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:de67ad12a4381b0a069cb90c36f50e858dc02570e254b5488b82ab117c954961
+oid sha256:327789f69a0dba5152d58604cea9de71241ef017ae61491373a1bab63db5e0f0
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c85aeafad585b708668966ad75669d827d32f99252f0a5bddbf753a74dfc08
+oid sha256:20b54a4f765bfc95b7ffc24e9904c66713bc0967cc673ab4e58201f30b5501ca
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a743be74462527e81ca17aae9eee9e5ebb43011104a01de8708b347c20639d4a
+oid sha256:681311bf5990981f897c8da6383c4b16db40b7e45a2aa153d33537f9004b99e0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72efe327f2b5a5708facc1161a4d6a2fab51ae5bae2814944316834a44e90e5e
+oid sha256:630c57fba64374382c9cfa9c8d8b3fa5d383cf3ed519e817c9d7d0caa086851b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f3654edc314e06c0eb5dbcb790ea4fbd5449e1c240de657473fa1277e4547a
+oid sha256:f02f6262d19b9856cd2c907d6e612c22bc59f904b4bbe5f7a2506cfd03dcecf3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17b379d1579c2b7aaed69f5486e2129606a49b0f3a55b5cb3cb182798484aff
+oid sha256:8ac1201fd6f87b6bdbbfb6b6ced1512fd854928af2487e7d93ed79ac941e20aa
 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": 11.04233169555664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.051759834368530024,
+  "best_metric": 11.016731262207031,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10351966873706005,
   "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": 588.797,
       "eval_steps_per_second": 153.087,
       "step": 25
+    },
+    {
+      "epoch": 0.053830227743271224,
+      "grad_norm": 6.590371608734131,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 176.4769,
+      "step": 26
+    },
+    {
+      "epoch": 0.055900621118012424,
+      "grad_norm": 4.6611480712890625,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 176.7507,
+      "step": 27
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 4.020076274871826,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 176.7667,
+      "step": 28
+    },
+    {
+      "epoch": 0.060041407867494824,
+      "grad_norm": 4.015106678009033,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 176.8385,
+      "step": 29
+    },
+    {
+      "epoch": 0.062111801242236024,
+      "grad_norm": 3.977048873901367,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 176.9064,
+      "step": 30
+    },
+    {
+      "epoch": 0.06418219461697723,
+      "grad_norm": 3.951341152191162,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 176.7282,
+      "step": 31
+    },
+    {
+      "epoch": 0.06625258799171843,
+      "grad_norm": 4.043701648712158,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 176.7812,
+      "step": 32
+    },
+    {
+      "epoch": 0.06832298136645963,
+      "grad_norm": 4.244744300842285,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 176.6306,
+      "step": 33
+    },
+    {
+      "epoch": 0.07039337474120083,
+      "grad_norm": 4.570371627807617,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 176.5429,
+      "step": 34
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 4.860273361206055,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 176.557,
+      "step": 35
+    },
+    {
+      "epoch": 0.07453416149068323,
+      "grad_norm": 5.925064563751221,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 176.2983,
+      "step": 36
+    },
+    {
+      "epoch": 0.07660455486542443,
+      "grad_norm": 6.933615207672119,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 176.0812,
+      "step": 37
+    },
+    {
+      "epoch": 0.07867494824016563,
+      "grad_norm": 7.716263294219971,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 175.6745,
+      "step": 38
+    },
+    {
+      "epoch": 0.08074534161490683,
+      "grad_norm": 6.395534992218018,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 176.2174,
+      "step": 39
+    },
+    {
+      "epoch": 0.08281573498964803,
+      "grad_norm": 4.4871673583984375,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 176.5033,
+      "step": 40
+    },
+    {
+      "epoch": 0.08488612836438923,
+      "grad_norm": 4.042433738708496,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 176.6441,
+      "step": 41
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 4.071824073791504,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 176.6377,
+      "step": 42
+    },
+    {
+      "epoch": 0.08902691511387163,
+      "grad_norm": 4.026284217834473,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 176.613,
+      "step": 43
+    },
+    {
+      "epoch": 0.09109730848861283,
+      "grad_norm": 4.184352874755859,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 176.524,
+      "step": 44
+    },
+    {
+      "epoch": 0.09316770186335403,
+      "grad_norm": 4.085234642028809,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 176.5405,
+      "step": 45
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 4.481105804443359,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 176.4587,
+      "step": 46
+    },
+    {
+      "epoch": 0.09730848861283643,
+      "grad_norm": 4.551030158996582,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 176.3409,
+      "step": 47
+    },
+    {
+      "epoch": 0.09937888198757763,
+      "grad_norm": 5.4851813316345215,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 176.1347,
+      "step": 48
+    },
+    {
+      "epoch": 0.10144927536231885,
+      "grad_norm": 5.989502906799316,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 176.0228,
+      "step": 49
+    },
+    {
+      "epoch": 0.10351966873706005,
+      "grad_norm": 9.128138542175293,
+      "learning_rate": 1e-05,
+      "loss": 175.3216,
+      "step": 50
+    },
+    {
+      "epoch": 0.10351966873706005,
+      "eval_loss": 11.016731262207031,
+      "eval_runtime": 0.0781,
+      "eval_samples_per_second": 640.344,
+      "eval_steps_per_second": 166.489,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null