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:b01df03d9370143ccb32929c12164d31d3dd52db07a63e691b6c34557d3c2c1c
+oid sha256:7455d33dab36e9ea399749ee3a895c3db3631d476e8bebe2c7a56adad30c07a6
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493ec82ad1e00b15f6c81b84743cbeff233cf150befcef87e0ca2694c10ef31e
+oid sha256:1b1cdcc17c61425ea2b78a54ac8a7c985e07e59f160f109d9dddebac62209b40
 size 226735226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce904ffc17c717facaefc2ec7d34ff8bc86da09c1df60734bd9f6195dee0af6d
+oid sha256:39bc93c1b424320a71c637c636811049fce5dbfdc11d710f42a57b8f47441c41
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a7a41e2dfbc24dcef07e045a6f6df0f7c4c8a5e933099ec7cc0696d3775120
+oid sha256:0bcbd9875d72c15713b2ca536701d2e7509bcc8940913e37409392569efdddf1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10291748089314c7b40b53285254483034523adc413aa1a951562140fb8aeee
+oid sha256:12f9528ace3329f704d2a0d7fe72d2665367988ca2b76a40fd147ebb8afc44e7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34829c8dd542d17644d1c5baf0108bdbeb7f74020cafe189cf098787b61ddb1b
+oid sha256:5d3bf8f03d3ac8c9ce7caf3ed884279c702a5daec397352986c2d323babd0105
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1881874054670334,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006544020809986176,
+  "best_metric": 0.11451411992311478,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013088041619972351,
   "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": 25.295,
       "eval_steps_per_second": 6.577,
       "step": 25
+    },
+    {
+      "epoch": 0.0068057816423856225,
+      "grad_norm": 5.67341423034668,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4068,
+      "step": 26
+    },
+    {
+      "epoch": 0.00706754247478507,
+      "grad_norm": 3.0895113945007324,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.2435,
+      "step": 27
+    },
+    {
+      "epoch": 0.007329303307184517,
+      "grad_norm": 1.4776486158370972,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1991,
+      "step": 28
+    },
+    {
+      "epoch": 0.007591064139583964,
+      "grad_norm": 0.6345441341400146,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1249,
+      "step": 29
+    },
+    {
+      "epoch": 0.007852824971983412,
+      "grad_norm": 1.7844918966293335,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2232,
+      "step": 30
+    },
+    {
+      "epoch": 0.008114585804382858,
+      "grad_norm": 2.8927695751190186,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1696,
+      "step": 31
+    },
+    {
+      "epoch": 0.008376346636782305,
+      "grad_norm": 2.8414504528045654,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1395,
+      "step": 32
+    },
+    {
+      "epoch": 0.008638107469181752,
+      "grad_norm": 1.5258004665374756,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0917,
+      "step": 33
+    },
+    {
+      "epoch": 0.0088998683015812,
+      "grad_norm": 0.6212219595909119,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0516,
+      "step": 34
+    },
+    {
+      "epoch": 0.009161629133980645,
+      "grad_norm": 0.23419176042079926,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0359,
+      "step": 35
+    },
+    {
+      "epoch": 0.009423389966380093,
+      "grad_norm": 0.5231649279594421,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0743,
+      "step": 36
+    },
+    {
+      "epoch": 0.00968515079877954,
+      "grad_norm": 0.6994382739067078,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0664,
+      "step": 37
+    },
+    {
+      "epoch": 0.009946911631178987,
+      "grad_norm": 1.0030083656311035,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.252,
+      "step": 38
+    },
+    {
+      "epoch": 0.010208672463578435,
+      "grad_norm": 1.226110577583313,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2104,
+      "step": 39
+    },
+    {
+      "epoch": 0.01047043329597788,
+      "grad_norm": 1.3695590496063232,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1364,
+      "step": 40
+    },
+    {
+      "epoch": 0.010732194128377328,
+      "grad_norm": 0.5650397539138794,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1441,
+      "step": 41
+    },
+    {
+      "epoch": 0.010993954960776776,
+      "grad_norm": 0.5469205975532532,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1786,
+      "step": 42
+    },
+    {
+      "epoch": 0.011255715793176222,
+      "grad_norm": 0.5554198026657104,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1201,
+      "step": 43
+    },
+    {
+      "epoch": 0.01151747662557567,
+      "grad_norm": 0.9979183077812195,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1336,
+      "step": 44
+    },
+    {
+      "epoch": 0.011779237457975116,
+      "grad_norm": 0.17333826422691345,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0317,
+      "step": 45
+    },
+    {
+      "epoch": 0.012040998290374564,
+      "grad_norm": 0.44120076298713684,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0867,
+      "step": 46
+    },
+    {
+      "epoch": 0.01230275912277401,
+      "grad_norm": 0.700712263584137,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1132,
+      "step": 47
+    },
+    {
+      "epoch": 0.012564519955173457,
+      "grad_norm": 0.21309413015842438,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0381,
+      "step": 48
+    },
+    {
+      "epoch": 0.012826280787572905,
+      "grad_norm": 0.19383953511714935,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0265,
+      "step": 49
+    },
+    {
+      "epoch": 0.013088041619972351,
+      "grad_norm": 0.8902148604393005,
+      "learning_rate": 1e-05,
+      "loss": 0.2106,
+      "step": 50
+    },
+    {
+      "epoch": 0.013088041619972351,
+      "eval_loss": 0.11451411992311478,
+      "eval_runtime": 1.9751,
+      "eval_samples_per_second": 25.315,
+      "eval_steps_per_second": 6.582,
+      "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": 5.277524789978726e+16,
+  "total_flos": 1.0553400876230246e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null