Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126b3362703d53d7d27e59418dac98e1760b0fcab99d6906f5a7c13bd583aef4
+oid sha256:a2cc08303eef12aa8801999f335cd4692c3cb3b3141cf3eed583ee03c5cd966b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f740e55ecbfdc4533de96121956a19ca73e7f3fb3a99eeb16348cf156d6c7b8a
+oid sha256:15415d79e0ae1d4f89a4044fe50b24b67a405f72ea9cffd72489bf05ca53aa75
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0273fae3db9584c7b58a4385e4e22315632bd1316ee43001d728064104898e9f
+oid sha256:ad8fcaeb8bca087ab69bd44d9fd8a3324a1650663ed73279cc980b4cbeeff8da
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fa5db750de860dffd0c7d104dc1dac31bce6330993aafedf3530afcd8afdd2
+oid sha256:29a02baa7d3cdad62082b96575a1074e4d31dc7b3957e839e147c2f98120f12c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b85ec0583a37c7dad65780565b39da6f66f90604b24c1a4eeff2fb80053f404
+oid sha256:88f1ca2976f98633dee5fee72e88d61b4068999e04f95c455b6359ad1388be17
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a395945e5673aa529ec048f327f78b8b8a99033fa9ea248ded6c9f519ac0214e
+oid sha256:cc1ac8696e3ee2cf76b9fa988f3a063e6c8a7f6f10edc6e7a11593fc296d9455
 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": 3.4035658836364746,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03415300546448088,
+  "best_metric": 3.254734516143799,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06830601092896176,
   "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": 24.491,
       "eval_steps_per_second": 6.368,
       "step": 25
+    },
+    {
+      "epoch": 0.03551912568306011,
+      "grad_norm": 1.473652720451355,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3435,
+      "step": 26
+    },
+    {
+      "epoch": 0.036885245901639344,
+      "grad_norm": 2.3803224563598633,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.9444,
+      "step": 27
+    },
+    {
+      "epoch": 0.03825136612021858,
+      "grad_norm": 2.5919227600097656,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9708,
+      "step": 28
+    },
+    {
+      "epoch": 0.03961748633879782,
+      "grad_norm": 2.073823928833008,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.1827,
+      "step": 29
+    },
+    {
+      "epoch": 0.040983606557377046,
+      "grad_norm": 1.6544225215911865,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.3102,
+      "step": 30
+    },
+    {
+      "epoch": 0.04234972677595628,
+      "grad_norm": 1.3670271635055542,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.3568,
+      "step": 31
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 1.489598274230957,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.3932,
+      "step": 32
+    },
+    {
+      "epoch": 0.045081967213114756,
+      "grad_norm": 1.6354660987854004,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.6028,
+      "step": 33
+    },
+    {
+      "epoch": 0.04644808743169399,
+      "grad_norm": 1.849533200263977,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.4509,
+      "step": 34
+    },
+    {
+      "epoch": 0.04781420765027322,
+      "grad_norm": 2.0685839653015137,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.506,
+      "step": 35
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 2.4601333141326904,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.7161,
+      "step": 36
+    },
+    {
+      "epoch": 0.050546448087431695,
+      "grad_norm": 2.7234838008880615,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.0133,
+      "step": 37
+    },
+    {
+      "epoch": 0.05191256830601093,
+      "grad_norm": 0.6714175939559937,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.485,
+      "step": 38
+    },
+    {
+      "epoch": 0.05327868852459016,
+      "grad_norm": 0.6364284157752991,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.6755,
+      "step": 39
+    },
+    {
+      "epoch": 0.0546448087431694,
+      "grad_norm": 0.7471128106117249,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.8658,
+      "step": 40
+    },
+    {
+      "epoch": 0.056010928961748634,
+      "grad_norm": 0.9513612985610962,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.1072,
+      "step": 41
+    },
+    {
+      "epoch": 0.05737704918032787,
+      "grad_norm": 0.9536485075950623,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.1031,
+      "step": 42
+    },
+    {
+      "epoch": 0.05874316939890711,
+      "grad_norm": 0.9675177931785583,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.098,
+      "step": 43
+    },
+    {
+      "epoch": 0.060109289617486336,
+      "grad_norm": 1.053505301475525,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.2611,
+      "step": 44
+    },
+    {
+      "epoch": 0.06147540983606557,
+      "grad_norm": 1.2233757972717285,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.4145,
+      "step": 45
+    },
+    {
+      "epoch": 0.06284153005464481,
+      "grad_norm": 1.488215684890747,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.4454,
+      "step": 46
+    },
+    {
+      "epoch": 0.06420765027322405,
+      "grad_norm": 1.4474998712539673,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.6539,
+      "step": 47
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 1.5923969745635986,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.5898,
+      "step": 48
+    },
+    {
+      "epoch": 0.06693989071038252,
+      "grad_norm": 1.9314665794372559,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.6862,
+      "step": 49
+    },
+    {
+      "epoch": 0.06830601092896176,
+      "grad_norm": 3.2003865242004395,
+      "learning_rate": 1e-05,
+      "loss": 4.0908,
+      "step": 50
+    },
+    {
+      "epoch": 0.06830601092896176,
+      "eval_loss": 3.254734516143799,
+      "eval_runtime": 2.0493,
+      "eval_samples_per_second": 24.399,
+      "eval_steps_per_second": 6.344,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.971813667564421e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null