Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262c3d41df8e8caadd5157de4230e13a063383f1ecb6bbd912ac2cf0f9da96ab
+oid sha256:df311620faa0f22c66acfd71a37087908190715ac1101e5630a74291ece48618
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f99e555452e6c937fab436760fe2b133f6bbf6ecb922dea43559f67d41b234
+oid sha256:25ce9ea86489d62517a8ce37c6ba68ce79900040e89e9905bbfc8221aa661e64
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee33139737f458b17e6d181bd21534b3a82739e23958a49ca431b8793550d45d
+oid sha256:0ad8f2d2dabbe15f8c4c0a68a5b5f17851cd64cd36243a68ad19166d85e5a042
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732ac0cccb65eeee2b9f7e76669a61010581171d7260ec32ffdc967d9e1a1b5b
+oid sha256:db261e667ddb28b9edc1f61971fa9d53daf1cc35a3e378aa56fe3c89c36c6708
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9cced44e88ca40cc37c8e917c06505caec9eed908a71d167105ea50f6cc2f0d
+oid sha256:afc287ae5718ef1bee1c547fa4a22141a6caa4b65bab5481be46239de710c0cf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f75881be2b458c7cc0b4fe3c2f87f57782f87392697cda3a03638674f6cb2b
+oid sha256:4fa753634a4caa49bc5fca9d7fb294c8a244fe4e9fcdeb3761e6484a582740e4
 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": 11.896537780761719,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6042296072507553,
+  "best_metric": 11.886322975158691,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2084592145015105,
   "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": 119.0,
       "eval_steps_per_second": 30.94,
       "step": 25
+    },
+    {
+      "epoch": 0.6283987915407855,
+      "grad_norm": 0.32997435331344604,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.8971,
+      "step": 26
+    },
+    {
+      "epoch": 0.6525679758308157,
+      "grad_norm": 0.30715274810791016,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.8941,
+      "step": 27
+    },
+    {
+      "epoch": 0.676737160120846,
+      "grad_norm": 0.29583367705345154,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.8952,
+      "step": 28
+    },
+    {
+      "epoch": 0.7009063444108762,
+      "grad_norm": 0.3171089291572571,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.8913,
+      "step": 29
+    },
+    {
+      "epoch": 0.7250755287009063,
+      "grad_norm": 0.35418152809143066,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.8905,
+      "step": 30
+    },
+    {
+      "epoch": 0.7492447129909365,
+      "grad_norm": 0.3350968062877655,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.8956,
+      "step": 31
+    },
+    {
+      "epoch": 0.7734138972809668,
+      "grad_norm": 0.3001876473426819,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.8968,
+      "step": 32
+    },
+    {
+      "epoch": 0.797583081570997,
+      "grad_norm": 0.3062438368797302,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.8931,
+      "step": 33
+    },
+    {
+      "epoch": 0.8217522658610272,
+      "grad_norm": 0.2976103723049164,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.8914,
+      "step": 34
+    },
+    {
+      "epoch": 0.8459214501510574,
+      "grad_norm": 0.2852192223072052,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.8905,
+      "step": 35
+    },
+    {
+      "epoch": 0.8700906344410876,
+      "grad_norm": 0.27989819645881653,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.8896,
+      "step": 36
+    },
+    {
+      "epoch": 0.8942598187311178,
+      "grad_norm": 0.2709686756134033,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.8924,
+      "step": 37
+    },
+    {
+      "epoch": 0.918429003021148,
+      "grad_norm": 0.25340571999549866,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.8902,
+      "step": 38
+    },
+    {
+      "epoch": 0.9425981873111783,
+      "grad_norm": 0.2850501835346222,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.8876,
+      "step": 39
+    },
+    {
+      "epoch": 0.9667673716012085,
+      "grad_norm": 0.28280991315841675,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.8828,
+      "step": 40
+    },
+    {
+      "epoch": 0.9909365558912386,
+      "grad_norm": 0.4183381497859955,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.8819,
+      "step": 41
+    },
+    {
+      "epoch": 1.0151057401812689,
+      "grad_norm": 0.5442397594451904,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 20.7319,
+      "step": 42
+    },
+    {
+      "epoch": 1.039274924471299,
+      "grad_norm": 0.25542905926704407,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.0284,
+      "step": 43
+    },
+    {
+      "epoch": 1.0634441087613293,
+      "grad_norm": 0.2500249147415161,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.705,
+      "step": 44
+    },
+    {
+      "epoch": 1.0876132930513596,
+      "grad_norm": 0.2602107524871826,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9346,
+      "step": 45
+    },
+    {
+      "epoch": 1.1117824773413898,
+      "grad_norm": 0.2505055367946625,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.8477,
+      "step": 46
+    },
+    {
+      "epoch": 1.13595166163142,
+      "grad_norm": 0.2512243390083313,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.8917,
+      "step": 47
+    },
+    {
+      "epoch": 1.1601208459214503,
+      "grad_norm": 0.2396506816148758,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.8054,
+      "step": 48
+    },
+    {
+      "epoch": 1.1842900302114803,
+      "grad_norm": 0.2575649917125702,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.848,
+      "step": 49
+    },
+    {
+      "epoch": 1.2084592145015105,
+      "grad_norm": 0.29371464252471924,
+      "learning_rate": 1e-05,
+      "loss": 12.1832,
+      "step": 50
+    },
+    {
+      "epoch": 1.2084592145015105,
+      "eval_loss": 11.886322975158691,
+      "eval_runtime": 0.4237,
+      "eval_samples_per_second": 118.019,
+      "eval_steps_per_second": 30.685,
+      "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": 208998073630720.0,
+  "total_flos": 418126689206272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null