Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764f98112260f13b34f8338d12dc74021d184151b45a339da1f5a2be57f1bc95
+oid sha256:79092d0b03d43c33785952a9cbdc831f70b510319c371529a32051d12a1370ea
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a65478e4369c8110de1b233a15e85e113f7a381f95bbdaa9494061b0f1935f
+oid sha256:b06a995921c958466a58340dec4c534b899efd24e967f12c8ee80210fa60b66c
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8777858d6602328ac39fa3dfc11add75ae644bead05ab56c881e8b8da418a73
+oid sha256:908ffddda760aa3c6929f01e42fc0e6a4ed7aa94568e361881d64e22ea4ac3a4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939d398f6ebbad9c45b59af75fa504c0ac03543d5b6ac43f3db40b62fdeb7861
+oid sha256:92db2b68105942a8c17402f6285f50db2ad83f6d3b229947a6531ea8edbcf3f9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92fc1af5a610d422c2121800a20ee91af28de264a22c80c1fb23073cfd99879
+oid sha256:37b838404a058d1dc983b71973305eeeee6fc5abbbd783b9b04bd802ab144c97
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7718c27b38473db144d23908e6bde585fc792441b82ddd4bb7fd97994c4ade79
+oid sha256:22f3558a08a1bef04a315bb00fcb23552d7e93bc890d565bc889b539da2bd4ea
 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": 1.6829791069030762,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.5131086142322099,
+  "best_metric": 1.6665854454040527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 3.041198501872659,
   "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": 27.357,
       "eval_steps_per_second": 7.113,
       "step": 25
+    },
+    {
+      "epoch": 1.5730337078651684,
+      "grad_norm": 0.33176758885383606,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.383,
+      "step": 26
+    },
+    {
+      "epoch": 1.6329588014981273,
+      "grad_norm": 0.3632158637046814,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5214,
+      "step": 27
+    },
+    {
+      "epoch": 1.6928838951310863,
+      "grad_norm": 0.38027459383010864,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5188,
+      "step": 28
+    },
+    {
+      "epoch": 1.7528089887640448,
+      "grad_norm": 0.29419416189193726,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3006,
+      "step": 29
+    },
+    {
+      "epoch": 1.8127340823970037,
+      "grad_norm": 0.3693186044692993,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3916,
+      "step": 30
+    },
+    {
+      "epoch": 1.8726591760299627,
+      "grad_norm": 0.3255068361759186,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.4854,
+      "step": 31
+    },
+    {
+      "epoch": 1.9325842696629212,
+      "grad_norm": 0.3359717130661011,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.598,
+      "step": 32
+    },
+    {
+      "epoch": 2.00749063670412,
+      "grad_norm": 0.4821653962135315,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.0111,
+      "step": 33
+    },
+    {
+      "epoch": 2.067415730337079,
+      "grad_norm": 0.30877596139907837,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2679,
+      "step": 34
+    },
+    {
+      "epoch": 2.1273408239700373,
+      "grad_norm": 0.3017288148403168,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.4301,
+      "step": 35
+    },
+    {
+      "epoch": 2.1872659176029963,
+      "grad_norm": 0.31851115822792053,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5345,
+      "step": 36
+    },
+    {
+      "epoch": 2.247191011235955,
+      "grad_norm": 0.500640869140625,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.3951,
+      "step": 37
+    },
+    {
+      "epoch": 2.3071161048689137,
+      "grad_norm": 0.29736557602882385,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2302,
+      "step": 38
+    },
+    {
+      "epoch": 2.3670411985018727,
+      "grad_norm": 0.28461888432502747,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3484,
+      "step": 39
+    },
+    {
+      "epoch": 2.4269662921348316,
+      "grad_norm": 0.3220164179801941,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4882,
+      "step": 40
+    },
+    {
+      "epoch": 2.48689138576779,
+      "grad_norm": 0.5141438245773315,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3637,
+      "step": 41
+    },
+    {
+      "epoch": 2.546816479400749,
+      "grad_norm": 0.2807631194591522,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2415,
+      "step": 42
+    },
+    {
+      "epoch": 2.606741573033708,
+      "grad_norm": 0.28683772683143616,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.405,
+      "step": 43
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.32397252321243286,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.3742,
+      "step": 44
+    },
+    {
+      "epoch": 2.7265917602996255,
+      "grad_norm": 0.4401939809322357,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.4012,
+      "step": 45
+    },
+    {
+      "epoch": 2.7865168539325844,
+      "grad_norm": 0.3006478548049927,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2044,
+      "step": 46
+    },
+    {
+      "epoch": 2.846441947565543,
+      "grad_norm": 0.3210304081439972,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.3406,
+      "step": 47
+    },
+    {
+      "epoch": 2.906367041198502,
+      "grad_norm": 0.311988890171051,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.3981,
+      "step": 48
+    },
+    {
+      "epoch": 2.966292134831461,
+      "grad_norm": 0.4421902000904083,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5215,
+      "step": 49
+    },
+    {
+      "epoch": 3.041198501872659,
+      "grad_norm": 0.4435513913631439,
+      "learning_rate": 1e-05,
+      "loss": 1.7807,
+      "step": 50
+    },
+    {
+      "epoch": 3.041198501872659,
+      "eval_loss": 1.6665854454040527,
+      "eval_runtime": 1.825,
+      "eval_samples_per_second": 27.397,
+      "eval_steps_per_second": 7.123,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null