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:afd12a11cf23dc342e93905710241434d0113b0544af9ff28a2dc9ccf9963829
+oid sha256:8a8b2256da4f55f1330a12669ac4662144edeba45f53744a73ecab97620169be
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93fbc3b3ad213bba7d8d90eede181f7f029a43ea3214d11000eb1af769c2e1a3
+oid sha256:1c5c917954384172b77f6e0f1d9aedae41e2b950a476e66c2d916f54ee920805
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4151da4ec5348f7508d50736b22f32303be2446f29cb383dabdbbd7009b37e7b
+oid sha256:f3e984d30b6d33fe5881cc26f9576698bc5ee30073ddc29a5af9c3e7d59c130e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f224b33462bde2d3c54a877f5eca6199b38dfeae0d2981cdd05d919e5b8c57c1
+oid sha256:d57aff9af9a65c89530c41f73bff215dd8361914e404df36753c8aff94f585d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56243470f5855ea6ae659945321b6c99c3391f494baeef293bf78caefe38be6
+oid sha256:1f47848f119e37c10d539ec971f712a6e53a924943b147a3c768b198bc4bdfcb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd01117a9b1d61f1e88fe9adb1770618730cf604aee82987331e0c0faaa9dd56
+oid sha256:a4bdaaee837f42aaad1b38a8bc73b27f1f8b84025a31b7b430e2b1b57d70cfe8
 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": 1.1190599203109741,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14738393515106854,
+  "best_metric": 1.026161789894104,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2947678703021371,
   "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": 15.431,
       "eval_steps_per_second": 4.012,
       "step": 25
+    },
+    {
+      "epoch": 0.15327929255711129,
+      "grad_norm": 0.3763660490512848,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9391,
+      "step": 26
+    },
+    {
+      "epoch": 0.159174649963154,
+      "grad_norm": 0.5650990605354309,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.262,
+      "step": 27
+    },
+    {
+      "epoch": 0.16507000736919675,
+      "grad_norm": 0.5373654961585999,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.221,
+      "step": 28
+    },
+    {
+      "epoch": 0.1709653647752395,
+      "grad_norm": 0.500039279460907,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.196,
+      "step": 29
+    },
+    {
+      "epoch": 0.17686072218128224,
+      "grad_norm": 0.6380913853645325,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1443,
+      "step": 30
+    },
+    {
+      "epoch": 0.18275607958732498,
+      "grad_norm": 0.5256316661834717,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0691,
+      "step": 31
+    },
+    {
+      "epoch": 0.18865143699336773,
+      "grad_norm": 0.4717680513858795,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0654,
+      "step": 32
+    },
+    {
+      "epoch": 0.19454679439941047,
+      "grad_norm": 0.4717838168144226,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0109,
+      "step": 33
+    },
+    {
+      "epoch": 0.20044215180545322,
+      "grad_norm": 0.5672800540924072,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9381,
+      "step": 34
+    },
+    {
+      "epoch": 0.20633750921149593,
+      "grad_norm": 0.5292719602584839,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.924,
+      "step": 35
+    },
+    {
+      "epoch": 0.21223286661753868,
+      "grad_norm": 2.673468589782715,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.4451,
+      "step": 36
+    },
+    {
+      "epoch": 0.21812822402358142,
+      "grad_norm": 2.2796475887298584,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.4291,
+      "step": 37
+    },
+    {
+      "epoch": 0.22402358142962417,
+      "grad_norm": 0.26701611280441284,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9015,
+      "step": 38
+    },
+    {
+      "epoch": 0.22991893883566691,
+      "grad_norm": 0.3951334059238434,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2104,
+      "step": 39
+    },
+    {
+      "epoch": 0.23581429624170966,
+      "grad_norm": 0.42779994010925293,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.232,
+      "step": 40
+    },
+    {
+      "epoch": 0.2417096536477524,
+      "grad_norm": 0.4500541090965271,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1563,
+      "step": 41
+    },
+    {
+      "epoch": 0.24760501105379515,
+      "grad_norm": 0.4688700735569,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.152,
+      "step": 42
+    },
+    {
+      "epoch": 0.25350036845983787,
+      "grad_norm": 0.4694727659225464,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.0749,
+      "step": 43
+    },
+    {
+      "epoch": 0.2593957258658806,
+      "grad_norm": 0.4634798765182495,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0726,
+      "step": 44
+    },
+    {
+      "epoch": 0.26529108327192336,
+      "grad_norm": 0.4798823893070221,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9676,
+      "step": 45
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.4697292447090149,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9161,
+      "step": 46
+    },
+    {
+      "epoch": 0.27708179808400885,
+      "grad_norm": 0.5120259523391724,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8731,
+      "step": 47
+    },
+    {
+      "epoch": 0.2829771554900516,
+      "grad_norm": 0.6791577339172363,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0644,
+      "step": 48
+    },
+    {
+      "epoch": 0.28887251289609434,
+      "grad_norm": 0.7600632309913635,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.3989,
+      "step": 49
+    },
+    {
+      "epoch": 0.2947678703021371,
+      "grad_norm": 0.7026044726371765,
+      "learning_rate": 1e-05,
+      "loss": 1.4065,
+      "step": 50
+    },
+    {
+      "epoch": 0.2947678703021371,
+      "eval_loss": 1.026161789894104,
+      "eval_runtime": 3.2414,
+      "eval_samples_per_second": 15.426,
+      "eval_steps_per_second": 4.011,
+      "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": 2.8313616161282458e+17,
+  "total_flos": 5.652178131914588e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null