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:a0832d83b031ffcb26a0bff8ff371a2ec3756b2edb346a7399789035cd9b0b90
+oid sha256:a2c3ddf2ae8c0d79098a5af6132dea6793156d2e5eaba21962e57107c832f7fa
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4769685af6f25fa39bcc1a988676c2f78849236ef173ab5085bfa05584ee0885
+oid sha256:cfeb871e4b0f104186cfc5c993061067c9fa2971e9011ef7d6f66fc632992669
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a585e039cfecaa9198a54c8435b42610e00b11ba1eb1c167edfb6c1a99ab6d8f
+oid sha256:2a5245b1ef7929f165c50a071c4fd3b519fb6a3552992b319195ea56d86a7f38
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81276e444073a80953070c77cd2426c7dcc14b38603bdbe4ae4d6171848102aa
+oid sha256:9797c4606c59c45dd65975cca245dafbc87e8fa73ed99953d34fcb149664a13a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f334318047a4afdd1224d059c3206cc737c71228ccd7fcbb7ec7cd8c358d6c
+oid sha256:1a2b932d68de4dc96b6bb86068590ce2474a29a300e5819c5cce72b42cc492b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafd0c621387445da760369ce6c649c28123ab54a064bbfc08136ed51e26d8d8
+oid sha256:a25697e3bf7ac5285096f7dbbfb79327199d3e20cfde49d5f7b438384e367cc8
 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": 0.3736724555492401,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28188865398167723,
+  "best_metric": 0.328974187374115,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5637773079633545,
   "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": 5.309,
       "eval_steps_per_second": 1.38,
       "step": 25
+    },
+    {
+      "epoch": 0.29316420014094435,
+      "grad_norm": 3.929647207260132,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3929,
+      "step": 26
+    },
+    {
+      "epoch": 0.3044397463002114,
+      "grad_norm": 3.0069169998168945,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3753,
+      "step": 27
+    },
+    {
+      "epoch": 0.3157152924594785,
+      "grad_norm": 0.7478533983230591,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3487,
+      "step": 28
+    },
+    {
+      "epoch": 0.3269908386187456,
+      "grad_norm": 0.6217486262321472,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3633,
+      "step": 29
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 0.8256338834762573,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3486,
+      "step": 30
+    },
+    {
+      "epoch": 0.34954193093727975,
+      "grad_norm": 4.838144302368164,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4128,
+      "step": 31
+    },
+    {
+      "epoch": 0.3608174770965469,
+      "grad_norm": 4.683679103851318,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3967,
+      "step": 32
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 2.6548237800598145,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3645,
+      "step": 33
+    },
+    {
+      "epoch": 0.383368569415081,
+      "grad_norm": 1.9402390718460083,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3623,
+      "step": 34
+    },
+    {
+      "epoch": 0.39464411557434814,
+      "grad_norm": 3.5657272338867188,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3842,
+      "step": 35
+    },
+    {
+      "epoch": 0.4059196617336152,
+      "grad_norm": 2.6976256370544434,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3498,
+      "step": 36
+    },
+    {
+      "epoch": 0.41719520789288234,
+      "grad_norm": 1.291695475578308,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3353,
+      "step": 37
+    },
+    {
+      "epoch": 0.4284707540521494,
+      "grad_norm": 1.30393385887146,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3776,
+      "step": 38
+    },
+    {
+      "epoch": 0.4397463002114165,
+      "grad_norm": 4.662352085113525,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4494,
+      "step": 39
+    },
+    {
+      "epoch": 0.4510218463706836,
+      "grad_norm": 3.815720319747925,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4232,
+      "step": 40
+    },
+    {
+      "epoch": 0.46229739252995067,
+      "grad_norm": 3.353482961654663,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4129,
+      "step": 41
+    },
+    {
+      "epoch": 0.47357293868921774,
+      "grad_norm": 3.1307156085968018,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3914,
+      "step": 42
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.4309184551239014,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3662,
+      "step": 43
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 2.453277111053467,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3712,
+      "step": 44
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 0.6218744516372681,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3338,
+      "step": 45
+    },
+    {
+      "epoch": 0.5186751233262861,
+      "grad_norm": 1.4151079654693604,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3575,
+      "step": 46
+    },
+    {
+      "epoch": 0.5299506694855532,
+      "grad_norm": 1.0527911186218262,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3386,
+      "step": 47
+    },
+    {
+      "epoch": 0.5412262156448203,
+      "grad_norm": 1.8253545761108398,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3542,
+      "step": 48
+    },
+    {
+      "epoch": 0.5525017618040874,
+      "grad_norm": 1.5399640798568726,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3583,
+      "step": 49
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "grad_norm": 1.680297613143921,
+      "learning_rate": 1e-05,
+      "loss": 0.3236,
+      "step": 50
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "eval_loss": 0.328974187374115,
+      "eval_runtime": 9.4029,
+      "eval_samples_per_second": 5.318,
+      "eval_steps_per_second": 1.383,
+      "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": 1.8550015935276646e+17,
+  "total_flos": 3.7108326150334054e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null