Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b34806b80e567e22296ba77224e7eb2bfd31df6a09d138388d6757b6f8e7fea
+oid sha256:8671ccc4a22e3305d727bd5b224745cea53ac70c0bcea9bceeabe9fada8eca9a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5c00d494dc15eb05d7ed9168cec71e9521d03aeb4b9db128b2fadb5a204abb
+oid sha256:8e1796813608adcc21b1c3a8f4e70078c282815ed6b5b92b0400347bdea25fac
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70804066f1e7229d3bc6f7e6ab2d03d8691e2800aca531e462c517d195247433
+oid sha256:3a26781fed6dcf1c60fc02672868528e76521e1f0ee9bbf4ec864ba7b0fe8d60
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483bf6cc4bcdb51f59fd06d673ee7c2b9d3859a4c4305aa7bee26ec991db429f
+oid sha256:81397047f0a6c5b8e9022a61343106ddaf9576d5a3b7931b74424d55edeaf51b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e73a405f59038f9cb1f6b36382ac7d9f81d0bbe03f68083095c8f6249e1139
+oid sha256:fa4850d7637643b2e9ab5c789be1d20898767a729523c66fce154c1cdec49a97
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7df947eb6302c641b9e4a6251e4dcfc47ec8198af43d7c32c34079a63940c4b
+oid sha256:4fda56787dc89111adb1b84df426c05a941391f692cff43671adc16afddce667
 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": 0.049961287528276443,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.36363636363636365,
+  "best_metric": 0.046489227563142776,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7272727272727273,
   "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": 23.354,
       "eval_steps_per_second": 2.919,
       "step": 25
+    },
+    {
+      "epoch": 0.3781818181818182,
+      "grad_norm": 1.5513335466384888,
+      "learning_rate": 5e-05,
+      "loss": 0.418,
+      "step": 26
+    },
+    {
+      "epoch": 0.3927272727272727,
+      "grad_norm": 1.1485812664031982,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.523,
+      "step": 27
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 1.2391613721847534,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5771,
+      "step": 28
+    },
+    {
+      "epoch": 0.4218181818181818,
+      "grad_norm": 1.317054033279419,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6581,
+      "step": 29
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 1.6672873497009277,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7339,
+      "step": 30
+    },
+    {
+      "epoch": 0.4509090909090909,
+      "grad_norm": 1.7663410902023315,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8093,
+      "step": 31
+    },
+    {
+      "epoch": 0.46545454545454545,
+      "grad_norm": 1.8384978771209717,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8133,
+      "step": 32
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.6507760286331177,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8096,
+      "step": 33
+    },
+    {
+      "epoch": 0.49454545454545457,
+      "grad_norm": 1.973745584487915,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9453,
+      "step": 34
+    },
+    {
+      "epoch": 0.509090909090909,
+      "grad_norm": 2.1544129848480225,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9739,
+      "step": 35
+    },
+    {
+      "epoch": 0.5236363636363637,
+      "grad_norm": 2.3645403385162354,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0393,
+      "step": 36
+    },
+    {
+      "epoch": 0.5381818181818182,
+      "grad_norm": 2.7798073291778564,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2032,
+      "step": 37
+    },
+    {
+      "epoch": 0.5527272727272727,
+      "grad_norm": 2.2902143001556396,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8116,
+      "step": 38
+    },
+    {
+      "epoch": 0.5672727272727273,
+      "grad_norm": 1.0294620990753174,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4392,
+      "step": 39
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 1.2548834085464478,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5312,
+      "step": 40
+    },
+    {
+      "epoch": 0.5963636363636363,
+      "grad_norm": 1.2893308401107788,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5329,
+      "step": 41
+    },
+    {
+      "epoch": 0.610909090909091,
+      "grad_norm": 1.4130041599273682,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6743,
+      "step": 42
+    },
+    {
+      "epoch": 0.6254545454545455,
+      "grad_norm": 1.6451098918914795,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8124,
+      "step": 43
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6494089365005493,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8184,
+      "step": 44
+    },
+    {
+      "epoch": 0.6545454545454545,
+      "grad_norm": 1.5135403871536255,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6655,
+      "step": 45
+    },
+    {
+      "epoch": 0.6690909090909091,
+      "grad_norm": 1.7748284339904785,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9069,
+      "step": 46
+    },
+    {
+      "epoch": 0.6836363636363636,
+      "grad_norm": 1.7287698984146118,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.879,
+      "step": 47
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 1.8177392482757568,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9566,
+      "step": 48
+    },
+    {
+      "epoch": 0.7127272727272728,
+      "grad_norm": 2.316375732421875,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0862,
+      "step": 49
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 3.1790921688079834,
+      "learning_rate": 0.0,
+      "loss": 1.3497,
+      "step": 50
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "eval_loss": 0.046489227563142776,
+      "eval_runtime": 19.4744,
+      "eval_samples_per_second": 23.826,
+      "eval_steps_per_second": 2.978,
+      "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": 4.515808286657741e+17,
+  "total_flos": 8.994485807947448e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null