Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f813160edf37de77f48a9412770a2dbba38f3e2fc356650c15e864092e65f5
+oid sha256:219a0b0a25ca8ff29b7e0d9d76e56abc40bf8b0ce687476521a5b966f08c7455
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3261cb2b187247e8ccb5c5b0a6399dbf3ce4cd91514569743e1e9e5097dd2c29
+oid sha256:5c020b61206ebe3afcb1846c55340c9763030ac1b4e2e1e5f402d587ed4831bd
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af370fd02f3990e26aaa0ddd8f763858ca177f87eb40f6415f77c96809d0bf95
+oid sha256:8a75bdda6db4dec3917713711e947f06f3f0031fe4de09776a7142118bb7033b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34fc726612eb08456229bd9a5ea313b3c723c4c0857a5a4322b3cbfe6a18a884
+oid sha256:7079ce2aa07dd3bfce74825c8cb943cca858af5f055452c622a65e4319cf20c7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a1587d1be63a638f65c76104c5d1592d6f9f7603b4b9eadf45c6f25de19a18
+oid sha256:5753fbccc12f56e5d829a30421452c9ed35db879f218cc042985eaf9d85b72cf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e563a5f6378684ebe07e298ee198dfde8c0bd21bf4160f005329cb556544c6a4
+oid sha256:8152a9ccfdaaa67f9888dada6c4c70056af8ffe083e7d8425a889da33a524820
 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": 0.8185063600540161,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2183406113537118,
+  "best_metric": 0.8061870336532593,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4366812227074236,
   "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": 14.703,
       "eval_steps_per_second": 1.847,
       "step": 25
+    },
+    {
+      "epoch": 0.22707423580786026,
+      "grad_norm": 1.7064659595489502,
+      "learning_rate": 5e-05,
+      "loss": 0.8381,
+      "step": 26
+    },
+    {
+      "epoch": 0.23580786026200873,
+      "grad_norm": 1.4659017324447632,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8363,
+      "step": 27
+    },
+    {
+      "epoch": 0.2445414847161572,
+      "grad_norm": 1.1928423643112183,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8347,
+      "step": 28
+    },
+    {
+      "epoch": 0.25327510917030566,
+      "grad_norm": 0.5484209656715393,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8144,
+      "step": 29
+    },
+    {
+      "epoch": 0.26200873362445415,
+      "grad_norm": 0.43038228154182434,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8166,
+      "step": 30
+    },
+    {
+      "epoch": 0.27074235807860264,
+      "grad_norm": 0.3309982717037201,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8088,
+      "step": 31
+    },
+    {
+      "epoch": 0.2794759825327511,
+      "grad_norm": 0.9024494290351868,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8146,
+      "step": 32
+    },
+    {
+      "epoch": 0.28820960698689957,
+      "grad_norm": 0.295159250497818,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8075,
+      "step": 33
+    },
+    {
+      "epoch": 0.29694323144104806,
+      "grad_norm": 0.48754653334617615,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8115,
+      "step": 34
+    },
+    {
+      "epoch": 0.3056768558951965,
+      "grad_norm": 0.673410952091217,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8127,
+      "step": 35
+    },
+    {
+      "epoch": 0.314410480349345,
+      "grad_norm": 0.37311244010925293,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7991,
+      "step": 36
+    },
+    {
+      "epoch": 0.3231441048034934,
+      "grad_norm": 0.2106884866952896,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8031,
+      "step": 37
+    },
+    {
+      "epoch": 0.3318777292576419,
+      "grad_norm": 0.41157469153404236,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8116,
+      "step": 38
+    },
+    {
+      "epoch": 0.3406113537117904,
+      "grad_norm": 0.3884178102016449,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.811,
+      "step": 39
+    },
+    {
+      "epoch": 0.34934497816593885,
+      "grad_norm": 0.6447245478630066,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8133,
+      "step": 40
+    },
+    {
+      "epoch": 0.35807860262008734,
+      "grad_norm": 0.4535675048828125,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8094,
+      "step": 41
+    },
+    {
+      "epoch": 0.36681222707423583,
+      "grad_norm": 0.4354056119918823,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8063,
+      "step": 42
+    },
+    {
+      "epoch": 0.37554585152838427,
+      "grad_norm": 0.40337520837783813,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.808,
+      "step": 43
+    },
+    {
+      "epoch": 0.38427947598253276,
+      "grad_norm": 0.313003808259964,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8062,
+      "step": 44
+    },
+    {
+      "epoch": 0.3930131004366812,
+      "grad_norm": 0.48915451765060425,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8036,
+      "step": 45
+    },
+    {
+      "epoch": 0.4017467248908297,
+      "grad_norm": 0.260262668132782,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8076,
+      "step": 46
+    },
+    {
+      "epoch": 0.4104803493449782,
+      "grad_norm": 0.558372974395752,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.813,
+      "step": 47
+    },
+    {
+      "epoch": 0.4192139737991266,
+      "grad_norm": 0.6793051362037659,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8055,
+      "step": 48
+    },
+    {
+      "epoch": 0.4279475982532751,
+      "grad_norm": 0.2688404619693756,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8053,
+      "step": 49
+    },
+    {
+      "epoch": 0.4366812227074236,
+      "grad_norm": 0.43385910987854004,
+      "learning_rate": 0.0,
+      "loss": 0.8029,
+      "step": 50
+    },
+    {
+      "epoch": 0.4366812227074236,
+      "eval_loss": 0.8061870336532593,
+      "eval_runtime": 52.4813,
+      "eval_samples_per_second": 14.71,
+      "eval_steps_per_second": 1.848,
+      "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