Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1517a3f9e33cc2b5804ea14712bc1dc72c8b835e0897ebe16b2879dd7649dd79
+oid sha256:f1a34fdf91eab79af3c82910291c0e5df6bf65837774dd84ddc4cfe67441025b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72099e49352bb7053139e64c6243919c37a4405a2cdbb0fb40587c68fa45f773
+oid sha256:30b41dbd44746a4e534db0019f45a77ecda6fc53ac75a750ccafaccc06c718e7
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347e8db50b660eda62e6fe17b82d83d11e3d3904f69fc57ff626680b604a1440
+oid sha256:20dd4793f6d3b1189b3720db01e6df073ee6b86cd7d08930d78ed2815faa585a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66123ef0c64b4e4b3ff1c35cc55d4f604231f4513e65dcc72310cfdc52636402
+oid sha256:5fa0142c2f601664f14ede1e76f964c7f9710ee8d050da3b691589cce2788345
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193d0ad58f458e535562d790b862a0fdabc93ef862c692d28ace214ceb6bc297
+oid sha256:0fc9a6e2a9f69c24b482f1f60b1131b3aa93ea2768de4f210bc3ad1f29c6e820
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c170638612bde06d03faebe52f4017a4ccb66d9e677720ed7caa3cef89c715fa
+oid sha256:3f8dd7e48e8b909b258173956b44f464b94b0dfd0e78d6a66a8bb6d0f4b4c9fe
 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": 0.9392008185386658,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8547008547008547,
+  "best_metric": 0.8931620717048645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7094017094017095,
   "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": 24.72,
       "eval_steps_per_second": 6.427,
       "step": 25
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.28828299045562744,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9403,
+      "step": 26
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.38371339440345764,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.0333,
+      "step": 27
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 0.44360658526420593,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.98,
+      "step": 28
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 0.6779705882072449,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9648,
+      "step": 29
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.5517345666885376,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4473,
+      "step": 30
+    },
+    {
+      "epoch": 1.0598290598290598,
+      "grad_norm": 0.23404933512210846,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7709,
+      "step": 31
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 0.2610025107860565,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8031,
+      "step": 32
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": 0.2766599953174591,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8361,
+      "step": 33
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 0.27406713366508484,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.904,
+      "step": 34
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.4131571650505066,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0052,
+      "step": 35
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.5624709129333496,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8572,
+      "step": 36
+    },
+    {
+      "epoch": 1.264957264957265,
+      "grad_norm": 0.277886301279068,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6639,
+      "step": 37
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 0.24286344647407532,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7853,
+      "step": 38
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.2343275249004364,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7609,
+      "step": 39
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.24362745881080627,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.8369,
+      "step": 40
+    },
+    {
+      "epoch": 1.4017094017094016,
+      "grad_norm": 0.33069658279418945,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9203,
+      "step": 41
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 0.4633345603942871,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0051,
+      "step": 42
+    },
+    {
+      "epoch": 1.4700854700854702,
+      "grad_norm": 0.48219937086105347,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7931,
+      "step": 43
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 0.2977604269981384,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5812,
+      "step": 44
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.2524968683719635,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8629,
+      "step": 45
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 0.23304057121276855,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7652,
+      "step": 46
+    },
+    {
+      "epoch": 1.606837606837607,
+      "grad_norm": 0.2518332004547119,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7838,
+      "step": 47
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.3052296042442322,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.896,
+      "step": 48
+    },
+    {
+      "epoch": 1.6752136752136753,
+      "grad_norm": 0.398416131734848,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9798,
+      "step": 49
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.47965478897094727,
+      "learning_rate": 1e-05,
+      "loss": 0.8143,
+      "step": 50
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "eval_loss": 0.8931620717048645,
+      "eval_runtime": 2.0295,
+      "eval_samples_per_second": 24.637,
+      "eval_steps_per_second": 6.406,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null