Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fdb684f37c705b4891243f5d3ebca8a80b7018c2060ecfc2ab8cf708081053e
+oid sha256:d21a94118c10881921c5df4ed0280f345feb47ec446f1ef4ccd4f102e5674b9a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1436651c00c0db4549ff0de50384e7ebe18b95db360dc2851fe4338f8ea923
+oid sha256:d421a6c418e7c75542af086bed68dc3ac4316ba0255125ad0811f12c0087be25
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b761cb9dbc0b6970c7501380386434115ffd87e9a3f53de788760780903dacac
+oid sha256:81a27c64b7ecfb023faabe5dfe889c3f2b240cc6c510ff2decb313d1a5d7dc00
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4047704f93cadb7da62f00d81ab471869fc2fa7b4a5e83150c05a0c0d7fe9311
+oid sha256:927c9b487e2b84aa76d2d8b64923bd5e21340b2fb3048c9477173f9754385bb0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105de2f7326c60f9adc4d8c1ae97b8ec185c7d253635da83c8cb38ee86f2c706
+oid sha256:9cfca026a4e6fa389ed8704f685fd60f9f7327e6167b1ae5fe0fc5ef8db3c997
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b793bd6d05f4b6f20df0fc0b57aed4478acc73e3ec20329e01f9669c15fde163
+oid sha256:e44c44fe0324b1b549117f790bc10b03196b874f80f4fb705b898f7f6b5706e4
 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": 1.2425333261489868,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032208712456719545,
+  "best_metric": 0.992637038230896,
+  "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": 18.137,
       "eval_steps_per_second": 4.716,
       "step": 25
+    },
+    {
+      "epoch": 0.03349706095498833,
+      "grad_norm": 14.467223167419434,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 17.1847,
+      "step": 26
+    },
+    {
+      "epoch": 0.03478540945325711,
+      "grad_norm": 15.1301908493042,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 18.7308,
+      "step": 27
+    },
+    {
+      "epoch": 0.03607375795152589,
+      "grad_norm": 15.84472942352295,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 16.7793,
+      "step": 28
+    },
+    {
+      "epoch": 0.03736210644979467,
+      "grad_norm": 14.654438972473145,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 16.9268,
+      "step": 29
+    },
+    {
+      "epoch": 0.03865045494806345,
+      "grad_norm": 16.933069229125977,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 17.3412,
+      "step": 30
+    },
+    {
+      "epoch": 0.03993880344633223,
+      "grad_norm": 18.706647872924805,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 15.8512,
+      "step": 31
+    },
+    {
+      "epoch": 0.04122715194460101,
+      "grad_norm": 20.193010330200195,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 17.2783,
+      "step": 32
+    },
+    {
+      "epoch": 0.042515500442869794,
+      "grad_norm": 18.044654846191406,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 18.8747,
+      "step": 33
+    },
+    {
+      "epoch": 0.043803848941138576,
+      "grad_norm": 40.971641540527344,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 15.7067,
+      "step": 34
+    },
+    {
+      "epoch": 0.04509219743940736,
+      "grad_norm": 17.42156410217285,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 15.6263,
+      "step": 35
+    },
+    {
+      "epoch": 0.04638054593767614,
+      "grad_norm": 18.421106338500977,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 15.8048,
+      "step": 36
+    },
+    {
+      "epoch": 0.04766889443594492,
+      "grad_norm": 19.15827751159668,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 16.9444,
+      "step": 37
+    },
+    {
+      "epoch": 0.048957242934213704,
+      "grad_norm": 22.42970848083496,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 18.447,
+      "step": 38
+    },
+    {
+      "epoch": 0.050245591432482486,
+      "grad_norm": 26.890399932861328,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 15.0767,
+      "step": 39
+    },
+    {
+      "epoch": 0.05153393993075127,
+      "grad_norm": 26.706233978271484,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 15.1897,
+      "step": 40
+    },
+    {
+      "epoch": 0.05282228842902005,
+      "grad_norm": 20.240707397460938,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 15.4051,
+      "step": 41
+    },
+    {
+      "epoch": 0.05411063692728883,
+      "grad_norm": 22.28195571899414,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 16.4359,
+      "step": 42
+    },
+    {
+      "epoch": 0.055398985425557615,
+      "grad_norm": 17.792125701904297,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 16.4363,
+      "step": 43
+    },
+    {
+      "epoch": 0.0566873339238264,
+      "grad_norm": 15.587968826293945,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 14.1074,
+      "step": 44
+    },
+    {
+      "epoch": 0.05797568242209518,
+      "grad_norm": 16.642824172973633,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 13.7041,
+      "step": 45
+    },
+    {
+      "epoch": 0.05926403092036396,
+      "grad_norm": 17.23164939880371,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 15.2712,
+      "step": 46
+    },
+    {
+      "epoch": 0.06055237941863274,
+      "grad_norm": 20.500869750976562,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 14.5086,
+      "step": 47
+    },
+    {
+      "epoch": 0.061840727916901525,
+      "grad_norm": 25.045188903808594,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 15.6716,
+      "step": 48
+    },
+    {
+      "epoch": 0.06312907641517031,
+      "grad_norm": 20.765283584594727,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 13.7933,
+      "step": 49
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "grad_norm": 27.19532012939453,
+      "learning_rate": 1e-05,
+      "loss": 19.0819,
+      "step": 50
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "eval_loss": 0.992637038230896,
+      "eval_runtime": 2.7412,
+      "eval_samples_per_second": 18.24,
+      "eval_steps_per_second": 4.742,
+      "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