Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789041e9689055e1ade7cbec3f2415192125b64da5d9ab67a86923ccae052b61
+oid sha256:75f087fe03503f04aedc6014449b907c55f8be30cc11feb9fbf26a523e5d1c26
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d119089267a123a9407b4084f3446a2acc25fa993f2780db74830a849d54edab
+oid sha256:60505ecf907737a82264929b05d104a1b4891f055efe46b78a592142cfc72af1
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517559cb9cb5227c1645e3a9aabee5ff52432631ace26c2beaec35e203fc5525
+oid sha256:7c8f06445144be9e28d80949cb5a53d77e8f2e096e1b6191c5afe6363be8f401
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6114040bbd90350f914efae7632890aa63bead544518dfacb4305ae0d8c1a3
+oid sha256:b70f5042627d7f515be8d19aaa9f93b932c0d5a4101f538ddfb3179757d7ffe9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a783b28b5103a2699291efbdb4624a8f1d84cd51dba0eb5edf66f02eadbc39
+oid sha256:ef39e0116ff755e0a6a5c72b2d4d9f7ed1538088944860db1a6daa29e9eb5d81
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989e74b5eb33a675c1d14077fa3821703abc61d35b1833fb88e81c119927c9d1
+oid sha256:3302f1bfedfb132c3fc596c7594b7fa4b61ee04e40de6f343b86a57c050685b0
 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": 9.407609939575195,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005207316279372518,
+  "best_metric": 9.132105827331543,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010414632558745036,
   "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": 99.239,
       "eval_steps_per_second": 25.802,
       "step": 25
+    },
+    {
+      "epoch": 0.005415608930547419,
+      "grad_norm": 2.699100971221924,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 9.4023,
+      "step": 26
+    },
+    {
+      "epoch": 0.00562390158172232,
+      "grad_norm": 2.5721964836120605,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 9.3974,
+      "step": 27
+    },
+    {
+      "epoch": 0.00583219423289722,
+      "grad_norm": 2.452620267868042,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 9.3736,
+      "step": 28
+    },
+    {
+      "epoch": 0.006040486884072121,
+      "grad_norm": 2.3704941272735596,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 9.3641,
+      "step": 29
+    },
+    {
+      "epoch": 0.006248779535247022,
+      "grad_norm": 2.2959113121032715,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 9.3428,
+      "step": 30
+    },
+    {
+      "epoch": 0.0064570721864219225,
+      "grad_norm": 2.5590760707855225,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 9.3309,
+      "step": 31
+    },
+    {
+      "epoch": 0.0066653648375968235,
+      "grad_norm": 2.2302350997924805,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 9.3157,
+      "step": 32
+    },
+    {
+      "epoch": 0.0068736574887717245,
+      "grad_norm": 2.2170119285583496,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.2802,
+      "step": 33
+    },
+    {
+      "epoch": 0.007081950139946625,
+      "grad_norm": 2.3711395263671875,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.2608,
+      "step": 34
+    },
+    {
+      "epoch": 0.007290242791121526,
+      "grad_norm": 2.4080708026885986,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.246,
+      "step": 35
+    },
+    {
+      "epoch": 0.007498535442296427,
+      "grad_norm": 2.4190449714660645,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.2148,
+      "step": 36
+    },
+    {
+      "epoch": 0.007706828093471327,
+      "grad_norm": 2.703991174697876,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 9.2031,
+      "step": 37
+    },
+    {
+      "epoch": 0.007915120744646228,
+      "grad_norm": 2.100898265838623,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 9.2105,
+      "step": 38
+    },
+    {
+      "epoch": 0.008123413395821129,
+      "grad_norm": 2.0093116760253906,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 9.2042,
+      "step": 39
+    },
+    {
+      "epoch": 0.00833170604699603,
+      "grad_norm": 1.8878018856048584,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 9.198,
+      "step": 40
+    },
+    {
+      "epoch": 0.00853999869817093,
+      "grad_norm": 1.8706705570220947,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 9.2053,
+      "step": 41
+    },
+    {
+      "epoch": 0.00874829134934583,
+      "grad_norm": 1.8576347827911377,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 9.2106,
+      "step": 42
+    },
+    {
+      "epoch": 0.008956584000520731,
+      "grad_norm": 1.8795746564865112,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 9.207,
+      "step": 43
+    },
+    {
+      "epoch": 0.009164876651695632,
+      "grad_norm": 2.854189395904541,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 9.2486,
+      "step": 44
+    },
+    {
+      "epoch": 0.009373169302870533,
+      "grad_norm": 1.8021515607833862,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 9.171,
+      "step": 45
+    },
+    {
+      "epoch": 0.009581461954045434,
+      "grad_norm": 1.9334605932235718,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 9.1662,
+      "step": 46
+    },
+    {
+      "epoch": 0.009789754605220335,
+      "grad_norm": 1.9953815937042236,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.1518,
+      "step": 47
+    },
+    {
+      "epoch": 0.009998047256395236,
+      "grad_norm": 2.0963637828826904,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 9.131,
+      "step": 48
+    },
+    {
+      "epoch": 0.010206339907570135,
+      "grad_norm": 2.3475289344787598,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 9.1236,
+      "step": 49
+    },
+    {
+      "epoch": 0.010414632558745036,
+      "grad_norm": 3.048788070678711,
+      "learning_rate": 1e-05,
+      "loss": 9.1111,
+      "step": 50
+    },
+    {
+      "epoch": 0.010414632558745036,
+      "eval_loss": 9.132105827331543,
+      "eval_runtime": 0.5071,
+      "eval_samples_per_second": 98.598,
+      "eval_steps_per_second": 25.635,
+      "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": 155666757451776.0,
+  "total_flos": 311333514903552.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null