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:a5ad6cb6cbe104310494bbf3da5732a40f4f01215d698d693a0ca518859e736e
+oid sha256:336349cdda9e552594efc596c1c8c81093535034cd5326ae7a1e5db7112ab287
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613a3aa309e6850faa4fbe254524545581a8c30f07dd2fffcef85981fec1ac40
+oid sha256:05004a8fd6e5f98efaa8a79a7d4622594f30d45b1bf1d3f70017f28510d85e83
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3981afc63daf71086abaa6c47bae987d820db809f08e70453a8f5bad49b3d9bc
+oid sha256:1efca72e85f47c3412b8269c01893c0997c89bff5c55003771da72332cf48b74
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf24768151772e316495d2e41ac860bcab8b4932aabb4b7a4c85d6004f4edcc
+oid sha256:a4841180974da24cb0c9ce1a2ad169bfb90c37460517a3ce06052b09a0edd78d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e983daa0bf767063df502c460b587815ec088620367ed65a8460dfee9ff709
+oid sha256:bce7d20276c64c4aa56a5506733daad4cee09902505287ad9bd79e8ed7cdde7e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb9db4ada4984e87a8acb647388c3507797a86d394cb4f4cef233b1a5f10712
+oid sha256:05f5852112f6eb3a1deba045635ca49b48da54b7aada39a0e15ad89cbccd9bfb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6939069628715515,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08029709926728897,
+  "best_metric": 0.5405478477478027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16059419853457793,
   "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": 99.361,
       "eval_steps_per_second": 25.834,
       "step": 25
+    },
+    {
+      "epoch": 0.08350898323798053,
+      "grad_norm": 13.219664573669434,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 1.18,
+      "step": 26
+    },
+    {
+      "epoch": 0.08672086720867209,
+      "grad_norm": 3.907947301864624,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.8817,
+      "step": 27
+    },
+    {
+      "epoch": 0.08993275117936364,
+      "grad_norm": 2.1503279209136963,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.6689,
+      "step": 28
+    },
+    {
+      "epoch": 0.09314463515005521,
+      "grad_norm": 1.8644012212753296,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.5879,
+      "step": 29
+    },
+    {
+      "epoch": 0.09635651912074676,
+      "grad_norm": 5.081637859344482,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.6628,
+      "step": 30
+    },
+    {
+      "epoch": 0.09956840309143832,
+      "grad_norm": 1.9498679637908936,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.4971,
+      "step": 31
+    },
+    {
+      "epoch": 0.10278028706212988,
+      "grad_norm": 1.7911735773086548,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.5756,
+      "step": 32
+    },
+    {
+      "epoch": 0.10599217103282144,
+      "grad_norm": 5.527887344360352,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 1.094,
+      "step": 33
+    },
+    {
+      "epoch": 0.109204055003513,
+      "grad_norm": 1.6801953315734863,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.4828,
+      "step": 34
+    },
+    {
+      "epoch": 0.11241593897420456,
+      "grad_norm": 2.1924173831939697,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.3928,
+      "step": 35
+    },
+    {
+      "epoch": 0.11562782294489611,
+      "grad_norm": 2.8271541595458984,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.3965,
+      "step": 36
+    },
+    {
+      "epoch": 0.11883970691558768,
+      "grad_norm": 1.9707531929016113,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.3363,
+      "step": 37
+    },
+    {
+      "epoch": 0.12205159088627923,
+      "grad_norm": 2.6084580421447754,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.5723,
+      "step": 38
+    },
+    {
+      "epoch": 0.12526347485697079,
+      "grad_norm": 2.948139190673828,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.7208,
+      "step": 39
+    },
+    {
+      "epoch": 0.12847535882766234,
+      "grad_norm": 3.0574727058410645,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.5781,
+      "step": 40
+    },
+    {
+      "epoch": 0.13168724279835392,
+      "grad_norm": 2.222038984298706,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.466,
+      "step": 41
+    },
+    {
+      "epoch": 0.13489912676904547,
+      "grad_norm": 1.6518263816833496,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.3927,
+      "step": 42
+    },
+    {
+      "epoch": 0.13811101073973703,
+      "grad_norm": 2.6922054290771484,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.5703,
+      "step": 43
+    },
+    {
+      "epoch": 0.14132289471042858,
+      "grad_norm": 2.6648433208465576,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.5503,
+      "step": 44
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 2.1673121452331543,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.7952,
+      "step": 45
+    },
+    {
+      "epoch": 0.14774666265181172,
+      "grad_norm": 3.4408926963806152,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.6431,
+      "step": 46
+    },
+    {
+      "epoch": 0.15095854662250327,
+      "grad_norm": 2.1872146129608154,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.4239,
+      "step": 47
+    },
+    {
+      "epoch": 0.15417043059319482,
+      "grad_norm": 1.5436232089996338,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.4114,
+      "step": 48
+    },
+    {
+      "epoch": 0.15738231456388638,
+      "grad_norm": 1.8399603366851807,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.3185,
+      "step": 49
+    },
+    {
+      "epoch": 0.16059419853457793,
+      "grad_norm": 2.190896987915039,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.2297,
+      "step": 50
+    },
+    {
+      "epoch": 0.16059419853457793,
+      "eval_loss": 0.5405478477478027,
+      "eval_runtime": 0.5041,
+      "eval_samples_per_second": 99.187,
+      "eval_steps_per_second": 25.789,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null