": 0.30071163177490234,
+      "learning_rate": 1.0024093563563546e-05,
+      "loss": 0.6271,
+      "step": 99
+    },
+    {
+      "epoch": 0.6415396952686447,
+      "grad_norm": 0.28551459312438965,
+      "learning_rate": 1e-05,
+      "loss": 0.6224,
+      "step": 100
+    },
+    {
+      "epoch": 0.6415396952686447,
+      "eval_loss": 0.642619788646698,
+      "eval_runtime": 0.6069,
+      "eval_samples_per_second": 82.392,
+      "eval_steps_per_second": 21.422,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.81668108009472e+16,
+  "total_flos": 5.08890810679296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null