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:efbddcd3cb275df2ea56fa0c8b9941edfb01b0025534fba57d50d541be502f6d
+oid sha256:1482796b1aed6a1df089e2d33ab0e61092f09cfb90a4eeba6fc103c101bbb732
 size 261131840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8988b69d971815d277a6cac8c5c39df4585d15faa51d45e83159d5a665d82a
+oid sha256:e21d944f60d456c2d6ad8d8e0b96acf6cbbec743610154a744f9e06497a99d99
 size 522406650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250fac0481afeca9564cc785af64705a1a0073025c50afffac2ba138110fa5cb
+oid sha256:2c2572a8a03e5d689f02af1451d1c5ca7c60301095af061a82420a7f5aeb9f20
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1eac1c56706269cbaf420bc150d99af3d7c59e4465a24cc03a08356d6ccd1b
+oid sha256:1096d6c92360329110b3330409e7ab40ea40fc787fea5f920f5e1c27ef617e20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c3ee880c60d81b45bcf3798558d68637dc71377bae9be667e736c9753956de
+oid sha256:b47fb0ef0b76b0ec55148efb904951b04e98ae0b59ed21d9df2314e12208331e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb14c8e901ec85d3a53c149e66ef6c281bdd2dba4ca1cfbe62fa319f866eb16f
+oid sha256:a6497a5322d8fbaaefe3155f9ca4e7469c110fd5be9e9e0e4a5e32b91b540778
 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": 3.1194334030151367,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0648403306856865,
+  "best_metric": 3.035244941711426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.129680661371373,
   "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": 16.04,
       "eval_steps_per_second": 4.17,
       "step": 25
+    },
+    {
+      "epoch": 0.06743394391311396,
+      "grad_norm": 21.67609977722168,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 44.0538,
+      "step": 26
+    },
+    {
+      "epoch": 0.07002755714054142,
+      "grad_norm": 24.147232055664062,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 48.1777,
+      "step": 27
+    },
+    {
+      "epoch": 0.07262117036796888,
+      "grad_norm": 25.220670700073242,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 49.6091,
+      "step": 28
+    },
+    {
+      "epoch": 0.07521478359539634,
+      "grad_norm": 21.60172462463379,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 49.3253,
+      "step": 29
+    },
+    {
+      "epoch": 0.0778083968228238,
+      "grad_norm": 19.519107818603516,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 51.2563,
+      "step": 30
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 16.33799171447754,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 50.3858,
+      "step": 31
+    },
+    {
+      "epoch": 0.08299562327767872,
+      "grad_norm": 14.904318809509277,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 50.18,
+      "step": 32
+    },
+    {
+      "epoch": 0.08558923650510618,
+      "grad_norm": 14.375073432922363,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 51.0253,
+      "step": 33
+    },
+    {
+      "epoch": 0.08818284973253364,
+      "grad_norm": 15.682596206665039,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 52.4275,
+      "step": 34
+    },
+    {
+      "epoch": 0.0907764629599611,
+      "grad_norm": 17.654769897460938,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 52.5927,
+      "step": 35
+    },
+    {
+      "epoch": 0.09337007618738856,
+      "grad_norm": 22.502099990844727,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 57.4791,
+      "step": 36
+    },
+    {
+      "epoch": 0.09596368941481602,
+      "grad_norm": 31.115272521972656,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 61.1302,
+      "step": 37
+    },
+    {
+      "epoch": 0.09855730264224348,
+      "grad_norm": 24.96523666381836,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 58.228,
+      "step": 38
+    },
+    {
+      "epoch": 0.10115091586967094,
+      "grad_norm": 15.320883750915527,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 44.4613,
+      "step": 39
+    },
+    {
+      "epoch": 0.1037445290970984,
+      "grad_norm": 16.11422348022461,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 47.0968,
+      "step": 40
+    },
+    {
+      "epoch": 0.10633814232452586,
+      "grad_norm": 15.900169372558594,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 46.3016,
+      "step": 41
+    },
+    {
+      "epoch": 0.10893175555195332,
+      "grad_norm": 15.33053970336914,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 46.9842,
+      "step": 42
+    },
+    {
+      "epoch": 0.11152536877938077,
+      "grad_norm": 13.822281837463379,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 46.4142,
+      "step": 43
+    },
+    {
+      "epoch": 0.11411898200680823,
+      "grad_norm": 13.50814151763916,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 48.2081,
+      "step": 44
+    },
+    {
+      "epoch": 0.11671259523423569,
+      "grad_norm": 12.32927131652832,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 49.4131,
+      "step": 45
+    },
+    {
+      "epoch": 0.11930620846166315,
+      "grad_norm": 13.220865249633789,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 49.9703,
+      "step": 46
+    },
+    {
+      "epoch": 0.12189982168909061,
+      "grad_norm": 16.602933883666992,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 53.779,
+      "step": 47
+    },
+    {
+      "epoch": 0.12449343491651807,
+      "grad_norm": 19.967239379882812,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 54.368,
+      "step": 48
+    },
+    {
+      "epoch": 0.12708704814394553,
+      "grad_norm": 24.27589988708496,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 56.5035,
+      "step": 49
+    },
+    {
+      "epoch": 0.129680661371373,
+      "grad_norm": 43.7401123046875,
+      "learning_rate": 1e-05,
+      "loss": 65.2046,
+      "step": 50
+    },
+    {
+      "epoch": 0.129680661371373,
+      "eval_loss": 3.035244941711426,
+      "eval_runtime": 3.1129,
+      "eval_samples_per_second": 16.062,
+      "eval_steps_per_second": 4.176,
+      "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": 2.631214808694784e+17,
+  "total_flos": 5.262429617389568e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null