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:fd0cc0e25bb6f732cd419b0b3a63bec27fffcd9430d40b37ef15420b9079072d
+oid sha256:9852e831c64c6614bf135a085a8f7f5a9ecced977e8f66b41ecd1f61df067d30
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aeceacd5eaa410a0cbcd3ab73950f72b06e77619e0a7932905e30893b0f07f1
+oid sha256:47272a1f1061d87e5317706e22f58deb4ff246e85c03db43fb6bcb831526a55f
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdee0d3b16cc3c96a60f88c6e2a1fe7dbe387f9ec7b9c01c98dd71317828e961
+oid sha256:52d91dd278d807036fbb0c28ae380203eeb1091a0fe03d5c8396a8813e10f8e4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65148d881e952a5e4a0af21147b42b89b958ded7cc797777e5819c1b865bff06
+oid sha256:dc106292be3ecbabc4d1e860dd522d829311b28df039e935eb39034b0811adee
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3774acdffcd2464c07eacc5300f713d3c62c89721fd469494d38729845be3a6b
+oid sha256:41d20dae444fdb305f45770ff3221b1a8480358c0a08ba93fec6614f2922ad6d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18aac741bf8436457d9ed4d68b3e86ca1f5d440f0a09570bb818234512a29fad
+oid sha256:1c6ebdf61f2f7cf13bcee7bf98270f36f38371194282832d3a1a1be71722b68d
 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": 0.5807715058326721,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9950248756218906,
+  "best_metric": 0.5620399713516235,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9900497512437811,
   "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": 15.235,
       "eval_steps_per_second": 1.972,
       "step": 25
+    },
+    {
+      "epoch": 1.0348258706467661,
+      "grad_norm": 0.22895914316177368,
+      "learning_rate": 5e-05,
+      "loss": 1.1264,
+      "step": 26
+    },
+    {
+      "epoch": 1.0746268656716418,
+      "grad_norm": 0.14677956700325012,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5921,
+      "step": 27
+    },
+    {
+      "epoch": 1.1144278606965174,
+      "grad_norm": 0.11105823516845703,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5877,
+      "step": 28
+    },
+    {
+      "epoch": 1.154228855721393,
+      "grad_norm": 0.1271418184041977,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5577,
+      "step": 29
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 0.1278061419725418,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5555,
+      "step": 30
+    },
+    {
+      "epoch": 1.2338308457711442,
+      "grad_norm": 0.14156891405582428,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5235,
+      "step": 31
+    },
+    {
+      "epoch": 1.2736318407960199,
+      "grad_norm": 0.11495278775691986,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5603,
+      "step": 32
+    },
+    {
+      "epoch": 1.3134328358208955,
+      "grad_norm": 0.11897273361682892,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5988,
+      "step": 33
+    },
+    {
+      "epoch": 1.3532338308457712,
+      "grad_norm": 0.12612038850784302,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5884,
+      "step": 34
+    },
+    {
+      "epoch": 1.3930348258706466,
+      "grad_norm": 0.11991294473409653,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5569,
+      "step": 35
+    },
+    {
+      "epoch": 1.4328358208955223,
+      "grad_norm": 0.1252669394016266,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5409,
+      "step": 36
+    },
+    {
+      "epoch": 1.472636815920398,
+      "grad_norm": 0.1387309730052948,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5438,
+      "step": 37
+    },
+    {
+      "epoch": 1.5124378109452736,
+      "grad_norm": 0.1291898936033249,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5205,
+      "step": 38
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 0.12257789820432663,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5969,
+      "step": 39
+    },
+    {
+      "epoch": 1.5920398009950247,
+      "grad_norm": 0.12527777254581451,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.56,
+      "step": 40
+    },
+    {
+      "epoch": 1.6318407960199006,
+      "grad_norm": 0.12541717290878296,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5398,
+      "step": 41
+    },
+    {
+      "epoch": 1.671641791044776,
+      "grad_norm": 0.12988954782485962,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5432,
+      "step": 42
+    },
+    {
+      "epoch": 1.7114427860696517,
+      "grad_norm": 0.13142308592796326,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.553,
+      "step": 43
+    },
+    {
+      "epoch": 1.7512437810945274,
+      "grad_norm": 0.1271471232175827,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4937,
+      "step": 44
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.11726174503564835,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6301,
+      "step": 45
+    },
+    {
+      "epoch": 1.8308457711442787,
+      "grad_norm": 0.12278467416763306,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5612,
+      "step": 46
+    },
+    {
+      "epoch": 1.8706467661691542,
+      "grad_norm": 0.12573637068271637,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5555,
+      "step": 47
+    },
+    {
+      "epoch": 1.9104477611940298,
+      "grad_norm": 0.12766633927822113,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5573,
+      "step": 48
+    },
+    {
+      "epoch": 1.9502487562189055,
+      "grad_norm": 0.14149890840053558,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5547,
+      "step": 49
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "grad_norm": 0.14994728565216064,
+      "learning_rate": 0.0,
+      "loss": 0.4937,
+      "step": 50
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "eval_loss": 0.5620399713516235,
+      "eval_runtime": 11.1558,
+      "eval_samples_per_second": 15.239,
+      "eval_steps_per_second": 1.972,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null