Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:371a547ba373dad1158cb067ff3b8ffbe1b3a31b8c933e0736cebdeef94ec77c
+oid sha256:e3b5cd0288132ddf2922d5549765ff24d8526ab7cc0a69f267161eaada122019
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2587ca0fa10b7caac9903e00c433c1b460d0d88753aa7e86cd2bdee61794f5
+oid sha256:905aff4cd25dc1da04c139199c3d4e0c1445c0b7dc27344a0245d91946664ec7
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df7235ced99a079be52fe3cdb4c41c66a8bb717d35635dc55e06743676d000b
+oid sha256:94414ba57717a3e266ad63b0d0ebb9eb40fdb334e0ce11223e2c2c7c0501b9f3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a6f58d675f47ac6b2696b9ee80e63c626257e7dc1085f482936b8f13fc7b12
+oid sha256:b0a59712c8ee3b1a3aa8b2af3a3483d93415264872fc317650a6e444f89f6ef9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9215b8bb9b3d3122b86499fdaa3f673f6689c883238a9ec45899f8fff0e6d50
+oid sha256:66b1321d67712f58fa74daee7bed90289ae37fff50596821f6591ca955583eca
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afa369cb519aa66180288b19f106b1da76a0a22080069575ff930b639c621e2
+oid sha256:64cf2f2191cae438784771caaa9392eeb14fd8a6ae5b0f48d230620540d460d3
 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": 1.8585928678512573,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06260760682422914,
+  "best_metric": 1.8121256828308105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12521521364845828,
   "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": 23.344,
       "eval_steps_per_second": 6.069,
       "step": 25
+    },
+    {
+      "epoch": 0.06511191109719831,
+      "grad_norm": 0.5401023030281067,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.0874,
+      "step": 26
+    },
+    {
+      "epoch": 0.06761621537016747,
+      "grad_norm": 0.6644024848937988,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.885,
+      "step": 27
+    },
+    {
+      "epoch": 0.07012051964313665,
+      "grad_norm": 0.6998805403709412,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.8473,
+      "step": 28
+    },
+    {
+      "epoch": 0.07262482391610581,
+      "grad_norm": 0.710325300693512,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.9115,
+      "step": 29
+    },
+    {
+      "epoch": 0.07512912818907497,
+      "grad_norm": 0.7311844825744629,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.8294,
+      "step": 30
+    },
+    {
+      "epoch": 0.07763343246204414,
+      "grad_norm": 0.7246997952461243,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.8153,
+      "step": 31
+    },
+    {
+      "epoch": 0.0801377367350133,
+      "grad_norm": 0.6861525177955627,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.7765,
+      "step": 32
+    },
+    {
+      "epoch": 0.08264204100798248,
+      "grad_norm": 0.7207047939300537,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.7935,
+      "step": 33
+    },
+    {
+      "epoch": 0.08514634528095164,
+      "grad_norm": 0.7323021292686462,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6575,
+      "step": 34
+    },
+    {
+      "epoch": 0.0876506495539208,
+      "grad_norm": 0.7945370078086853,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.6349,
+      "step": 35
+    },
+    {
+      "epoch": 0.09015495382688997,
+      "grad_norm": 0.8801825046539307,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7027,
+      "step": 36
+    },
+    {
+      "epoch": 0.09265925809985913,
+      "grad_norm": 1.0775583982467651,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.6302,
+      "step": 37
+    },
+    {
+      "epoch": 0.0951635623728283,
+      "grad_norm": 0.5862182974815369,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.0585,
+      "step": 38
+    },
+    {
+      "epoch": 0.09766786664579746,
+      "grad_norm": 0.45996057987213135,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.8886,
+      "step": 39
+    },
+    {
+      "epoch": 0.10017217091876664,
+      "grad_norm": 0.4821791350841522,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.84,
+      "step": 40
+    },
+    {
+      "epoch": 0.1026764751917358,
+      "grad_norm": 0.5062988996505737,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.779,
+      "step": 41
+    },
+    {
+      "epoch": 0.10518077946470496,
+      "grad_norm": 0.5627591609954834,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8208,
+      "step": 42
+    },
+    {
+      "epoch": 0.10768508373767413,
+      "grad_norm": 0.5769994258880615,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8244,
+      "step": 43
+    },
+    {
+      "epoch": 0.11018938801064329,
+      "grad_norm": 0.6159007549285889,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.7565,
+      "step": 44
+    },
+    {
+      "epoch": 0.11269369228361246,
+      "grad_norm": 0.6384226679801941,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6759,
+      "step": 45
+    },
+    {
+      "epoch": 0.11519799655658162,
+      "grad_norm": 0.7101210951805115,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.6337,
+      "step": 46
+    },
+    {
+      "epoch": 0.11770230082955078,
+      "grad_norm": 0.740799605846405,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.6714,
+      "step": 47
+    },
+    {
+      "epoch": 0.12020660510251996,
+      "grad_norm": 0.8116076588630676,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6488,
+      "step": 48
+    },
+    {
+      "epoch": 0.12271090937548912,
+      "grad_norm": 0.9194896817207336,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.6645,
+      "step": 49
+    },
+    {
+      "epoch": 0.12521521364845828,
+      "grad_norm": 1.1691306829452515,
+      "learning_rate": 1e-05,
+      "loss": 1.6732,
+      "step": 50
+    },
+    {
+      "epoch": 0.12521521364845828,
+      "eval_loss": 1.8121256828308105,
+      "eval_runtime": 2.1227,
+      "eval_samples_per_second": 23.555,
+      "eval_steps_per_second": 6.124,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null