Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a16b1515f5db2797a458b6bc063388afd0126894c4acef3a32aec92c6d8d0f
+oid sha256:2953f6f9b4db4db179d43d19bdb896957d3b705eb48559d367d5578d3eeb5112
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ccaa56e30f193bd109e78b8f004d745f1d6244e987d95ba54dd26f80956470
+oid sha256:876c13502f93aa9ae8c7eef2e4a275b0ccd4d6e723b6e42a4d79478167eb08fc
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4b6e970e27e41312bb49fe90f5d181e3bfb7b3154759e7a843fd1a45aed8e7
+oid sha256:d645d01bea52080b9a660fedeeceb46cd238fd3c61b4c1047f675e549003b36e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a7b5bc01cafbf487077a723e3c9370847bcc495d698f1450d306ffc281cb53
+oid sha256:f9f6f30c128fc10b543eb0410b542b157a46f319a88726f970892eb7612ebd8c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:854dd3b7753e00e0024ecbd928c59d6a9239b29bdfccf6f9af8bff3068cdd43c
+oid sha256:824a4198080e55d55facff29e14b863f4a60b97bea214e6c61c5d4b27c245dba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0847401839a7732cd416934080948e890b9c473fe4af84539f47f2229640154
+oid sha256:b556e2379de94d4da7f4968e43dc9d3b41123e61208a7224a2c1a056c84b11ea
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2875629043853343,
+  "epoch": 0.5751258087706685,
   "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": 9.508,
       "eval_steps_per_second": 2.472,
       "step": 25
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 3.764979124069214,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8616,
+      "step": 26
+    },
+    {
+      "epoch": 0.310567936736161,
+      "grad_norm": 3.678941249847412,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8434,
+      "step": 27
+    },
+    {
+      "epoch": 0.32207045291157443,
+      "grad_norm": 3.1119205951690674,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7273,
+      "step": 28
+    },
+    {
+      "epoch": 0.3335729690869878,
+      "grad_norm": 2.377394199371338,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6829,
+      "step": 29
+    },
+    {
+      "epoch": 0.34507548526240117,
+      "grad_norm": 1.8314098119735718,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5708,
+      "step": 30
+    },
+    {
+      "epoch": 0.35657800143781454,
+      "grad_norm": 1.2278950214385986,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5391,
+      "step": 31
+    },
+    {
+      "epoch": 0.3680805176132279,
+      "grad_norm": 1.1506680250167847,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5648,
+      "step": 32
+    },
+    {
+      "epoch": 0.3795830337886413,
+      "grad_norm": 0.9588247537612915,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.489,
+      "step": 33
+    },
+    {
+      "epoch": 0.39108554996405465,
+      "grad_norm": 1.5099307298660278,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4334,
+      "step": 34
+    },
+    {
+      "epoch": 0.402588066139468,
+      "grad_norm": 2.1597650051116943,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5894,
+      "step": 35
+    },
+    {
+      "epoch": 0.4140905823148814,
+      "grad_norm": 5.968879699707031,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9712,
+      "step": 36
+    },
+    {
+      "epoch": 0.42559309849029475,
+      "grad_norm": 8.183683395385742,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8839,
+      "step": 37
+    },
+    {
+      "epoch": 0.4370956146657081,
+      "grad_norm": 1.7860997915267944,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6139,
+      "step": 38
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 1.6000277996063232,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.616,
+      "step": 39
+    },
+    {
+      "epoch": 0.46010064701653486,
+      "grad_norm": 1.1554548740386963,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5576,
+      "step": 40
+    },
+    {
+      "epoch": 0.4716031631919482,
+      "grad_norm": 0.9421719312667847,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4917,
+      "step": 41
+    },
+    {
+      "epoch": 0.4831056793673616,
+      "grad_norm": 0.9385743141174316,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4912,
+      "step": 42
+    },
+    {
+      "epoch": 0.49460819554277496,
+      "grad_norm": 0.9931282997131348,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4781,
+      "step": 43
+    },
+    {
+      "epoch": 0.5061107117181883,
+      "grad_norm": 1.0186808109283447,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5008,
+      "step": 44
+    },
+    {
+      "epoch": 0.5176132278936018,
+      "grad_norm": 0.9983035326004028,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4088,
+      "step": 45
+    },
+    {
+      "epoch": 0.5291157440690151,
+      "grad_norm": 1.0832576751708984,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4366,
+      "step": 46
+    },
+    {
+      "epoch": 0.5406182602444285,
+      "grad_norm": 1.115883231163025,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4505,
+      "step": 47
+    },
+    {
+      "epoch": 0.5521207764198418,
+      "grad_norm": 2.39801287651062,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6856,
+      "step": 48
+    },
+    {
+      "epoch": 0.5636232925952552,
+      "grad_norm": 4.311333656311035,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.7679,
+      "step": 49
+    },
+    {
+      "epoch": 0.5751258087706685,
+      "grad_norm": 7.141336917877197,
+      "learning_rate": 1e-05,
+      "loss": 0.8328,
+      "step": 50
+    },
+    {
+      "epoch": 0.5751258087706685,
+      "eval_loss": NaN,
+      "eval_runtime": 5.284,
+      "eval_samples_per_second": 9.462,
+      "eval_steps_per_second": 2.46,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null