Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2b974c8aaae9993fa7232cb1d78d6251a8efac86c5b3b380dc6f7860c362c8
+oid sha256:a4f51aba38fbb687748ac5042c5a60c1fce0e2e25b5e45ad4416dc383f87e4ec
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beea50613ad5594cd06076286779b028cb4c392a9448527a808adc8d28ccc990
+oid sha256:d52ccb04aab0ad0add93256b1b74bb5a1eba075dd15d72076cf0a29573c7869e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae155a72e67e21c68cc816efca7431cdd2690c32a05617f92b637717cb81c41e
+oid sha256:a1fc44cc208a466bc4dcaa69da51f02a9e5fd3978412dabd4e960fabe6f246d1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459df844445411b69d2c05c6bb7f8f44abacca8b1d20edf27eb459e7975e9b41
+oid sha256:fa0dc5592bce2403cda6988c46ecb245ff8ec91767808f912239f36053f7a11b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca813d4adb3c06b1b29f37ad6e8a8ac22072f7328f36c1742a3514675a9d45e
+oid sha256:13087c6f6957687b834c3aadcbbadf54ece494f6a3e82baa76bd26261d1e9584
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ad2eb2428e3a1ca6cc383ae3d7d6449f048c27f74830e45f1270fe3ed53d4d
+oid sha256:b71289905a06753a4d6d57d35fd19f47296fc4d186cc1f0e02b9e19ff1e84005
 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": 0.9366852045059204,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4652014652014653,
+  "best_metric": 0.9223546385765076,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.9304029304029307,
   "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": 14.813,
       "eval_steps_per_second": 1.932,
       "step": 25
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 32.0912971496582,
+      "learning_rate": 5e-05,
+      "loss": 0.821,
+      "step": 26
+    },
+    {
+      "epoch": 1.5824175824175826,
+      "grad_norm": 30.892793655395508,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8939,
+      "step": 27
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 28.635496139526367,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8442,
+      "step": 28
+    },
+    {
+      "epoch": 1.6996336996336996,
+      "grad_norm": 28.831605911254883,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7968,
+      "step": 29
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 29.72295570373535,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8014,
+      "step": 30
+    },
+    {
+      "epoch": 1.8168498168498168,
+      "grad_norm": 32.9221076965332,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8923,
+      "step": 31
+    },
+    {
+      "epoch": 1.8754578754578755,
+      "grad_norm": 30.689712524414062,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8141,
+      "step": 32
+    },
+    {
+      "epoch": 1.934065934065934,
+      "grad_norm": 28.754140853881836,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8102,
+      "step": 33
+    },
+    {
+      "epoch": 1.9926739926739927,
+      "grad_norm": 26.2111759185791,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7266,
+      "step": 34
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 29.376527786254883,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8551,
+      "step": 35
+    },
+    {
+      "epoch": 2.10989010989011,
+      "grad_norm": 28.342126846313477,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8365,
+      "step": 36
+    },
+    {
+      "epoch": 2.1684981684981683,
+      "grad_norm": 28.068082809448242,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8089,
+      "step": 37
+    },
+    {
+      "epoch": 2.227106227106227,
+      "grad_norm": 26.8826904296875,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7149,
+      "step": 38
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 33.95366668701172,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7723,
+      "step": 39
+    },
+    {
+      "epoch": 2.3443223443223444,
+      "grad_norm": 29.23862075805664,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8039,
+      "step": 40
+    },
+    {
+      "epoch": 2.402930402930403,
+      "grad_norm": 24.6160831451416,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7711,
+      "step": 41
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 25.017553329467773,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.703,
+      "step": 42
+    },
+    {
+      "epoch": 2.52014652014652,
+      "grad_norm": 28.609981536865234,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7448,
+      "step": 43
+    },
+    {
+      "epoch": 2.578754578754579,
+      "grad_norm": 29.547321319580078,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8256,
+      "step": 44
+    },
+    {
+      "epoch": 2.6373626373626373,
+      "grad_norm": 26.95943832397461,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7883,
+      "step": 45
+    },
+    {
+      "epoch": 2.695970695970696,
+      "grad_norm": 27.201311111450195,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7294,
+      "step": 46
+    },
+    {
+      "epoch": 2.7545787545787546,
+      "grad_norm": 24.49020767211914,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.704,
+      "step": 47
+    },
+    {
+      "epoch": 2.813186813186813,
+      "grad_norm": 32.30080032348633,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8153,
+      "step": 48
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 30.446308135986328,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8346,
+      "step": 49
+    },
+    {
+      "epoch": 2.9304029304029307,
+      "grad_norm": 23.781755447387695,
+      "learning_rate": 0.0,
+      "loss": 0.7575,
+      "step": 50
+    },
+    {
+      "epoch": 2.9304029304029307,
+      "eval_loss": 0.9223546385765076,
+      "eval_runtime": 7.7692,
+      "eval_samples_per_second": 14.802,
+      "eval_steps_per_second": 1.931,
+      "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": 2.8426299460131226e+17,
+  "total_flos": 5.681722084514857e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null