Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603e0411866c614986f0e91c7e50e8a47662d5984bdec48da70f064e66e3953e
+oid sha256:4849b9ffc18c1f5d8bbd33d7d811d611b0e7dda2a7a6f94bd9bf54a63941f9d2
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c3a72a5f29663d7982118c93b91b00f217e11d6c1b598768cb2488848f5c75
+oid sha256:49eb311aa7d3dcdd67b51bbedace2005e079ddcfac4b2a44a7cc6554cfe1274a
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a09e97ebf65ae65efb107e2ed59f7a96cb1b8a425f57620d41e721db9b4f126
+oid sha256:f5f5abfa1119d5796caf489424cfef84705628776f9cc8c42249969051b09e5e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4304b75f97174815cffb03c724f70b7215419fd132b8232608e704ecc72f692b
+oid sha256:14a0967e2b1a42af3acbd17a9829deeff712b962d32db48017ed85f68a71eff3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0343e640ed02a1ab39778a1559ea47fc2d434480f3b8cd6618d66c81d778d824
+oid sha256:6093cc526e746956640cb2b85fb774ed8d83d2fac426864855d910b3500eb4e9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb52695a43993698945856a7b2196b4500d1425dabc8ae28d3a81c8dec46fb3
+oid sha256:50d67e1a6504a452728f88db4cf142ce4eafce5a29c2bfe80ae38b26475f4123
 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": 2.5546910762786865,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1659062629614268,
+  "best_metric": 2.412879228591919,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3318125259228536,
   "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": 9.008,
       "eval_steps_per_second": 2.342,
       "step": 25
+    },
+    {
+      "epoch": 0.17254251347988386,
+      "grad_norm": 24.010421752929688,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 89.4733,
+      "step": 26
+    },
+    {
+      "epoch": 0.17917876399834093,
+      "grad_norm": 16.442790985107422,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 79.1688,
+      "step": 27
+    },
+    {
+      "epoch": 0.18581501451679802,
+      "grad_norm": 23.459074020385742,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 75.9344,
+      "step": 28
+    },
+    {
+      "epoch": 0.1924512650352551,
+      "grad_norm": 23.219343185424805,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 75.0841,
+      "step": 29
+    },
+    {
+      "epoch": 0.19908751555371215,
+      "grad_norm": 36.46348571777344,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 71.8608,
+      "step": 30
+    },
+    {
+      "epoch": 0.20572376607216922,
+      "grad_norm": 24.08379364013672,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 72.6857,
+      "step": 31
+    },
+    {
+      "epoch": 0.21236001659062628,
+      "grad_norm": 20.700775146484375,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 73.6169,
+      "step": 32
+    },
+    {
+      "epoch": 0.21899626710908338,
+      "grad_norm": 14.344165802001953,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 72.8962,
+      "step": 33
+    },
+    {
+      "epoch": 0.22563251762754044,
+      "grad_norm": 19.467073440551758,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 75.4409,
+      "step": 34
+    },
+    {
+      "epoch": 0.2322687681459975,
+      "grad_norm": 35.137939453125,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 93.4653,
+      "step": 35
+    },
+    {
+      "epoch": 0.23890501866445457,
+      "grad_norm": 45.6280517578125,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 88.3274,
+      "step": 36
+    },
+    {
+      "epoch": 0.24554126918291166,
+      "grad_norm": 47.0994873046875,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 98.4404,
+      "step": 37
+    },
+    {
+      "epoch": 0.2521775197013687,
+      "grad_norm": 56.962154388427734,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 107.2939,
+      "step": 38
+    },
+    {
+      "epoch": 0.2588137702198258,
+      "grad_norm": 14.456352233886719,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 81.9888,
+      "step": 39
+    },
+    {
+      "epoch": 0.2654500207382829,
+      "grad_norm": 11.632476806640625,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 72.7757,
+      "step": 40
+    },
+    {
+      "epoch": 0.27208627125673995,
+      "grad_norm": 13.044448852539062,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 75.0724,
+      "step": 41
+    },
+    {
+      "epoch": 0.278722521775197,
+      "grad_norm": 12.491575241088867,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 74.1388,
+      "step": 42
+    },
+    {
+      "epoch": 0.2853587722936541,
+      "grad_norm": 12.832867622375488,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 72.2979,
+      "step": 43
+    },
+    {
+      "epoch": 0.29199502281211115,
+      "grad_norm": 12.466416358947754,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 72.1957,
+      "step": 44
+    },
+    {
+      "epoch": 0.2986312733305682,
+      "grad_norm": 13.381525993347168,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 71.8714,
+      "step": 45
+    },
+    {
+      "epoch": 0.3052675238490253,
+      "grad_norm": 17.53035545349121,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 71.4497,
+      "step": 46
+    },
+    {
+      "epoch": 0.31190377436748234,
+      "grad_norm": 25.668964385986328,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 86.7853,
+      "step": 47
+    },
+    {
+      "epoch": 0.31854002488593947,
+      "grad_norm": 40.41082763671875,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 88.0605,
+      "step": 48
+    },
+    {
+      "epoch": 0.32517627540439653,
+      "grad_norm": 40.9230842590332,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 85.4458,
+      "step": 49
+    },
+    {
+      "epoch": 0.3318125259228536,
+      "grad_norm": 53.349674224853516,
+      "learning_rate": 1e-05,
+      "loss": 109.816,
+      "step": 50
+    },
+    {
+      "epoch": 0.3318125259228536,
+      "eval_loss": 2.412879228591919,
+      "eval_runtime": 5.5758,
+      "eval_samples_per_second": 8.967,
+      "eval_steps_per_second": 2.331,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null