Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874059a95400690aa266597b14222319aca03969614babe6eae2bdffb2b13444
+oid sha256:c5369595cb249b01c76fa3af44facd23cec88b2581d3b9805a85d190019e4ef9
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744d3573944197bcfac3f0c61a57c597c2b48d5831f25875c56ccfae07186068
+oid sha256:3a14aaa14dbd3f405c8afe5bf633cbc4e2daea3011b2db670cec24c234577ee8
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3dcc0f977938e5edd37c64bbdc4e830585cdb2612a85cb64b4502960c624de0
+oid sha256:559dd4ccb6a6addeb1261cc199cd97418ae95225b39a5ef52c7fe26eaa7840e7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ffee8c302e646fa3e85fc0837376adc2df2ebe4b1b7614d995bca4954a73e4
+oid sha256:4b9cd5466ee470389c1e9531de723c9ca1050150fe2454b308019031970cd526
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11f6a6b66a2e93cf3465c6ab3ebb5ca86afc0af43c1f99fc9e8f4a4c3ab523f
+oid sha256:9f8c0508433f80056e56f7ac67aaf4d0cdd00aa574dddefc44cbaa7d5151760a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f303078f1366ace23579d9ad1af220fddfa01b28c6039e38232adc973214b5
+oid sha256:db870555cb1d50bd916ee978474c4b9514ad9efd7239e7c49e8deb00eaa1a63b
 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": 1.2492481470108032,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032208712456719545,
+  "best_metric": 0.9948898553848267,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06441742491343909,
   "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": 10.748,
       "eval_steps_per_second": 2.795,
       "step": 25
+    },
+    {
+      "epoch": 0.03349706095498833,
+      "grad_norm": 16.005144119262695,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 17.4033,
+      "step": 26
+    },
+    {
+      "epoch": 0.03478540945325711,
+      "grad_norm": 15.092500686645508,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 19.0921,
+      "step": 27
+    },
+    {
+      "epoch": 0.03607375795152589,
+      "grad_norm": 16.550247192382812,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 17.2011,
+      "step": 28
+    },
+    {
+      "epoch": 0.03736210644979467,
+      "grad_norm": 15.699130058288574,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 17.3538,
+      "step": 29
+    },
+    {
+      "epoch": 0.03865045494806345,
+      "grad_norm": 26.110191345214844,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 17.645,
+      "step": 30
+    },
+    {
+      "epoch": 0.03993880344633223,
+      "grad_norm": 18.78908348083496,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 16.3185,
+      "step": 31
+    },
+    {
+      "epoch": 0.04122715194460101,
+      "grad_norm": 57.27931594848633,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 17.6593,
+      "step": 32
+    },
+    {
+      "epoch": 0.042515500442869794,
+      "grad_norm": 16.303855895996094,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 18.9975,
+      "step": 33
+    },
+    {
+      "epoch": 0.043803848941138576,
+      "grad_norm": 28.298973083496094,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 16.0292,
+      "step": 34
+    },
+    {
+      "epoch": 0.04509219743940736,
+      "grad_norm": 18.73902130126953,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 15.6873,
+      "step": 35
+    },
+    {
+      "epoch": 0.04638054593767614,
+      "grad_norm": 21.300758361816406,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 15.8481,
+      "step": 36
+    },
+    {
+      "epoch": 0.04766889443594492,
+      "grad_norm": 20.065980911254883,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 17.0499,
+      "step": 37
+    },
+    {
+      "epoch": 0.048957242934213704,
+      "grad_norm": 21.519365310668945,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 18.4442,
+      "step": 38
+    },
+    {
+      "epoch": 0.050245591432482486,
+      "grad_norm": 27.642358779907227,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 15.2549,
+      "step": 39
+    },
+    {
+      "epoch": 0.05153393993075127,
+      "grad_norm": 25.120906829833984,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 15.2933,
+      "step": 40
+    },
+    {
+      "epoch": 0.05282228842902005,
+      "grad_norm": 19.137609481811523,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 15.309,
+      "step": 41
+    },
+    {
+      "epoch": 0.05411063692728883,
+      "grad_norm": 21.001296997070312,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 16.4754,
+      "step": 42
+    },
+    {
+      "epoch": 0.055398985425557615,
+      "grad_norm": 16.85972785949707,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 16.548,
+      "step": 43
+    },
+    {
+      "epoch": 0.0566873339238264,
+      "grad_norm": 16.204029083251953,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 14.3728,
+      "step": 44
+    },
+    {
+      "epoch": 0.05797568242209518,
+      "grad_norm": 39.45888900756836,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 13.8207,
+      "step": 45
+    },
+    {
+      "epoch": 0.05926403092036396,
+      "grad_norm": 18.450166702270508,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 15.3627,
+      "step": 46
+    },
+    {
+      "epoch": 0.06055237941863274,
+      "grad_norm": 22.184141159057617,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 14.598,
+      "step": 47
+    },
+    {
+      "epoch": 0.061840727916901525,
+      "grad_norm": 26.28811264038086,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 15.7772,
+      "step": 48
+    },
+    {
+      "epoch": 0.06312907641517031,
+      "grad_norm": 20.938220977783203,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 13.8192,
+      "step": 49
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "grad_norm": 26.821365356445312,
+      "learning_rate": 1e-05,
+      "loss": 19.0895,
+      "step": 50
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "eval_loss": 0.9948898553848267,
+      "eval_runtime": 4.6664,
+      "eval_samples_per_second": 10.715,
+      "eval_steps_per_second": 2.786,
+      "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": 2,
   "trial_name": null,
   "trial_params": null