Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b066118c9f69b978c46c5dc6eaef172bf4a12d7c4e4ba45237fff6feb0a9916
+oid sha256:6c1a3be62e218a0d3fb800c239bab9cdc0f58263e1cb90486243b74fb61fb418
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8492c1303e99a69ee3f352ff666d1246c83c15c05021d40a89fd50742377beb9
+oid sha256:8cf6f8f5e635ba680bc737a6be5d1ddfd9c847608964c80d9c9730d7f50bdd95
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30491503dd69b955e7adaaa9615fc4b61679603757911929aafbaf4322364aa5
+oid sha256:17b4718b5f964da24c95733eabd77ac06799db47bcc6e1462fff10581a5239a6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1248d514e24a2c4ed2ae70c553ba7158db855112875c409618ee6202a92ffa1e
+oid sha256:f21d20f8d53681043f988e30be18ea76768e0f93fab6cde31eaebb532061f1b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09a0eeeed319db2e8c2b885480966423638da5d6b765eebcdc322a83c1d7265
+oid sha256:097a1bbb2cc8787b5fdfe5a84dde5f01674c918037e243808d9754680195c20a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20df5063c6adccddea8ad33f22a735f9a58e071601486139f1e19b87a19922b0
+oid sha256:98e68677e5b7cb8cf42438036dab091aaf9e1fb327fa27eb0c517119e60b8a77
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9656898975372314,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014502211587267059,
+  "best_metric": 1.908427357673645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.029004423174534118,
   "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": 132.686,
       "eval_steps_per_second": 16.589,
       "step": 25
+    },
+    {
+      "epoch": 0.01508230005075774,
+      "grad_norm": 0.9242467880249023,
+      "learning_rate": 5e-05,
+      "loss": 2.4769,
+      "step": 26
+    },
+    {
+      "epoch": 0.015662388514248424,
+      "grad_norm": 0.8354268074035645,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2688,
+      "step": 27
+    },
+    {
+      "epoch": 0.016242476977739104,
+      "grad_norm": 0.8029454350471497,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1763,
+      "step": 28
+    },
+    {
+      "epoch": 0.016822565441229786,
+      "grad_norm": 0.752227246761322,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2302,
+      "step": 29
+    },
+    {
+      "epoch": 0.01740265390472047,
+      "grad_norm": 0.7801461219787598,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.9811,
+      "step": 30
+    },
+    {
+      "epoch": 0.017982742368211152,
+      "grad_norm": 0.8186996579170227,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0214,
+      "step": 31
+    },
+    {
+      "epoch": 0.018562830831701835,
+      "grad_norm": 0.8529973030090332,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9914,
+      "step": 32
+    },
+    {
+      "epoch": 0.019142919295192518,
+      "grad_norm": 0.85138338804245,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9744,
+      "step": 33
+    },
+    {
+      "epoch": 0.0197230077586832,
+      "grad_norm": 0.88033127784729,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0076,
+      "step": 34
+    },
+    {
+      "epoch": 0.020303096222173883,
+      "grad_norm": 0.9876776337623596,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9631,
+      "step": 35
+    },
+    {
+      "epoch": 0.020883184685664562,
+      "grad_norm": 0.9123481512069702,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9236,
+      "step": 36
+    },
+    {
+      "epoch": 0.021463273149155245,
+      "grad_norm": 1.1922837495803833,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7778,
+      "step": 37
+    },
+    {
+      "epoch": 0.022043361612645928,
+      "grad_norm": 0.5611425638198853,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3327,
+      "step": 38
+    },
+    {
+      "epoch": 0.02262345007613661,
+      "grad_norm": 0.612273633480072,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2909,
+      "step": 39
+    },
+    {
+      "epoch": 0.023203538539627293,
+      "grad_norm": 0.6433464288711548,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.1686,
+      "step": 40
+    },
+    {
+      "epoch": 0.023783627003117976,
+      "grad_norm": 0.6561065912246704,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0914,
+      "step": 41
+    },
+    {
+      "epoch": 0.02436371546660866,
+      "grad_norm": 0.7109490633010864,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.003,
+      "step": 42
+    },
+    {
+      "epoch": 0.024943803930099342,
+      "grad_norm": 0.690317690372467,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.9442,
+      "step": 43
+    },
+    {
+      "epoch": 0.02552389239359002,
+      "grad_norm": 0.6933758854866028,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9599,
+      "step": 44
+    },
+    {
+      "epoch": 0.026103980857080704,
+      "grad_norm": 0.7534849047660828,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9908,
+      "step": 45
+    },
+    {
+      "epoch": 0.026684069320571387,
+      "grad_norm": 0.7282309532165527,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9465,
+      "step": 46
+    },
+    {
+      "epoch": 0.02726415778406207,
+      "grad_norm": 0.7184540629386902,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8432,
+      "step": 47
+    },
+    {
+      "epoch": 0.027844246247552752,
+      "grad_norm": 0.7012395262718201,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8893,
+      "step": 48
+    },
+    {
+      "epoch": 0.028424334711043435,
+      "grad_norm": 0.8472903370857239,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8058,
+      "step": 49
+    },
+    {
+      "epoch": 0.029004423174534118,
+      "grad_norm": 1.0240179300308228,
+      "learning_rate": 0.0,
+      "loss": 1.8189,
+      "step": 50
+    },
+    {
+      "epoch": 0.029004423174534118,
+      "eval_loss": 1.908427357673645,
+      "eval_runtime": 174.9007,
+      "eval_samples_per_second": 132.801,
+      "eval_steps_per_second": 16.604,
+      "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": 2.9742338750283776e+16,
+  "total_flos": 5.954927461400576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null