Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84485bdc3ee9d280dfc65bc0450c65a91b4f0f76fd009910ba929077e955c344
+oid sha256:782224350b516c0ea86912b228ee109a49543e303d03715806112028f5d4513f
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59fb7224a59d4c68c3446ca92d8f97ef61ef29c0341628bdc9b62f71059219f9
+oid sha256:5a47bfd3555f403a1d1d492c95d1af8fbd7a2279f317883d197b0a4fc782381a
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba084912db5c0334ea63ad5403e3d0a27339d3408e43c08ab67f21d51691ad8b
+oid sha256:5599ced9e58ba6a6a4a00223cfa6b648f833d9be06aa3aa0322c480ff5c217c8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d23a5adf86acd3096a0943a21fab885c08854cd5d5557ae05e2c064c8a10f4
+oid sha256:744ad1abec995a8312de7ea31967df2172a1acfe4ecbd86de0ec11bfbd487c82
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3acacb0c95c81119f866752edc83bd911f07f658d71c0a2e001970a1166f2b54
+oid sha256:1145b42b815bbd9b8cdb8cd4b7487efcabbe18a2231d966b1a25b694a7c6e613
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05157cde8ebbd91ceb0a07b70227f0a90c4fa7fcc91c51ac94b21ab9779f6288
+oid sha256:6de0b888cdad6fbfc2ce6b54f469dd02af5df67af9430c7bc0e3c91627acb128
 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": 0.33710530400276184,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06397952655150352,
+  "best_metric": 0.33107176423072815,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12795905310300704,
   "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": 14.471,
       "eval_steps_per_second": 3.762,
       "step": 25
+    },
+    {
+      "epoch": 0.06653870761356366,
+      "grad_norm": 0.14013031125068665,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.34,
+      "step": 26
+    },
+    {
+      "epoch": 0.0690978886756238,
+      "grad_norm": 0.1556030660867691,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3469,
+      "step": 27
+    },
+    {
+      "epoch": 0.07165706973768395,
+      "grad_norm": 0.16703511774539948,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3745,
+      "step": 28
+    },
+    {
+      "epoch": 0.07421625079974409,
+      "grad_norm": 0.1567988246679306,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.373,
+      "step": 29
+    },
+    {
+      "epoch": 0.07677543186180422,
+      "grad_norm": 0.16023825109004974,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07933461292386436,
+      "grad_norm": 0.15885958075523376,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3569,
+      "step": 31
+    },
+    {
+      "epoch": 0.0818937939859245,
+      "grad_norm": 0.15370488166809082,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3678,
+      "step": 32
+    },
+    {
+      "epoch": 0.08445297504798464,
+      "grad_norm": 0.16905587911605835,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3617,
+      "step": 33
+    },
+    {
+      "epoch": 0.08701215611004479,
+      "grad_norm": 0.18098001182079315,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3593,
+      "step": 34
+    },
+    {
+      "epoch": 0.08957133717210493,
+      "grad_norm": 0.17493058741092682,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3738,
+      "step": 35
+    },
+    {
+      "epoch": 0.09213051823416507,
+      "grad_norm": 0.18294112384319305,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3448,
+      "step": 36
+    },
+    {
+      "epoch": 0.09468969929622521,
+      "grad_norm": 0.1955849975347519,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3488,
+      "step": 37
+    },
+    {
+      "epoch": 0.09724888035828536,
+      "grad_norm": 0.1269148886203766,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3316,
+      "step": 38
+    },
+    {
+      "epoch": 0.09980806142034548,
+      "grad_norm": 0.11683975160121918,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3704,
+      "step": 39
+    },
+    {
+      "epoch": 0.10236724248240563,
+      "grad_norm": 0.1327202469110489,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3693,
+      "step": 40
+    },
+    {
+      "epoch": 0.10492642354446577,
+      "grad_norm": 0.13617070019245148,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3638,
+      "step": 41
+    },
+    {
+      "epoch": 0.10748560460652591,
+      "grad_norm": 0.1420089602470398,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3789,
+      "step": 42
+    },
+    {
+      "epoch": 0.11004478566858605,
+      "grad_norm": 0.13661804795265198,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3617,
+      "step": 43
+    },
+    {
+      "epoch": 0.1126039667306462,
+      "grad_norm": 0.18816272914409637,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3645,
+      "step": 44
+    },
+    {
+      "epoch": 0.11516314779270634,
+      "grad_norm": 0.1535802036523819,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3545,
+      "step": 45
+    },
+    {
+      "epoch": 0.11772232885476648,
+      "grad_norm": 0.15371079742908478,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3251,
+      "step": 46
+    },
+    {
+      "epoch": 0.12028150991682661,
+      "grad_norm": 0.1656692773103714,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3545,
+      "step": 47
+    },
+    {
+      "epoch": 0.12284069097888675,
+      "grad_norm": 0.17977501451969147,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3567,
+      "step": 48
+    },
+    {
+      "epoch": 0.1253998720409469,
+      "grad_norm": 0.17077907919883728,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3524,
+      "step": 49
+    },
+    {
+      "epoch": 0.12795905310300704,
+      "grad_norm": 0.19544556736946106,
+      "learning_rate": 1e-05,
+      "loss": 0.3457,
+      "step": 50
+    },
+    {
+      "epoch": 0.12795905310300704,
+      "eval_loss": 0.33107176423072815,
+      "eval_runtime": 3.4346,
+      "eval_samples_per_second": 14.558,
+      "eval_steps_per_second": 3.785,
+      "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": 3.340558550601564e+17,
+  "total_flos": 6.674900178991841e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null