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:fe6b94df64f22a469c816eab0ba7f0f9ab82a64ae4d1a8be279e4170a9cdab88
+oid sha256:f95196d98472cc4099210974140c6ed2117b2e214a111682f54a4a5715c74b61
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92f9dbe65e19b12fbf18086370be51888e91ba31725779df40115d9a9635bd4
+oid sha256:d34c7989622673e914e2a0879394e261d5b6da47ded4990fc2d8829f5e42c5db
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65a62cd480dcb355f4ddb920dfa651c0b25692ffe82371f45205cce396e8c3d
+oid sha256:64e8a2500182389a360c530c9e234d82cd7e024dcf44c158f58cc16541339819
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0712230e589ea2c46338cd050a8e4e013fde0ac38fea8453e353a1dcf3a4695e
+oid sha256:b9e80790c3e6d4a119e412fdf9a0b7ef672f728faa7f82106f9d209da516e361
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020c61742962acae55fc64ffae83fc714d16ec5ced5f1e518b24dc811588ff7a
+oid sha256:7cd44c5b38a7cacb5c46f5f29f20e774d86d4de27888f36db1e0ba73b54c444f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c78b989a040d856d734f60ae6e96af0ab5755eaba4420f896e723fd133842b
+oid sha256:e780d4cbf10daebfef2b1bbf2e1dcfb8872cf5bcbbbb3c899ea702912a0bf658
 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": 0.8185915350914001,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010168543610341408,
+  "best_metric": 0.785561203956604,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020337087220682816,
   "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": 9.446,
       "eval_steps_per_second": 2.456,
       "step": 25
+    },
+    {
+      "epoch": 0.010575285354755066,
+      "grad_norm": 4.994813442230225,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 24.9078,
+      "step": 26
+    },
+    {
+      "epoch": 0.010982027099168722,
+      "grad_norm": 5.219534397125244,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 28.395,
+      "step": 27
+    },
+    {
+      "epoch": 0.011388768843582378,
+      "grad_norm": 5.788186073303223,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 30.7909,
+      "step": 28
+    },
+    {
+      "epoch": 0.011795510587996034,
+      "grad_norm": 6.449784278869629,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 30.4489,
+      "step": 29
+    },
+    {
+      "epoch": 0.01220225233240969,
+      "grad_norm": 5.068568706512451,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 28.3087,
+      "step": 30
+    },
+    {
+      "epoch": 0.012608994076823346,
+      "grad_norm": 7.565436840057373,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 29.5816,
+      "step": 31
+    },
+    {
+      "epoch": 0.013015735821237003,
+      "grad_norm": 5.332314968109131,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 27.4378,
+      "step": 32
+    },
+    {
+      "epoch": 0.01342247756565066,
+      "grad_norm": 6.02372932434082,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 29.1633,
+      "step": 33
+    },
+    {
+      "epoch": 0.013829219310064316,
+      "grad_norm": 6.785523891448975,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 28.2066,
+      "step": 34
+    },
+    {
+      "epoch": 0.014235961054477973,
+      "grad_norm": 6.292851448059082,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 25.9299,
+      "step": 35
+    },
+    {
+      "epoch": 0.014642702798891629,
+      "grad_norm": 5.5777716636657715,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 24.8049,
+      "step": 36
+    },
+    {
+      "epoch": 0.015049444543305285,
+      "grad_norm": 7.278702259063721,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 24.2338,
+      "step": 37
+    },
+    {
+      "epoch": 0.015456186287718941,
+      "grad_norm": 6.606675148010254,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 23.7511,
+      "step": 38
+    },
+    {
+      "epoch": 0.015862928032132597,
+      "grad_norm": 3.8052306175231934,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 25.953,
+      "step": 39
+    },
+    {
+      "epoch": 0.016269669776546255,
+      "grad_norm": 4.5456953048706055,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 28.1611,
+      "step": 40
+    },
+    {
+      "epoch": 0.01667641152095991,
+      "grad_norm": 4.992256164550781,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 28.9608,
+      "step": 41
+    },
+    {
+      "epoch": 0.017083153265373567,
+      "grad_norm": 4.703763484954834,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 27.5949,
+      "step": 42
+    },
+    {
+      "epoch": 0.017489895009787225,
+      "grad_norm": 4.844160556793213,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 28.8721,
+      "step": 43
+    },
+    {
+      "epoch": 0.01789663675420088,
+      "grad_norm": 5.016782283782959,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 27.4048,
+      "step": 44
+    },
+    {
+      "epoch": 0.018303378498614537,
+      "grad_norm": 5.641413688659668,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 27.7797,
+      "step": 45
+    },
+    {
+      "epoch": 0.01871012024302819,
+      "grad_norm": 6.395452976226807,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 27.9617,
+      "step": 46
+    },
+    {
+      "epoch": 0.01911686198744185,
+      "grad_norm": 6.129427433013916,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 25.9191,
+      "step": 47
+    },
+    {
+      "epoch": 0.019523603731855504,
+      "grad_norm": 5.464219093322754,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 25.7966,
+      "step": 48
+    },
+    {
+      "epoch": 0.01993034547626916,
+      "grad_norm": 6.133424758911133,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 25.617,
+      "step": 49
+    },
+    {
+      "epoch": 0.020337087220682816,
+      "grad_norm": 7.993808269500732,
+      "learning_rate": 1e-05,
+      "loss": 22.7906,
+      "step": 50
+    },
+    {
+      "epoch": 0.020337087220682816,
+      "eval_loss": 0.785561203956604,
+      "eval_runtime": 5.4563,
+      "eval_samples_per_second": 9.164,
+      "eval_steps_per_second": 2.383,
+      "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": 3.357609699615703e+17,
+  "total_flos": 6.73658452077183e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null