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:e744fb179840dec54b68ff8fda815fbc129a7dadaba265d83a03dcb848ab8639
+oid sha256:76ed789327e973a3bb8e47a7ccdce489a6c96f9cb726bb427bc5db3e54905898
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18904d248d47307c38e1ed56c3782ab06bf7b80e9c83ccd39f779db16f0cf85
+oid sha256:2ba1019bbf87efbaa0de74c415d20380557a44d39946a3610f64b294252d3caa
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82bc45f3b3e2980df7bd4dc8903f63ec81c6e56382a07f3216584cb283d9d97
+oid sha256:b047250531bd2d5ea5ba55912795d43094211ef8b7742fa867556fa20ba34133
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5caf2a12bd77a23bd7b6628c10dee6414efdde65f54fec822e81828f9b152b7a
+oid sha256:4de4e47a8e936ece29eeafd62986b4cd997ed52c5d9f3c9915f2cd50fbfa11d4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c3876a5c537e9da801cf74e7527a56859e9749ba5e7f3a3ae02c477a281a3d
+oid sha256:5188d2ca412d671040dd9291ab948bea5b2e0430ef528e5423bd546f865d3f0c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bae7a2e334c3224fdec86935c3428cf54f86ee25e8080d9904d74414d16a3ec
+oid sha256:e0d3b6020ff042970aefd3227640eadaed46d0405eda0f3aba5bd147ca1566ce
 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": 10.361374855041504,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6530612244897959,
+  "best_metric": 10.357850074768066,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.9795918367346939,
   "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": 485.159,
       "eval_steps_per_second": 126.141,
       "step": 50
+    },
+    {
+      "epoch": 0.6661224489795918,
+      "grad_norm": 0.10061974823474884,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 10.3688,
+      "step": 51
+    },
+    {
+      "epoch": 0.6791836734693878,
+      "grad_norm": 0.10003743320703506,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 10.3675,
+      "step": 52
+    },
+    {
+      "epoch": 0.6922448979591836,
+      "grad_norm": 0.10272656381130219,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 10.3657,
+      "step": 53
+    },
+    {
+      "epoch": 0.7053061224489796,
+      "grad_norm": 0.09442754834890366,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 10.3653,
+      "step": 54
+    },
+    {
+      "epoch": 0.7183673469387755,
+      "grad_norm": 0.09699378907680511,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 10.3657,
+      "step": 55
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.0912444069981575,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 10.364,
+      "step": 56
+    },
+    {
+      "epoch": 0.7444897959183674,
+      "grad_norm": 0.11898164451122284,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 10.3635,
+      "step": 57
+    },
+    {
+      "epoch": 0.7575510204081632,
+      "grad_norm": 0.11395476013422012,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 10.3596,
+      "step": 58
+    },
+    {
+      "epoch": 0.7706122448979592,
+      "grad_norm": 0.12100130319595337,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 10.3591,
+      "step": 59
+    },
+    {
+      "epoch": 0.7836734693877551,
+      "grad_norm": 0.08402037620544434,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 10.3578,
+      "step": 60
+    },
+    {
+      "epoch": 0.796734693877551,
+      "grad_norm": 0.11241566389799118,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 10.353,
+      "step": 61
+    },
+    {
+      "epoch": 0.809795918367347,
+      "grad_norm": 0.0890788733959198,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 10.3523,
+      "step": 62
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.12000347673892975,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 10.3655,
+      "step": 63
+    },
+    {
+      "epoch": 0.8359183673469388,
+      "grad_norm": 0.11988016963005066,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 10.364,
+      "step": 64
+    },
+    {
+      "epoch": 0.8489795918367347,
+      "grad_norm": 0.11741887778043747,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 10.3622,
+      "step": 65
+    },
+    {
+      "epoch": 0.8620408163265306,
+      "grad_norm": 0.1116131916642189,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 10.3641,
+      "step": 66
+    },
+    {
+      "epoch": 0.8751020408163265,
+      "grad_norm": 0.09721927344799042,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 10.3633,
+      "step": 67
+    },
+    {
+      "epoch": 0.8881632653061224,
+      "grad_norm": 0.09096729010343552,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 10.3615,
+      "step": 68
+    },
+    {
+      "epoch": 0.9012244897959184,
+      "grad_norm": 0.09501949697732925,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 10.3602,
+      "step": 69
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.08972970396280289,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 10.3622,
+      "step": 70
+    },
+    {
+      "epoch": 0.9273469387755102,
+      "grad_norm": 0.07294773310422897,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 10.3584,
+      "step": 71
+    },
+    {
+      "epoch": 0.9404081632653061,
+      "grad_norm": 0.08683331310749054,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3582,
+      "step": 72
+    },
+    {
+      "epoch": 0.953469387755102,
+      "grad_norm": 0.0977322980761528,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 10.3551,
+      "step": 73
+    },
+    {
+      "epoch": 0.966530612244898,
+      "grad_norm": 0.09911535680294037,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 10.3532,
+      "step": 74
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.13088646531105042,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 10.3459,
+      "step": 75
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "eval_loss": 10.357850074768066,
+      "eval_runtime": 0.1083,
+      "eval_samples_per_second": 461.853,
+      "eval_steps_per_second": 120.082,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 42834884689920.0,
+  "total_flos": 64259009544192.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null