Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94ee0f6988f83cd4ef03e7ffae48ca5bd3984bf40c52f830a30c24b9f9cb5a31
+oid sha256:4b1bdd05f33d2ecdb388fecd29730076a92a4432bd9b600165059ff88ff8f009
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9202310df2d9db613231b7fc7a242ca06a13414eba8b535b20bb30d15e80472f
+oid sha256:1c9fa5d18703b5db2261ea691cf5aa8d23c3d2d9071d83fd8e3396f561794af3
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a37982c5488050494a52c478302a8dd63290b3ffb0d784ddc2fb48ea000f79
+oid sha256:1c3c2aba7c5b382d86a4ed8484ba3cba2d335b08b1e4fdc869aa9419ae644205
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98415381139bd6225d404cd5143e1b2be9bf38786d6d6c65190915cf1eb7cd43
+oid sha256:95870058511eff305e3eb1a8668d3d8e986bdde393eb6d46569597447f25cc2b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e406a6e55c3251410f3e20bffac822fce10bce184dbf55c211af4c2b0c0c0bc4
+oid sha256:6c7430bfb28116565033d43b2eed2f48d707b765bf350f10c42842fc37b3df75
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e678e49cbfc6d6bf000fb228892def1ac28b972fdff0917d424f00967ff4ae5
+oid sha256:3bc16268b4d8cde4727f248c936e6ef8d2c88817b612aed307af8c8f9bb23134
 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": 1.8876161575317383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06796941376380629,
+  "best_metric": 1.835883617401123,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13593882752761258,
   "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": 14.224,
       "eval_steps_per_second": 3.698,
       "step": 25
+    },
+    {
+      "epoch": 0.07068819031435854,
+      "grad_norm": 0.7148436903953552,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1067,
+      "step": 26
+    },
+    {
+      "epoch": 0.07340696686491079,
+      "grad_norm": 0.6958780288696289,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.0677,
+      "step": 27
+    },
+    {
+      "epoch": 0.07612574341546305,
+      "grad_norm": 0.6679629683494568,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0391,
+      "step": 28
+    },
+    {
+      "epoch": 0.0788445199660153,
+      "grad_norm": 0.6717768907546997,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.9869,
+      "step": 29
+    },
+    {
+      "epoch": 0.08156329651656755,
+      "grad_norm": 0.6259593963623047,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.866,
+      "step": 30
+    },
+    {
+      "epoch": 0.0842820730671198,
+      "grad_norm": 0.7161216735839844,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.9687,
+      "step": 31
+    },
+    {
+      "epoch": 0.08700084961767204,
+      "grad_norm": 0.7441960573196411,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9273,
+      "step": 32
+    },
+    {
+      "epoch": 0.08971962616822429,
+      "grad_norm": 0.7459737658500671,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9958,
+      "step": 33
+    },
+    {
+      "epoch": 0.09243840271877656,
+      "grad_norm": 0.6967633366584778,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8823,
+      "step": 34
+    },
+    {
+      "epoch": 0.0951571792693288,
+      "grad_norm": 0.669630765914917,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.8409,
+      "step": 35
+    },
+    {
+      "epoch": 0.09787595581988105,
+      "grad_norm": 0.7518098950386047,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7421,
+      "step": 36
+    },
+    {
+      "epoch": 0.1005947323704333,
+      "grad_norm": 0.7188749313354492,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.7415,
+      "step": 37
+    },
+    {
+      "epoch": 0.10331350892098555,
+      "grad_norm": 0.9793473482131958,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.9251,
+      "step": 38
+    },
+    {
+      "epoch": 0.10603228547153781,
+      "grad_norm": 0.6875200867652893,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.9748,
+      "step": 39
+    },
+    {
+      "epoch": 0.10875106202209006,
+      "grad_norm": 0.6666844487190247,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.0227,
+      "step": 40
+    },
+    {
+      "epoch": 0.11146983857264231,
+      "grad_norm": 0.6823920607566833,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.9829,
+      "step": 41
+    },
+    {
+      "epoch": 0.11418861512319456,
+      "grad_norm": 0.6978684067726135,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9509,
+      "step": 42
+    },
+    {
+      "epoch": 0.11690739167374681,
+      "grad_norm": 0.6857638955116272,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.9204,
+      "step": 43
+    },
+    {
+      "epoch": 0.11962616822429907,
+      "grad_norm": 0.7402970194816589,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9686,
+      "step": 44
+    },
+    {
+      "epoch": 0.12234494477485132,
+      "grad_norm": 0.6844517588615417,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8972,
+      "step": 45
+    },
+    {
+      "epoch": 0.12506372132540358,
+      "grad_norm": 0.7217066884040833,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.9522,
+      "step": 46
+    },
+    {
+      "epoch": 0.12778249787595583,
+      "grad_norm": 0.6970483064651489,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.8359,
+      "step": 47
+    },
+    {
+      "epoch": 0.13050127442650808,
+      "grad_norm": 0.7298968434333801,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8112,
+      "step": 48
+    },
+    {
+      "epoch": 0.13322005097706033,
+      "grad_norm": 0.7759461402893066,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.8007,
+      "step": 49
+    },
+    {
+      "epoch": 0.13593882752761258,
+      "grad_norm": 0.8110302090644836,
+      "learning_rate": 1e-05,
+      "loss": 1.6085,
+      "step": 50
+    },
+    {
+      "epoch": 0.13593882752761258,
+      "eval_loss": 1.835883617401123,
+      "eval_runtime": 3.5145,
+      "eval_samples_per_second": 14.227,
+      "eval_steps_per_second": 3.699,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.979273768059535e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null