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:ec1ebb19629c8f6919459e4c081287201c54ff3fbaccfa4def4f8d93f5c7794a
+oid sha256:f2b1c34a4b80d1ad3d9bab875327f8d0356113793f547447d5e142004ed91bed
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b882444fdb09ff20c2aabbd21e98924560f56230b06bb23c8fcb16e4c0180e3
+oid sha256:ff7b4d6e5bb3202587d85c17cfa5f152b9d43559387d851c8a97670bb1c55c90
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7ad56fd87f7951b539591bbcbd1be20ca89321f3df5e5cb1c491ced81fc74a
+oid sha256:3913249c7030fd4849795db814a510e322d4e67dbc8d7d8502df7485aac26334
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:036617ccd7c1996b29650fadd328329517768415630d06676d311a8010cba09f
+oid sha256:bed0a9412b6595f9d37ff761f0a96b8b4cdd7868bd260c0925ef7e4911f74ae9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8c2b17cfb6485b0e5eb6576708a26db8540bfe0e27c217f1ea52bbbdb9ee959
+oid sha256:8f78941e0377783e626cab4746fc84741b5f8e34159246297280e2b604d274d6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b4db09401a7397c0a68db90fa054f27bf2b779595d43956fa4686ac5f4a7c7
+oid sha256:84aa212b501f7b9dff0c6b58c8a6079f60b49f3eddbc582b992711ca1781ffdc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0478220dc1c61b501af7edfe8fa4a46b7ebe1a2bbd0ae4d7514712a0c8b72900
+oid sha256:3192059420211edc26748a07e2699e00ee3be65f92a2cf84ef56d22611d9eb5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7290714979171753,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.23282887077997672,
+  "best_metric": 0.6151813268661499,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.46565774155995343,
   "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": 85.787,
       "eval_steps_per_second": 5.395,
       "step": 25
+    },
+    {
+      "epoch": 0.2421420256111758,
+      "grad_norm": 1.6958057880401611,
+      "learning_rate": 8.842005554284296e-05,
+      "loss": 0.7597,
+      "step": 26
+    },
+    {
+      "epoch": 0.25145518044237486,
+      "grad_norm": 1.23319411277771,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 0.6973,
+      "step": 27
+    },
+    {
+      "epoch": 0.2607683352735739,
+      "grad_norm": 0.9983011484146118,
+      "learning_rate": 8.622126023955446e-05,
+      "loss": 0.6683,
+      "step": 28
+    },
+    {
+      "epoch": 0.270081490104773,
+      "grad_norm": 0.9224321842193604,
+      "learning_rate": 8.506183921362443e-05,
+      "loss": 0.6433,
+      "step": 29
+    },
+    {
+      "epoch": 0.27939464493597205,
+      "grad_norm": 1.100515604019165,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.7131,
+      "step": 30
+    },
+    {
+      "epoch": 0.28870779976717115,
+      "grad_norm": 0.9684303402900696,
+      "learning_rate": 8.262928807620843e-05,
+      "loss": 0.6402,
+      "step": 31
+    },
+    {
+      "epoch": 0.2980209545983702,
+      "grad_norm": 0.9174941182136536,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.6461,
+      "step": 32
+    },
+    {
+      "epoch": 0.3073341094295693,
+      "grad_norm": 0.998300313949585,
+      "learning_rate": 8.005405736415126e-05,
+      "loss": 0.6634,
+      "step": 33
+    },
+    {
+      "epoch": 0.31664726426076834,
+      "grad_norm": 1.0989651679992676,
+      "learning_rate": 7.871643313414718e-05,
+      "loss": 0.6501,
+      "step": 34
+    },
+    {
+      "epoch": 0.3259604190919674,
+      "grad_norm": 1.152661919593811,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.7261,
+      "step": 35
+    },
+    {
+      "epoch": 0.3352735739231665,
+      "grad_norm": 1.1657490730285645,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.6728,
+      "step": 36
+    },
+    {
+      "epoch": 0.3445867287543655,
+      "grad_norm": 1.2655208110809326,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 0.6361,
+      "step": 37
+    },
+    {
+      "epoch": 0.3538998835855646,
+      "grad_norm": 1.10227632522583,
+      "learning_rate": 7.30670581489344e-05,
+      "loss": 0.6442,
+      "step": 38
+    },
+    {
+      "epoch": 0.36321303841676367,
+      "grad_norm": 0.8832430243492126,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 0.6495,
+      "step": 39
+    },
+    {
+      "epoch": 0.37252619324796277,
+      "grad_norm": 0.7977732419967651,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.6015,
+      "step": 40
+    },
+    {
+      "epoch": 0.3818393480791618,
+      "grad_norm": 0.8318562507629395,
+      "learning_rate": 6.855986244591104e-05,
+      "loss": 0.6,
+      "step": 41
+    },
+    {
+      "epoch": 0.3911525029103609,
+      "grad_norm": 0.8057540655136108,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.6115,
+      "step": 42
+    },
+    {
+      "epoch": 0.40046565774155995,
+      "grad_norm": 0.8961812853813171,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.6151,
+      "step": 43
+    },
+    {
+      "epoch": 0.409778812572759,
+      "grad_norm": 0.9129841923713684,
+      "learning_rate": 6.387014543809223e-05,
+      "loss": 0.5908,
+      "step": 44
+    },
+    {
+      "epoch": 0.4190919674039581,
+      "grad_norm": 0.970668613910675,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 0.6279,
+      "step": 45
+    },
+    {
+      "epoch": 0.42840512223515714,
+      "grad_norm": 0.9627373814582825,
+      "learning_rate": 6.066498153718735e-05,
+      "loss": 0.6181,
+      "step": 46
+    },
+    {
+      "epoch": 0.43771827706635624,
+      "grad_norm": 0.997525691986084,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 0.5777,
+      "step": 47
+    },
+    {
+      "epoch": 0.4470314318975553,
+      "grad_norm": 1.2201300859451294,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.6627,
+      "step": 48
+    },
+    {
+      "epoch": 0.4563445867287544,
+      "grad_norm": 1.1989392042160034,
+      "learning_rate": 5.577423184847932e-05,
+      "loss": 0.6586,
+      "step": 49
+    },
+    {
+      "epoch": 0.46565774155995343,
+      "grad_norm": 1.3301013708114624,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.6635,
+      "step": 50
+    },
+    {
+      "epoch": 0.46565774155995343,
+      "eval_loss": 0.6151813268661499,
+      "eval_runtime": 16.7916,
+      "eval_samples_per_second": 86.174,
+      "eval_steps_per_second": 5.419,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.589463780163584e+17,
+  "total_flos": 3.178927560327168e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null