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:a2570c336dfac740e6358c09c18c76d7a115198f49a43205addfdb5e1134768a
+oid sha256:140a651458458a3a72d9e9509560159ef753633d01824b2ad52425cac43e8d74
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d1859bba9cfe9063445cde92d019d2e22af5dbdafa9a7b4b21616d18a990ec
+oid sha256:2443f3c2180159f890e057c608dcae93d8f78679f21639a68a4453c32878f053
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef78b55cdce3a8af09e0c0668512cfc4c496b0c58118e2d38e93b0561899bc7
+oid sha256:6d0d35d5fd9a5243e46618bf58cc603a734ad14b30f920c221d5270f3631a667
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85b07749f63f27d20d27629b1bffb8d030b78e4c32111b6f5db9ff03cb5b466
+oid sha256:7b37e8d1b97e25cc24ce8a75da9168a309429324d072bf8a26428ef9d102b495
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0fd35eebcfb66c83c57bfa86f458025f5550914d3f8b1ba1d8ab8ac4f0d0e8
+oid sha256:b0cba16e513ab9ca4a461d0dc8a18092e796806a8ca76e870fb750649b9e1df9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e9efcc15ccdedf77459e0b890bd3a2ad456e9ccc0903edf600ae74da252692
+oid sha256:1155058eb66c582fd5d964902673133f28008fc54cf1f2df5b256ef763c328a8
 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": 1.0794994831085205,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3917727717923604,
+  "best_metric": 1.0705811977386475,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7835455435847208,
   "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": 12.302,
       "eval_steps_per_second": 3.199,
       "step": 25
+    },
+    {
+      "epoch": 0.40744368266405484,
+      "grad_norm": 0.1861858069896698,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8971,
+      "step": 26
+    },
+    {
+      "epoch": 0.42311459353574926,
+      "grad_norm": 0.419063925743103,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9787,
+      "step": 27
+    },
+    {
+      "epoch": 0.4387855044074437,
+      "grad_norm": 0.24568253755569458,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0591,
+      "step": 28
+    },
+    {
+      "epoch": 0.4544564152791381,
+      "grad_norm": 0.32705578207969666,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.0477,
+      "step": 29
+    },
+    {
+      "epoch": 0.4701273261508325,
+      "grad_norm": 0.23818816244602203,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0777,
+      "step": 30
+    },
+    {
+      "epoch": 0.48579823702252695,
+      "grad_norm": 0.28618699312210083,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0577,
+      "step": 31
+    },
+    {
+      "epoch": 0.5014691478942214,
+      "grad_norm": 0.4966736435890198,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.1423,
+      "step": 32
+    },
+    {
+      "epoch": 0.5171400587659157,
+      "grad_norm": 0.3694216012954712,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1966,
+      "step": 33
+    },
+    {
+      "epoch": 0.5328109696376102,
+      "grad_norm": 0.2748936116695404,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.254,
+      "step": 34
+    },
+    {
+      "epoch": 0.5484818805093046,
+      "grad_norm": 0.281665176153183,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1403,
+      "step": 35
+    },
+    {
+      "epoch": 0.564152791380999,
+      "grad_norm": 0.399133563041687,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3012,
+      "step": 36
+    },
+    {
+      "epoch": 0.5798237022526934,
+      "grad_norm": 0.3966122269630432,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1953,
+      "step": 37
+    },
+    {
+      "epoch": 0.5954946131243879,
+      "grad_norm": 0.17433038353919983,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8101,
+      "step": 38
+    },
+    {
+      "epoch": 0.6111655239960823,
+      "grad_norm": 0.24766185879707336,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9221,
+      "step": 39
+    },
+    {
+      "epoch": 0.6268364348677767,
+      "grad_norm": 0.249129518866539,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9939,
+      "step": 40
+    },
+    {
+      "epoch": 0.6425073457394711,
+      "grad_norm": 0.20314669609069824,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0355,
+      "step": 41
+    },
+    {
+      "epoch": 0.6581782566111655,
+      "grad_norm": 0.27352964878082275,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0654,
+      "step": 42
+    },
+    {
+      "epoch": 0.67384916748286,
+      "grad_norm": 0.22664915025234222,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.116,
+      "step": 43
+    },
+    {
+      "epoch": 0.6895200783545543,
+      "grad_norm": 0.2976838946342468,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1354,
+      "step": 44
+    },
+    {
+      "epoch": 0.7051909892262488,
+      "grad_norm": 0.45878639817237854,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1952,
+      "step": 45
+    },
+    {
+      "epoch": 0.7208619000979432,
+      "grad_norm": 0.46237072348594666,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1617,
+      "step": 46
+    },
+    {
+      "epoch": 0.7365328109696376,
+      "grad_norm": 0.41439488530158997,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1395,
+      "step": 47
+    },
+    {
+      "epoch": 0.752203721841332,
+      "grad_norm": 0.3287385106086731,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1399,
+      "step": 48
+    },
+    {
+      "epoch": 0.7678746327130265,
+      "grad_norm": 0.35915854573249817,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.1691,
+      "step": 49
+    },
+    {
+      "epoch": 0.7835455435847208,
+      "grad_norm": 0.5673591494560242,
+      "learning_rate": 1e-05,
+      "loss": 1.2819,
+      "step": 50
+    },
+    {
+      "epoch": 0.7835455435847208,
+      "eval_loss": 1.0705811977386475,
+      "eval_runtime": 4.0399,
+      "eval_samples_per_second": 12.377,
+      "eval_steps_per_second": 3.218,
+      "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": 2.993366934277325e+17,
+  "total_flos": 5.984868843430871e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null