Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0e3e6423021244f025e8a2756138044eaff61a4705331ffbb1494814f5398c
+oid sha256:1a77035769512ca32e73719aa55c11bc79eb5cc0b61959f7810e492a01abae8b
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330e5ce04c97ff952f87859cd9f1e5459326489e400928028bc5f602c01d72f5
+oid sha256:ab523bb6c00c781aa931c2bb49b6cd861f86279207b1ead1f21119e8ca14b102
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bfe710c13f053a31a062cb49cc8977f07aa304e727842ae94378d16f9c2eb54
+oid sha256:1b82663215514d2e15e138bd5f29cc14a027613fadf5ec71d5efb38b975dd0ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d78a1aebf19597cd8ff98f7926ac4269f296aa1d1624299a9f32e8caf8a078
+oid sha256:c8df72f092075a52322208049c03f4b09cc9f34969610024acd4dbbce4825748
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609cfa78dc97089f7bb964cf3c72d10ea4ffd6fc0c0a90e1ad086cd3d80896f6
+oid sha256:051c0f2a65f962c7ac612cd6d98aea8a58f1c2488407511d82a87a1e624f3e95
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71beadd62f059b758ab2b40331d8b84f794290e592baa996f44a3414cd82f51
+oid sha256:7322c1e75872ff8babcdb0f085ede43acec91dddbc0972f496bf5275436824db
 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": 10.138866424560547,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.041299914818925684,
+  "best_metric": 10.120731353759766,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.061949872228388526,
   "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": 614.338,
       "eval_steps_per_second": 159.728,
       "step": 50
+    },
+    {
+      "epoch": 0.0421259131153042,
+      "grad_norm": 0.6381344199180603,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 10.1596,
+      "step": 51
+    },
+    {
+      "epoch": 0.04295191141168271,
+      "grad_norm": 0.6048315167427063,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 10.1464,
+      "step": 52
+    },
+    {
+      "epoch": 0.043777909708061225,
+      "grad_norm": 0.5989148020744324,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 10.1373,
+      "step": 53
+    },
+    {
+      "epoch": 0.04460390800443974,
+      "grad_norm": 0.5282235145568848,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 10.1422,
+      "step": 54
+    },
+    {
+      "epoch": 0.04542990630081825,
+      "grad_norm": 0.5445945858955383,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 10.1465,
+      "step": 55
+    },
+    {
+      "epoch": 0.04625590459719677,
+      "grad_norm": 0.528545618057251,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 10.1424,
+      "step": 56
+    },
+    {
+      "epoch": 0.047081902893575285,
+      "grad_norm": 0.5194099545478821,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 10.1398,
+      "step": 57
+    },
+    {
+      "epoch": 0.0479079011899538,
+      "grad_norm": 0.489889532327652,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 10.1429,
+      "step": 58
+    },
+    {
+      "epoch": 0.04873389948633231,
+      "grad_norm": 0.49389705061912537,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 10.1465,
+      "step": 59
+    },
+    {
+      "epoch": 0.049559897782710825,
+      "grad_norm": 0.475475549697876,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 10.1475,
+      "step": 60
+    },
+    {
+      "epoch": 0.05038589607908934,
+      "grad_norm": 0.50710529088974,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 10.1394,
+      "step": 61
+    },
+    {
+      "epoch": 0.05121189437546785,
+      "grad_norm": 0.5150895118713379,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 10.1326,
+      "step": 62
+    },
+    {
+      "epoch": 0.052037892671846366,
+      "grad_norm": 0.4752042591571808,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 10.145,
+      "step": 63
+    },
+    {
+      "epoch": 0.05286389096822488,
+      "grad_norm": 0.4911608099937439,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 10.1347,
+      "step": 64
+    },
+    {
+      "epoch": 0.05368988926460339,
+      "grad_norm": 0.5078980326652527,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 10.1343,
+      "step": 65
+    },
+    {
+      "epoch": 0.054515887560981906,
+      "grad_norm": 0.47904160618782043,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 10.1393,
+      "step": 66
+    },
+    {
+      "epoch": 0.05534188585736042,
+      "grad_norm": 0.48951855301856995,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 10.1393,
+      "step": 67
+    },
+    {
+      "epoch": 0.05616788415373893,
+      "grad_norm": 0.5052370429039001,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 10.1344,
+      "step": 68
+    },
+    {
+      "epoch": 0.056993882450117446,
+      "grad_norm": 0.5891403555870056,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 10.1356,
+      "step": 69
+    },
+    {
+      "epoch": 0.05781988074649596,
+      "grad_norm": 0.5263543725013733,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 10.133,
+      "step": 70
+    },
+    {
+      "epoch": 0.05864587904287447,
+      "grad_norm": 0.5553152561187744,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 10.1311,
+      "step": 71
+    },
+    {
+      "epoch": 0.059471877339252986,
+      "grad_norm": 0.5369566679000854,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.136,
+      "step": 72
+    },
+    {
+      "epoch": 0.0602978756356315,
+      "grad_norm": 0.5451551079750061,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 10.1372,
+      "step": 73
+    },
+    {
+      "epoch": 0.06112387393201001,
+      "grad_norm": 0.5561919808387756,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 10.1302,
+      "step": 74
+    },
+    {
+      "epoch": 0.061949872228388526,
+      "grad_norm": 0.5314218401908875,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 10.1341,
+      "step": 75
+    },
+    {
+      "epoch": 0.061949872228388526,
+      "eval_loss": 10.120731353759766,
+      "eval_runtime": 0.0806,
+      "eval_samples_per_second": 620.248,
+      "eval_steps_per_second": 161.265,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 42768059596800.0,
+  "total_flos": 64152089395200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null