Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebd822c2791137ee56bd9dc715c20b6bfec6e6c9ae7606c883b10a67cada1a7
+oid sha256:1d0243739d7234437280d6d6acc558ec78ff05d5bb455d9446ff3a92e550748d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d178f0bad1a1205864534c745a7e4544f9cdcca006d6a7c3f9ca7addab2fa25
+oid sha256:6a9ce26cd6cb7597ac8e38b232252c0255213705a7cf5aa6d7b4e3592b7f721a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7650ed66867004f8256438d97319f50a318c176b2e84db850d71523e6cd11e
+oid sha256:41d3c14498426ade58c588ad688d79c4152b96f1b2a00367f32697940d06af86
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907a88adef93bb5feb604263b22c09d6112eee0b527e513ddd945e91289d08f1
+oid sha256:8de2e8eadcfe860f4e23dded4999d6540c4bc0b284cf7975c1e26bbcf9e8922b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac563c58c9c0e690c61917356fe70f5796256096636d46c02fd4762e705823d
+oid sha256:bbb5e2d9fcff1b79ab0b75fd410d6dca510aae4c2aeda7e05c393fe21bb6994d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af987e5a523170e893a07009ddcf5f0831754b4efd6aee42467e10d8359980b
+oid sha256:6c13cb0323d7065705d590003ec0bb68a10f2ec87a295ccc4fd2c1bc203be259
 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": 2.0515553951263428,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6334125098970704,
+  "best_metric": 1.9965410232543945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2668250197941409,
   "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": 11.173,
       "eval_steps_per_second": 2.905,
       "step": 25
+    },
+    {
+      "epoch": 0.6587490102929533,
+      "grad_norm": 0.6521803140640259,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 2.1157,
+      "step": 26
+    },
+    {
+      "epoch": 0.684085510688836,
+      "grad_norm": 0.704856812953949,
+      "learning_rate": 7.75e-05,
+      "loss": 2.0327,
+      "step": 27
+    },
+    {
+      "epoch": 0.7094220110847189,
+      "grad_norm": 0.7150166034698486,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 2.0704,
+      "step": 28
+    },
+    {
+      "epoch": 0.7347585114806018,
+      "grad_norm": 0.7469585537910461,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 2.1531,
+      "step": 29
+    },
+    {
+      "epoch": 0.7600950118764845,
+      "grad_norm": 0.8201628923416138,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 1.9451,
+      "step": 30
+    },
+    {
+      "epoch": 0.7854315122723674,
+      "grad_norm": 0.8757390975952148,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 1.9914,
+      "step": 31
+    },
+    {
+      "epoch": 0.8107680126682502,
+      "grad_norm": 0.7520741820335388,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 2.0039,
+      "step": 32
+    },
+    {
+      "epoch": 0.836104513064133,
+      "grad_norm": 0.6872738599777222,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 2.0456,
+      "step": 33
+    },
+    {
+      "epoch": 0.8614410134600158,
+      "grad_norm": 0.6908338665962219,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 1.9938,
+      "step": 34
+    },
+    {
+      "epoch": 0.8867775138558986,
+      "grad_norm": 0.6956162452697754,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 1.8879,
+      "step": 35
+    },
+    {
+      "epoch": 0.9121140142517815,
+      "grad_norm": 0.7513056397438049,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 1.8482,
+      "step": 36
+    },
+    {
+      "epoch": 0.9374505146476643,
+      "grad_norm": 0.7429540753364563,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 2.041,
+      "step": 37
+    },
+    {
+      "epoch": 0.9627870150435471,
+      "grad_norm": 0.7829824090003967,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 2.0959,
+      "step": 38
+    },
+    {
+      "epoch": 0.9881235154394299,
+      "grad_norm": 0.8197765350341797,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1425,
+      "step": 39
+    },
+    {
+      "epoch": 1.0134600158353126,
+      "grad_norm": 1.0817195177078247,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 2.9087,
+      "step": 40
+    },
+    {
+      "epoch": 1.0387965162311956,
+      "grad_norm": 0.6091715693473816,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 1.7902,
+      "step": 41
+    },
+    {
+      "epoch": 1.0641330166270784,
+      "grad_norm": 0.6952990293502808,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.9021,
+      "step": 42
+    },
+    {
+      "epoch": 1.0894695170229611,
+      "grad_norm": 0.685823917388916,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 1.8873,
+      "step": 43
+    },
+    {
+      "epoch": 1.114806017418844,
+      "grad_norm": 0.6813154816627502,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 1.9176,
+      "step": 44
+    },
+    {
+      "epoch": 1.1401425178147269,
+      "grad_norm": 0.6047990918159485,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.8264,
+      "step": 45
+    },
+    {
+      "epoch": 1.1654790182106096,
+      "grad_norm": 0.6644649505615234,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 1.8149,
+      "step": 46
+    },
+    {
+      "epoch": 1.1908155186064926,
+      "grad_norm": 0.6789914965629578,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 1.8527,
+      "step": 47
+    },
+    {
+      "epoch": 1.2161520190023754,
+      "grad_norm": 0.7495952248573303,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.8789,
+      "step": 48
+    },
+    {
+      "epoch": 1.241488519398258,
+      "grad_norm": 0.7526772022247314,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 1.9336,
+      "step": 49
+    },
+    {
+      "epoch": 1.2668250197941409,
+      "grad_norm": 0.6890441179275513,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 1.6726,
+      "step": 50
+    },
+    {
+      "epoch": 1.2668250197941409,
+      "eval_loss": 1.9965410232543945,
+      "eval_runtime": 4.3615,
+      "eval_samples_per_second": 11.464,
+      "eval_steps_per_second": 2.981,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null