Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c1ced1c5c50a9b18ca1667aad419ddee2eed0899093654360bbbb45e63d9a8
+oid sha256:46076b150c467921cd664b587d8df52f43f00b8498ed958a62ad39ccf0597797
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:577d476ad23ed91c571615b228a38e2ba16d0f42526494ee967b90a6b90a314a
+oid sha256:689a11cc2ac7a5163609e9ed64af824e804dd09ac452aad948757d4da0bc8500
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60dffe68a45efe56b018e14a5a1c71bd5751da65afd1ba47e6261f086ac961b4
+oid sha256:9f8ad9c92e780dc5c31cfb464ea8bfffde383470535750a9d3de7a6a419ae923
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5199d2be42e13b92010e91c2e55d1f309125db2e2c16d0783101abd403b98f49
+oid sha256:f652946445fc746eec38899b4afb65e0519424fb12528a3f8a37afa012356fb8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4ea071a088f3e615da4ad3d95b8a36093a9c595156c9c9c89146cf677bdc5b
+oid sha256:e32366c56c2b2f579d55807242fceb8cc4c3a60757d8f3050ce0e8bf1fb3c2e0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0670c863835d65eb45268c904ba2d84d4ab59f3c8bfb8b66111f13ca1d0866c
+oid sha256:3216fcaf1a4ff3145fbb93480ad0cad911cd67289de8a486e3a8cdebe7061f3a
 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": 0.780426561832428,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07479431563201197,
+  "best_metric": 0.7736887335777283,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.14958863126402394,
   "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": 10.332,
       "eval_steps_per_second": 2.686,
       "step": 25
+    },
+    {
+      "epoch": 0.07778608825729244,
+      "grad_norm": 1.333006739616394,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6628,
+      "step": 26
+    },
+    {
+      "epoch": 0.08077786088257292,
+      "grad_norm": 1.7285902500152588,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6592,
+      "step": 27
+    },
+    {
+      "epoch": 0.08376963350785341,
+      "grad_norm": 1.4240301847457886,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7008,
+      "step": 28
+    },
+    {
+      "epoch": 0.08676140613313388,
+      "grad_norm": 1.1722900867462158,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7124,
+      "step": 29
+    },
+    {
+      "epoch": 0.08975317875841436,
+      "grad_norm": 1.2526230812072754,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7312,
+      "step": 30
+    },
+    {
+      "epoch": 0.09274495138369485,
+      "grad_norm": 1.2709276676177979,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7181,
+      "step": 31
+    },
+    {
+      "epoch": 0.09573672400897532,
+      "grad_norm": 1.7405914068222046,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.805,
+      "step": 32
+    },
+    {
+      "epoch": 0.0987284966342558,
+      "grad_norm": 1.881058931350708,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8546,
+      "step": 33
+    },
+    {
+      "epoch": 0.10172026925953627,
+      "grad_norm": 1.591508388519287,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9129,
+      "step": 34
+    },
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 1.4230870008468628,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8932,
+      "step": 35
+    },
+    {
+      "epoch": 0.10770381451009724,
+      "grad_norm": 1.7755883932113647,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8137,
+      "step": 36
+    },
+    {
+      "epoch": 0.11069558713537771,
+      "grad_norm": 1.4336092472076416,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8812,
+      "step": 37
+    },
+    {
+      "epoch": 0.11368735976065819,
+      "grad_norm": 0.6839767098426819,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.746,
+      "step": 38
+    },
+    {
+      "epoch": 0.11667913238593867,
+      "grad_norm": 0.883723795413971,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4953,
+      "step": 39
+    },
+    {
+      "epoch": 0.11967090501121914,
+      "grad_norm": 1.1034191846847534,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5899,
+      "step": 40
+    },
+    {
+      "epoch": 0.12266267763649963,
+      "grad_norm": 1.3411037921905518,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5957,
+      "step": 41
+    },
+    {
+      "epoch": 0.1256544502617801,
+      "grad_norm": 1.173579216003418,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5889,
+      "step": 42
+    },
+    {
+      "epoch": 0.1286462228870606,
+      "grad_norm": 1.076574683189392,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7514,
+      "step": 43
+    },
+    {
+      "epoch": 0.13163799551234107,
+      "grad_norm": 1.0555602312088013,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6741,
+      "step": 44
+    },
+    {
+      "epoch": 0.13462976813762154,
+      "grad_norm": 1.1221964359283447,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6866,
+      "step": 45
+    },
+    {
+      "epoch": 0.137621540762902,
+      "grad_norm": 1.205617070198059,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8152,
+      "step": 46
+    },
+    {
+      "epoch": 0.1406133133881825,
+      "grad_norm": 1.2014487981796265,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7961,
+      "step": 47
+    },
+    {
+      "epoch": 0.14360508601346297,
+      "grad_norm": 1.2235502004623413,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8346,
+      "step": 48
+    },
+    {
+      "epoch": 0.14659685863874344,
+      "grad_norm": 1.4418388605117798,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8465,
+      "step": 49
+    },
+    {
+      "epoch": 0.14958863126402394,
+      "grad_norm": 1.4110114574432373,
+      "learning_rate": 1e-05,
+      "loss": 0.9157,
+      "step": 50
+    },
+    {
+      "epoch": 0.14958863126402394,
+      "eval_loss": 0.7736887335777283,
+      "eval_runtime": 4.8278,
+      "eval_samples_per_second": 10.357,
+      "eval_steps_per_second": 2.693,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null