Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4c916c6eeea576be930c43749310aef119e570f04ee0b90e828c201adda0a0
+oid sha256:87c92c058ba2f5f4bda5e5218b0e10228f00884f4f10e38e2269260a9b6eca92
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892b3d80524a89c6be3349b29aa25e62bf43a1f3e1b7ef8351db0f307000627d
+oid sha256:33c7a63589f00ab31c6ba07c23790ccbdf188b766c126236f16016269cfc23cf
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61a97895a589bb551eebe14ca96f8a6ddc0824bf17d3e639acd5e0a8bd0b276
+oid sha256:619d8a91381c8f893e6203a86f380ced90d180a08d12fae876d7ea0c06ab2b00
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc1887e8603f2b5aaee824815c12056e20544c807b80c6bd05ac5423e50de82
+oid sha256:2913fccdef36919bb2f011279eea5e19b38a3c08385de54504f3f5d8e8a624d8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1d75fe770f1ecdcbea06301ac63dbf5a3bcf245093ce3e4b1e5c3c56fd9e88
+oid sha256:f5c8fe3ac6db7d9195bac33c58b9fc88ecec8187bf55d51f187c9be783b9f93d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1ac28e177c6a7d11040ec4fc04bc06983068c5af4d3e66eccb8554f52044e7
+oid sha256:e24fa0f146e95e969ae981049759503c019b8e33139203dbd1c607d6618650f0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1385380029678345,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.4071246819338422,
+  "best_metric": 1.1252893209457397,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.6106870229007634,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 15.348,
       "eval_steps_per_second": 3.99,
       "step": 50
+    },
+    {
+      "epoch": 0.4152671755725191,
+      "grad_norm": 0.25706854462623596,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 1.3684,
+      "step": 51
+    },
+    {
+      "epoch": 0.42340966921119594,
+      "grad_norm": 0.2687229514122009,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 1.2704,
+      "step": 52
+    },
+    {
+      "epoch": 0.4315521628498728,
+      "grad_norm": 0.2694632411003113,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 1.2929,
+      "step": 53
+    },
+    {
+      "epoch": 0.4396946564885496,
+      "grad_norm": 0.27409684658050537,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 1.1768,
+      "step": 54
+    },
+    {
+      "epoch": 0.44783715012722647,
+      "grad_norm": 0.2727748453617096,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 1.1819,
+      "step": 55
+    },
+    {
+      "epoch": 0.45597964376590333,
+      "grad_norm": 0.29984185099601746,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 1.1877,
+      "step": 56
+    },
+    {
+      "epoch": 0.46412213740458014,
+      "grad_norm": 0.2994973957538605,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 1.1334,
+      "step": 57
+    },
+    {
+      "epoch": 0.472264631043257,
+      "grad_norm": 0.3209475576877594,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 1.1666,
+      "step": 58
+    },
+    {
+      "epoch": 0.48040712468193386,
+      "grad_norm": 0.317921906709671,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 1.029,
+      "step": 59
+    },
+    {
+      "epoch": 0.48854961832061067,
+      "grad_norm": 0.32125380635261536,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 0.9528,
+      "step": 60
+    },
+    {
+      "epoch": 0.49669211195928753,
+      "grad_norm": 0.30410146713256836,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 0.9018,
+      "step": 61
+    },
+    {
+      "epoch": 0.5048346055979643,
+      "grad_norm": 0.39632368087768555,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 0.9189,
+      "step": 62
+    },
+    {
+      "epoch": 0.5129770992366413,
+      "grad_norm": 0.28354790806770325,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 1.2053,
+      "step": 63
+    },
+    {
+      "epoch": 0.5211195928753181,
+      "grad_norm": 0.23840811848640442,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 1.3452,
+      "step": 64
+    },
+    {
+      "epoch": 0.5292620865139949,
+      "grad_norm": 0.2518406808376312,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 1.2796,
+      "step": 65
+    },
+    {
+      "epoch": 0.5374045801526718,
+      "grad_norm": 0.3083972632884979,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 1.2915,
+      "step": 66
+    },
+    {
+      "epoch": 0.5455470737913486,
+      "grad_norm": 0.28872764110565186,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 1.2188,
+      "step": 67
+    },
+    {
+      "epoch": 0.5536895674300254,
+      "grad_norm": 0.281512588262558,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 1.1432,
+      "step": 68
+    },
+    {
+      "epoch": 0.5618320610687023,
+      "grad_norm": 0.2897692918777466,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 1.197,
+      "step": 69
+    },
+    {
+      "epoch": 0.5699745547073791,
+      "grad_norm": 0.28706327080726624,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 1.065,
+      "step": 70
+    },
+    {
+      "epoch": 0.5781170483460559,
+      "grad_norm": 0.30318784713745117,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 0.9742,
+      "step": 71
+    },
+    {
+      "epoch": 0.5862595419847328,
+      "grad_norm": 0.310880571603775,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9485,
+      "step": 72
+    },
+    {
+      "epoch": 0.5944020356234097,
+      "grad_norm": 0.33773961663246155,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 0.98,
+      "step": 73
+    },
+    {
+      "epoch": 0.6025445292620865,
+      "grad_norm": 0.35677966475486755,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 0.8608,
+      "step": 74
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "grad_norm": 0.38845735788345337,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 0.787,
+      "step": 75
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "eval_loss": 1.1252893209457397,
+      "eval_runtime": 3.2469,
+      "eval_samples_per_second": 15.399,
+      "eval_steps_per_second": 4.004,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.624057810649088e+17,
+  "total_flos": 8.436086715973632e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null