Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119ecd5d7b6095e1cf08f79e1ca81276cab54706ca71b30903734ded566594ed
+oid sha256:4864a7ed8852b0aff46533b3cad6403ec16eec0c495fe577725217cf4bbfc122
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775dfc6f8035c4c08e721e480ba711e0b95554112d7106b5b4c75ecb2ccf5812
+oid sha256:35ff159d78b660fc8c32394e7fab888b29dc6d2f984c955f80245f5eb3a5b67e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708431c6915be28f28c8059ca58e11b535f1e57bd16062295a391eb62dad5cc7
+oid sha256:b9bbd04226c3a5e7a7e036281fdd57bd382a828f1b5ddd3fcfc989a365a1df3c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70956df085496d9b235138b682a32fcd0df3b3dda0f99376a677e0e34e634e6
+oid sha256:1b1647c4e4025b9c4313dee3c2b781914b65a76e803f05550ef1c7466ee67b8e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d551fb423a536cf2bbe38ded2fc0c4100d4bf41390c8d32c03814d7e88e08b1
+oid sha256:c90c606c2cb4b03eaaf017eb4e268e4966b59a3e02b9530841acff6e6af243b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bba482284a3e976095907dcff0c409232c2c44427c6befb6684f3f1c862f664
+oid sha256:5d5a6027c5a823d5079d707c514204bad7b1189062a522f9e7296731549e143e
 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": 1.383743166923523,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005629996622002027,
+  "best_metric": 1.2644882202148438,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.011259993244004054,
   "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": 11.469,
       "eval_steps_per_second": 2.982,
       "step": 25
+    },
+    {
+      "epoch": 0.0058551964868821076,
+      "grad_norm": 1.440894365310669,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.437,
+      "step": 26
+    },
+    {
+      "epoch": 0.006080396351762189,
+      "grad_norm": 1.1735705137252808,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.3097,
+      "step": 27
+    },
+    {
+      "epoch": 0.00630559621664227,
+      "grad_norm": 1.1329774856567383,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3424,
+      "step": 28
+    },
+    {
+      "epoch": 0.006530796081522351,
+      "grad_norm": 0.9169742465019226,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3145,
+      "step": 29
+    },
+    {
+      "epoch": 0.006755995946402432,
+      "grad_norm": 0.9972285032272339,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.293,
+      "step": 30
+    },
+    {
+      "epoch": 0.006981195811282513,
+      "grad_norm": 0.7764326930046082,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1881,
+      "step": 31
+    },
+    {
+      "epoch": 0.007206395676162595,
+      "grad_norm": 0.9762597680091858,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2747,
+      "step": 32
+    },
+    {
+      "epoch": 0.007431595541042675,
+      "grad_norm": 0.9153839349746704,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3023,
+      "step": 33
+    },
+    {
+      "epoch": 0.0076567954059227564,
+      "grad_norm": 1.050321102142334,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.3403,
+      "step": 34
+    },
+    {
+      "epoch": 0.007881995270802838,
+      "grad_norm": 1.0363044738769531,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.356,
+      "step": 35
+    },
+    {
+      "epoch": 0.008107195135682919,
+      "grad_norm": 1.1488126516342163,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.4176,
+      "step": 36
+    },
+    {
+      "epoch": 0.008332395000563,
+      "grad_norm": 1.3928390741348267,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.483,
+      "step": 37
+    },
+    {
+      "epoch": 0.00855759486544308,
+      "grad_norm": 0.9444141387939453,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2024,
+      "step": 38
+    },
+    {
+      "epoch": 0.008782794730323161,
+      "grad_norm": 1.0579701662063599,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2282,
+      "step": 39
+    },
+    {
+      "epoch": 0.009007994595203243,
+      "grad_norm": 1.11298668384552,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2977,
+      "step": 40
+    },
+    {
+      "epoch": 0.009233194460083324,
+      "grad_norm": 0.9378632307052612,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3119,
+      "step": 41
+    },
+    {
+      "epoch": 0.009458394324963405,
+      "grad_norm": 0.821485161781311,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3546,
+      "step": 42
+    },
+    {
+      "epoch": 0.009683594189843487,
+      "grad_norm": 0.7577347755432129,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.3223,
+      "step": 43
+    },
+    {
+      "epoch": 0.009908794054723568,
+      "grad_norm": 0.7188370823860168,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.266,
+      "step": 44
+    },
+    {
+      "epoch": 0.010133993919603648,
+      "grad_norm": 0.7744938135147095,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.3402,
+      "step": 45
+    },
+    {
+      "epoch": 0.010359193784483729,
+      "grad_norm": 0.6904383301734924,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2561,
+      "step": 46
+    },
+    {
+      "epoch": 0.01058439364936381,
+      "grad_norm": 0.9495808482170105,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.395,
+      "step": 47
+    },
+    {
+      "epoch": 0.010809593514243892,
+      "grad_norm": 0.967199981212616,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4136,
+      "step": 48
+    },
+    {
+      "epoch": 0.011034793379123973,
+      "grad_norm": 1.231441855430603,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4461,
+      "step": 49
+    },
+    {
+      "epoch": 0.011259993244004054,
+      "grad_norm": 1.7717180252075195,
+      "learning_rate": 1e-05,
+      "loss": 1.4848,
+      "step": 50
+    },
+    {
+      "epoch": 0.011259993244004054,
+      "eval_loss": 1.2644882202148438,
+      "eval_runtime": 4.484,
+      "eval_samples_per_second": 11.151,
+      "eval_steps_per_second": 2.899,
+      "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": 1,
   "trial_name": null,
   "trial_params": null