Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670a6f91511af3816acf3a64c893e884c62c82782f673e93247cd2168125874f
+oid sha256:3ac7bb8f3a71044b1b4da396173aed442d6087be899a50f09b280bb27c7abb3e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7ae8c8afb2d3ea0456d60ccc434f819b53955883009eafb3a6373426ce0f1b
+oid sha256:a1af7a889e88abd247872df9e8d5987c41e2ff8b0d5f97ab7848a8daab785c67
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc3135dce65065978699c9a136d91acb0197a1be5047533426027b5fa846185
+oid sha256:7874f5b50553407db50256d23e2cc28d658d542479d1dc8fa987a78448928a95
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae3d20573a6811f855b751f779997eebbaacf399eb557c85a6a5081fb32017a
+oid sha256:10b18da50fb8cfc74c59806316e017a84bcdb948bab8c147900df2f2de770d86
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc5b679335e7b06e2793cf789cd8d6bdcab2ad372c93ae55534d0d081ef25a9
+oid sha256:2374628fc44f2339115e7b3d06544f42f3e1403c50c9677ce0c4345e1717cf02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576a908b7c6efc3258fe636101e79861daea259b3dddf7e483fe50c126c8e02f
+oid sha256:bb6f1b2a6551be5043cc29896e59b8f58f812ba4521985d3fff6474f6e96eb00
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.129227638244629,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05777841976021956,
+  "best_metric": 2.0215489864349365,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11555683952043912,
   "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": 32.921,
       "eval_steps_per_second": 4.122,
       "step": 25
+    },
+    {
+      "epoch": 0.06008955655062834,
+      "grad_norm": 2.029036521911621,
+      "learning_rate": 5e-05,
+      "loss": 1.7592,
+      "step": 26
+    },
+    {
+      "epoch": 0.06240069334103712,
+      "grad_norm": 1.2845566272735596,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7265,
+      "step": 27
+    },
+    {
+      "epoch": 0.06471183013144591,
+      "grad_norm": 1.540757417678833,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8619,
+      "step": 28
+    },
+    {
+      "epoch": 0.0670229669218547,
+      "grad_norm": 1.925443410873413,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0363,
+      "step": 29
+    },
+    {
+      "epoch": 0.06933410371226346,
+      "grad_norm": 1.3662012815475464,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.963,
+      "step": 30
+    },
+    {
+      "epoch": 0.07164524050267225,
+      "grad_norm": 1.4941176176071167,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7522,
+      "step": 31
+    },
+    {
+      "epoch": 0.07395637729308104,
+      "grad_norm": 1.380921483039856,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8181,
+      "step": 32
+    },
+    {
+      "epoch": 0.07626751408348982,
+      "grad_norm": 0.9916651844978333,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.7789,
+      "step": 33
+    },
+    {
+      "epoch": 0.07857865087389859,
+      "grad_norm": 1.4869825839996338,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8595,
+      "step": 34
+    },
+    {
+      "epoch": 0.08088978766430738,
+      "grad_norm": 1.5238620042800903,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.0914,
+      "step": 35
+    },
+    {
+      "epoch": 0.08320092445471616,
+      "grad_norm": 0.9279425144195557,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1554,
+      "step": 36
+    },
+    {
+      "epoch": 0.08551206124512495,
+      "grad_norm": 1.8256399631500244,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2334,
+      "step": 37
+    },
+    {
+      "epoch": 0.08782319803553373,
+      "grad_norm": 1.595869779586792,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9371,
+      "step": 38
+    },
+    {
+      "epoch": 0.0901343348259425,
+      "grad_norm": 2.3368899822235107,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.729,
+      "step": 39
+    },
+    {
+      "epoch": 0.09244547161635129,
+      "grad_norm": 1.7104312181472778,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7021,
+      "step": 40
+    },
+    {
+      "epoch": 0.09475660840676008,
+      "grad_norm": 1.2494852542877197,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8049,
+      "step": 41
+    },
+    {
+      "epoch": 0.09706774519716886,
+      "grad_norm": 0.9061923623085022,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.956,
+      "step": 42
+    },
+    {
+      "epoch": 0.09937888198757763,
+      "grad_norm": 0.9129108190536499,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.7123,
+      "step": 43
+    },
+    {
+      "epoch": 0.10169001877798642,
+      "grad_norm": 1.039075255393982,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7464,
+      "step": 44
+    },
+    {
+      "epoch": 0.1040011555683952,
+      "grad_norm": 1.1822948455810547,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.8953,
+      "step": 45
+    },
+    {
+      "epoch": 0.10631229235880399,
+      "grad_norm": 1.2711695432662964,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8632,
+      "step": 46
+    },
+    {
+      "epoch": 0.10862342914921277,
+      "grad_norm": 1.3928056955337524,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.9191,
+      "step": 47
+    },
+    {
+      "epoch": 0.11093456593962155,
+      "grad_norm": 1.9826236963272095,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1083,
+      "step": 48
+    },
+    {
+      "epoch": 0.11324570273003033,
+      "grad_norm": 1.459694504737854,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0827,
+      "step": 49
+    },
+    {
+      "epoch": 0.11555683952043912,
+      "grad_norm": 1.7293628454208374,
+      "learning_rate": 0.0,
+      "loss": 2.5267,
+      "step": 50
+    },
+    {
+      "epoch": 0.11555683952043912,
+      "eval_loss": 2.0215489864349365,
+      "eval_runtime": 88.588,
+      "eval_samples_per_second": 32.905,
+      "eval_steps_per_second": 4.12,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null