Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5937e1f285fef1e643a1a54f59b012e292d5058d4a485bfd8cc66724a1a89f37
+oid sha256:f1cdfe1541e338b404a548f667f75b3b8906ac0ffdba88e9728477b79efbe7b9
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a13c65f47ce49ba5aa210f9d08b514acf5df3bb8ce552bf8c010a96396086a75
+oid sha256:55cf943477825295a6590e809eebfa29be55e3aef70e06d73ec8dabddb3391e0
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a052395c354098758284259a8f7a15eae4d4f2f12f0055ca70784467e2a072eb
+oid sha256:2bc0af35cf49d8c6dcf97e605ed3b67963fbe210de4265a0bb4305d385f1862f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03097149c8948e152115aae72779fc785d3c2bed84e89db5ecb118ce00d2978
+oid sha256:4b2ce2b7ffe62d289ef160457881667d9616f49754b0012d8ed945f3fe354b3e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f577c64256b7dae8b8a20d9364b19ba47e66327aa97d1fd584db28b5c64d2c93
+oid sha256:2b93a3f73856c1e1ab79ad0d85175a3f10d921f2a126453980a97f4d435c9a40
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52edc22620d116683bb850d78184a6b76cf4d47e093558a6b3e8766ed2529777
+oid sha256:a25234f641d98e0f912f2991ba0d52608e055387c29f71a25dd61da204159623
 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": 2.1400809288024902,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.024792363951902815,
+  "best_metric": 2.112521171569824,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04958472790380563,
   "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": 34.882,
       "eval_steps_per_second": 9.069,
       "step": 25
+    },
+    {
+      "epoch": 0.025784058509978926,
+      "grad_norm": 0.6622329950332642,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1491,
+      "step": 26
+    },
+    {
+      "epoch": 0.02677575306805504,
+      "grad_norm": 0.6250461339950562,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.1379,
+      "step": 27
+    },
+    {
+      "epoch": 0.02776744762613115,
+      "grad_norm": 0.5818557143211365,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0769,
+      "step": 28
+    },
+    {
+      "epoch": 0.028759142184207265,
+      "grad_norm": 0.6050412058830261,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.135,
+      "step": 29
+    },
+    {
+      "epoch": 0.029750836742283376,
+      "grad_norm": 0.634053111076355,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0189,
+      "step": 30
+    },
+    {
+      "epoch": 0.03074253130035949,
+      "grad_norm": 0.6110137701034546,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0755,
+      "step": 31
+    },
+    {
+      "epoch": 0.031734225858435605,
+      "grad_norm": 0.5948219299316406,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.0746,
+      "step": 32
+    },
+    {
+      "epoch": 0.03272592041651171,
+      "grad_norm": 0.5863483548164368,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.1102,
+      "step": 33
+    },
+    {
+      "epoch": 0.03371761497458783,
+      "grad_norm": 0.5736821293830872,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9682,
+      "step": 34
+    },
+    {
+      "epoch": 0.03470930953266394,
+      "grad_norm": 0.5776990652084351,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.0821,
+      "step": 35
+    },
+    {
+      "epoch": 0.03570100409074005,
+      "grad_norm": 0.6396189332008362,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.1349,
+      "step": 36
+    },
+    {
+      "epoch": 0.03669269864881616,
+      "grad_norm": 0.606553852558136,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.0829,
+      "step": 37
+    },
+    {
+      "epoch": 0.03768439320689228,
+      "grad_norm": 0.6115500330924988,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.2099,
+      "step": 38
+    },
+    {
+      "epoch": 0.03867608776496839,
+      "grad_norm": 0.606846272945404,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.1354,
+      "step": 39
+    },
+    {
+      "epoch": 0.0396677823230445,
+      "grad_norm": 0.5994709134101868,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.1579,
+      "step": 40
+    },
+    {
+      "epoch": 0.040659476881120614,
+      "grad_norm": 0.5895546674728394,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.0635,
+      "step": 41
+    },
+    {
+      "epoch": 0.04165117143919673,
+      "grad_norm": 0.5925672650337219,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.0997,
+      "step": 42
+    },
+    {
+      "epoch": 0.04264286599727284,
+      "grad_norm": 0.6125743985176086,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.0312,
+      "step": 43
+    },
+    {
+      "epoch": 0.04363456055534895,
+      "grad_norm": 0.593887448310852,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.0319,
+      "step": 44
+    },
+    {
+      "epoch": 0.044626255113425065,
+      "grad_norm": 0.5913119316101074,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.0568,
+      "step": 45
+    },
+    {
+      "epoch": 0.04561794967150118,
+      "grad_norm": 0.6023686528205872,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.1055,
+      "step": 46
+    },
+    {
+      "epoch": 0.04660964422957729,
+      "grad_norm": 0.5734410881996155,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.0804,
+      "step": 47
+    },
+    {
+      "epoch": 0.0476013387876534,
+      "grad_norm": 0.601888120174408,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.1679,
+      "step": 48
+    },
+    {
+      "epoch": 0.048593033345729515,
+      "grad_norm": 0.6172356605529785,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.2193,
+      "step": 49
+    },
+    {
+      "epoch": 0.04958472790380563,
+      "grad_norm": 0.6247469782829285,
+      "learning_rate": 1e-05,
+      "loss": 2.0932,
+      "step": 50
+    },
+    {
+      "epoch": 0.04958472790380563,
+      "eval_loss": 2.112521171569824,
+      "eval_runtime": 1.4403,
+      "eval_samples_per_second": 34.715,
+      "eval_steps_per_second": 9.026,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null