Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d922bb466be8d7e179ea114878383017a09f15bd77044172ec4e0da97ef78522
+oid sha256:cb421b1b2149d6b3a59fcbc86999a92142d50d0f7b91604b7b5bf1065201bd5e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e254354c6a214b1845f9e8bfbf9ef7820a259b656c44c013a4d17ffcc94e77
+oid sha256:02f2210df239def0373c93d574bb088a3aa180112415c89f7b3d08a9d6aff843
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c7a859ddd8f45f043326197adeb1bcdb4c70936f8cd4f9cb8ba3a9e7136957
+oid sha256:b163b66ca16443d10b1448a8ff58b349f202d9080dc486126e71c1bd237d6713
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afecb1b076770f9625934c60810945428ad6dabc4613752656257c0553aa9e0
+oid sha256:0b3fadf30e7094014c60e3e246d4def72d4ae9c37920b6bb1dba9875ea8d6bab
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beea23de209cfb416f038e7900db697a04b8fd6922e5ce3851846366555eef8e
+oid sha256:897a82cf027da8057ee5924fad004ee00680d3245e6a1acd6743830e6c7b7d11
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32ea5e6c9dac390e97edd4c2e930b55f3af311453c7cd1ef9a801e118f9d3b5
+oid sha256:42cd59d1e6915afb368ddb0594ee8c5e5dc45a760d107c597d6cc00d49035a44
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
+oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5544013381004333,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8333333333333335,
+  "epoch": 3.1216216216216215,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 10.394,
       "eval_steps_per_second": 2.702,
       "step": 25
+    },
+    {
+      "epoch": 1.9054054054054053,
+      "grad_norm": 10.637453079223633,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 15.3613,
+      "step": 26
+    },
+    {
+      "epoch": 2.009009009009009,
+      "grad_norm": 11.018033027648926,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 15.2808,
+      "step": 27
+    },
+    {
+      "epoch": 2.081081081081081,
+      "grad_norm": 9.55007553100586,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 14.7026,
+      "step": 28
+    },
+    {
+      "epoch": 2.153153153153153,
+      "grad_norm": 10.30716609954834,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 14.6719,
+      "step": 29
+    },
+    {
+      "epoch": 2.225225225225225,
+      "grad_norm": 10.953435897827148,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 13.8655,
+      "step": 30
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 10.068406105041504,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 14.6353,
+      "step": 31
+    },
+    {
+      "epoch": 2.3693693693693696,
+      "grad_norm": 11.066611289978027,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 14.7031,
+      "step": 32
+    },
+    {
+      "epoch": 2.4414414414414414,
+      "grad_norm": 11.900208473205566,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 14.1224,
+      "step": 33
+    },
+    {
+      "epoch": 2.5135135135135136,
+      "grad_norm": 10.959716796875,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 13.9909,
+      "step": 34
+    },
+    {
+      "epoch": 2.5855855855855854,
+      "grad_norm": 11.068878173828125,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 14.7811,
+      "step": 35
+    },
+    {
+      "epoch": 2.6576576576576576,
+      "grad_norm": 11.743328094482422,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 13.8688,
+      "step": 36
+    },
+    {
+      "epoch": 2.72972972972973,
+      "grad_norm": 11.463229179382324,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 13.4959,
+      "step": 37
+    },
+    {
+      "epoch": 2.801801801801802,
+      "grad_norm": 11.082849502563477,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 14.5614,
+      "step": 38
+    },
+    {
+      "epoch": 2.873873873873874,
+      "grad_norm": 11.691807746887207,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 13.9716,
+      "step": 39
+    },
+    {
+      "epoch": 2.945945945945946,
+      "grad_norm": 12.260763168334961,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 12.9331,
+      "step": 40
+    },
+    {
+      "epoch": 3.0495495495495497,
+      "grad_norm": 10.715076446533203,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 13.9412,
+      "step": 41
+    },
+    {
+      "epoch": 3.1216216216216215,
+      "grad_norm": 10.816911697387695,
+      "learning_rate": 1e-05,
+      "loss": 13.9132,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.8360831917883392e+17,
+  "total_flos": 4.7651148387896525e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null