Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9a36195bc9cf219ae53a8eb80a9c497c8eb5cd4c2eafb936a3e97d8b26217f
+oid sha256:1474f6f9d559e6e70ac14131c8f03d67e08b5ba6a023518ffad4ca8a1f360a66
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfd4ea00d8dafee12613277c03d6f6a812b43331912e9c4070f787b9ef4c367
+oid sha256:207bda815f0767c76c372a677b159fb23ecdbe7425891ff96bfb281d3b104dd3
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15aa704709262af39b744503ee069537790c0c64b583c2838ff68ddfc090fe95
+oid sha256:1592db3805eafdb4c9e2185d509843b01eaeb816ba62b62a9261d879c42f516b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a588b64fbf6bcc17e662d18a20337c9b82cdf061057c418ec4a636d415688552
+oid sha256:92d704ee7df4a32889ee4b90a815ed0c14f401071f202ac1517cb34d5b8a0519
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be94fe9dfd4ecf78766e995cedde1b98787eeaed252388999bd9b5a1134011b8
+oid sha256:c7d038fcac5afb060789f8b4a33b3ca597bb8f8a020746a381a96d4ba711cb13
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600cae40ad57d673f8eafe242c0120985fcf9039cceb8993c8b1ce17490c9d62
+oid sha256:8f8da15467b78dc159b5a583fd59db3b47807d6596bc3ae1e3a24737491e62de
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1300944834947586,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.32480714575720665,
+  "best_metric": 0.032049428671598434,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6496142915144133,
   "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": 33.599,
       "eval_steps_per_second": 8.736,
       "step": 25
+    },
+    {
+      "epoch": 0.3377994315874949,
+      "grad_norm": 7.682220458984375,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.1106,
+      "step": 26
+    },
+    {
+      "epoch": 0.3507917174177832,
+      "grad_norm": 8.865133285522461,
+      "learning_rate": 7.75e-05,
+      "loss": 0.1535,
+      "step": 27
+    },
+    {
+      "epoch": 0.3637840032480715,
+      "grad_norm": 3.1668100357055664,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0889,
+      "step": 28
+    },
+    {
+      "epoch": 0.37677628907835975,
+      "grad_norm": 2.320821523666382,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0714,
+      "step": 29
+    },
+    {
+      "epoch": 0.38976857490864797,
+      "grad_norm": 3.224240303039551,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0948,
+      "step": 30
+    },
+    {
+      "epoch": 0.40276086073893624,
+      "grad_norm": 2.759305953979492,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0817,
+      "step": 31
+    },
+    {
+      "epoch": 0.4157531465692245,
+      "grad_norm": 1.3898932933807373,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0546,
+      "step": 32
+    },
+    {
+      "epoch": 0.4287454323995128,
+      "grad_norm": 2.0559136867523193,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0792,
+      "step": 33
+    },
+    {
+      "epoch": 0.44173771822980107,
+      "grad_norm": 1.2107505798339844,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0658,
+      "step": 34
+    },
+    {
+      "epoch": 0.45473000406008934,
+      "grad_norm": 0.8181975483894348,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0573,
+      "step": 35
+    },
+    {
+      "epoch": 0.46772228989037756,
+      "grad_norm": 0.8736940622329712,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0906,
+      "step": 36
+    },
+    {
+      "epoch": 0.48071457572066584,
+      "grad_norm": 1.7226741313934326,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0669,
+      "step": 37
+    },
+    {
+      "epoch": 0.4937068615509541,
+      "grad_norm": 1.7814589738845825,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0771,
+      "step": 38
+    },
+    {
+      "epoch": 0.5066991473812423,
+      "grad_norm": 1.8109633922576904,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0613,
+      "step": 39
+    },
+    {
+      "epoch": 0.5196914332115307,
+      "grad_norm": 2.7186203002929688,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0735,
+      "step": 40
+    },
+    {
+      "epoch": 0.5326837190418189,
+      "grad_norm": 2.1896440982818604,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0928,
+      "step": 41
+    },
+    {
+      "epoch": 0.5456760048721072,
+      "grad_norm": 1.4338561296463013,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0955,
+      "step": 42
+    },
+    {
+      "epoch": 0.5586682907023954,
+      "grad_norm": 1.8646522760391235,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0481,
+      "step": 43
+    },
+    {
+      "epoch": 0.5716605765326838,
+      "grad_norm": 2.171997547149658,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0493,
+      "step": 44
+    },
+    {
+      "epoch": 0.584652862362972,
+      "grad_norm": 1.8785721063613892,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0529,
+      "step": 45
+    },
+    {
+      "epoch": 0.5976451481932602,
+      "grad_norm": 0.8664989471435547,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0541,
+      "step": 46
+    },
+    {
+      "epoch": 0.6106374340235485,
+      "grad_norm": 2.1312761306762695,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0664,
+      "step": 47
+    },
+    {
+      "epoch": 0.6236297198538368,
+      "grad_norm": 2.3210947513580322,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.095,
+      "step": 48
+    },
+    {
+      "epoch": 0.6366220056841251,
+      "grad_norm": 3.8043196201324463,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0916,
+      "step": 49
+    },
+    {
+      "epoch": 0.6496142915144133,
+      "grad_norm": 1.2356327772140503,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0625,
+      "step": 50
+    },
+    {
+      "epoch": 0.6496142915144133,
+      "eval_loss": 0.032049428671598434,
+      "eval_runtime": 1.5457,
+      "eval_samples_per_second": 32.348,
+      "eval_steps_per_second": 8.411,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null