Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0b11a979d278cd185e38fd06a1c4bcc5b9d2be8f9c57b4838af5d2b55c702b
+oid sha256:d80006bfd04c516b7c9046a22d32e8ac108f5347457f27826bd669d988fa8aa6
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b22809f3d97c508a1b402ca9edd85270c1ba52bd9da6a1e000959afb3ba09ba
+oid sha256:563292bd2f32b9e12df8bdde51b1d70c2415fb35a45ad019fa442e51157a45b3
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d694e21b6cc85047400680dffd2aae59e81bc693a406d97374cd034ded33506b
+oid sha256:7ac0e1091dae3273e9ff1fe7598303ccaf9cfd05a2912c25fa9f9e692426376d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fbda9c3d5a48c1412117b19424b3371348fef42c2f9af57cf16d942b4bd7b5
+oid sha256:c122c65ae9fe2f6a7f031a4e0d48177f4caba3f064865cab1df5388d54274f43
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec668fa8fd5177a84abfd6543642c1c754636a362a6a739684f5f8904a05ef5
+oid sha256:16ea90988538ffdd50a5b8e4e9ec014ca3b155b1e519369184e48676adca0aa9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c38248b28313f524c1184bd58846d0bf9c602d1a475d0107ae1f7e944748c4e
+oid sha256:fb6dfafda2d3c08b3bc10c47438b84ab65cc9276301d9f326e4132e36b149c96
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.993185520172119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.1188001188001188,
+  "best_metric": 3.924217939376831,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.1782001782001782,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 107.981,
       "eval_steps_per_second": 28.075,
       "step": 50
+    },
+    {
+      "epoch": 0.12117612117612117,
+      "grad_norm": 2.3711788654327393,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.7217,
+      "step": 51
+    },
+    {
+      "epoch": 0.12355212355212356,
+      "grad_norm": 2.324312686920166,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 3.7561,
+      "step": 52
+    },
+    {
+      "epoch": 0.12592812592812594,
+      "grad_norm": 2.2597808837890625,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 3.9246,
+      "step": 53
+    },
+    {
+      "epoch": 0.1283041283041283,
+      "grad_norm": 2.233111619949341,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.9591,
+      "step": 54
+    },
+    {
+      "epoch": 0.13068013068013068,
+      "grad_norm": 2.11525559425354,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 4.0181,
+      "step": 55
+    },
+    {
+      "epoch": 0.13305613305613306,
+      "grad_norm": 2.1554830074310303,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 4.0492,
+      "step": 56
+    },
+    {
+      "epoch": 0.13543213543213542,
+      "grad_norm": 2.260748863220215,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.096,
+      "step": 57
+    },
+    {
+      "epoch": 0.1378081378081378,
+      "grad_norm": 2.5770089626312256,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 4.1185,
+      "step": 58
+    },
+    {
+      "epoch": 0.1401841401841402,
+      "grad_norm": 2.5284464359283447,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 4.2158,
+      "step": 59
+    },
+    {
+      "epoch": 0.14256014256014257,
+      "grad_norm": 2.5339860916137695,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.3166,
+      "step": 60
+    },
+    {
+      "epoch": 0.14493614493614493,
+      "grad_norm": 3.2956223487854004,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 4.51,
+      "step": 61
+    },
+    {
+      "epoch": 0.1473121473121473,
+      "grad_norm": 3.547050952911377,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 4.6738,
+      "step": 62
+    },
+    {
+      "epoch": 0.1496881496881497,
+      "grad_norm": 2.2729122638702393,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.1461,
+      "step": 63
+    },
+    {
+      "epoch": 0.15206415206415205,
+      "grad_norm": 2.3304686546325684,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 3.7979,
+      "step": 64
+    },
+    {
+      "epoch": 0.15444015444015444,
+      "grad_norm": 2.1547152996063232,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 3.7298,
+      "step": 65
+    },
+    {
+      "epoch": 0.15681615681615682,
+      "grad_norm": 2.1138386726379395,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.9149,
+      "step": 66
+    },
+    {
+      "epoch": 0.1591921591921592,
+      "grad_norm": 2.197359561920166,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 3.9229,
+      "step": 67
+    },
+    {
+      "epoch": 0.16156816156816156,
+      "grad_norm": 2.0438430309295654,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 3.9128,
+      "step": 68
+    },
+    {
+      "epoch": 0.16394416394416395,
+      "grad_norm": 2.085602045059204,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0383,
+      "step": 69
+    },
+    {
+      "epoch": 0.16632016632016633,
+      "grad_norm": 2.3776140213012695,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 3.9447,
+      "step": 70
+    },
+    {
+      "epoch": 0.16869616869616869,
+      "grad_norm": 2.2178096771240234,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 4.0903,
+      "step": 71
+    },
+    {
+      "epoch": 0.17107217107217107,
+      "grad_norm": 2.8414366245269775,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.2017,
+      "step": 72
+    },
+    {
+      "epoch": 0.17344817344817345,
+      "grad_norm": 2.834662914276123,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 4.3855,
+      "step": 73
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 3.376075267791748,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 4.5297,
+      "step": 74
+    },
+    {
+      "epoch": 0.1782001782001782,
+      "grad_norm": 4.6905436515808105,
+      "learning_rate": 1e-05,
+      "loss": 5.0961,
+      "step": 75
+    },
+    {
+      "epoch": 0.1782001782001782,
+      "eval_loss": 3.924217939376831,
+      "eval_runtime": 0.4633,
+      "eval_samples_per_second": 107.912,
+      "eval_steps_per_second": 28.057,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.83042868150272e+16,
+  "total_flos": 1.174564302225408e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null