Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bada49662ce5714243662a8235afd4a3f891cf4184bb7ec1624e5f3e4ec0999
+oid sha256:886707c9a63ff1e74af6d10c8c6f88a9891616af00592ef53ec21e11e2d67d5a
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c9befd48d8a3f79e9ba78285798ac00c5f5bffc8f2d0a7fd43a06c4717a5a3
+oid sha256:1d42321e5e6335a5417c85a88a76764a3ae569f33e4a7073751e9c2af7b9fb11
 size 198011252

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00fcec9ac8717fd43136308c468bf7964cd4b2dc50a751ec2100b60acedd7f41
+oid sha256:55c9c582d34e181aa2e1902e5d8f1d25a757a6112e429c1cc7df2eef8e3ea427
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.137049913406372,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.32679738562091504,
+  "best_metric": 1.001587986946106,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6535947712418301,
   "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": 46.741,
       "eval_steps_per_second": 6.16,
       "step": 25
+    },
+    {
+      "epoch": 0.33986928104575165,
+      "grad_norm": 1.1448719501495361,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.1828,
+      "step": 26
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 1.1801111698150635,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3119,
+      "step": 27
+    },
+    {
+      "epoch": 0.3660130718954248,
+      "grad_norm": 1.3355175256729126,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.1409,
+      "step": 28
+    },
+    {
+      "epoch": 0.3790849673202614,
+      "grad_norm": 1.2064152956008911,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.0365,
+      "step": 29
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 1.1076024770736694,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.9831,
+      "step": 30
+    },
+    {
+      "epoch": 0.40522875816993464,
+      "grad_norm": 1.229954719543457,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.859,
+      "step": 31
+    },
+    {
+      "epoch": 0.41830065359477125,
+      "grad_norm": 1.0919172763824463,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.9309,
+      "step": 32
+    },
+    {
+      "epoch": 0.43137254901960786,
+      "grad_norm": 1.1399344205856323,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.8323,
+      "step": 33
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.083505392074585,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.8003,
+      "step": 34
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 1.2402992248535156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7761,
+      "step": 35
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.1251118183135986,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.5939,
+      "step": 36
+    },
+    {
+      "epoch": 0.48366013071895425,
+      "grad_norm": 1.2075703144073486,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.6067,
+      "step": 37
+    },
+    {
+      "epoch": 0.49673202614379086,
+      "grad_norm": 1.3176946640014648,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.6173,
+      "step": 38
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "grad_norm": 1.2353657484054565,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3562,
+      "step": 39
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 1.0886991024017334,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2615,
+      "step": 40
+    },
+    {
+      "epoch": 0.5359477124183006,
+      "grad_norm": 1.1880528926849365,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2867,
+      "step": 41
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 1.164398431777954,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.2298,
+      "step": 42
+    },
+    {
+      "epoch": 0.5620915032679739,
+      "grad_norm": 1.153171181678772,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.352,
+      "step": 43
+    },
+    {
+      "epoch": 0.5751633986928104,
+      "grad_norm": 1.2491941452026367,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.2632,
+      "step": 44
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.230054497718811,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2392,
+      "step": 45
+    },
+    {
+      "epoch": 0.6013071895424836,
+      "grad_norm": 1.2693663835525513,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.2007,
+      "step": 46
+    },
+    {
+      "epoch": 0.6143790849673203,
+      "grad_norm": 1.1482421159744263,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.0283,
+      "step": 47
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 1.1393154859542847,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9656,
+      "step": 48
+    },
+    {
+      "epoch": 0.6405228758169934,
+      "grad_norm": 1.2570338249206543,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.0083,
+      "step": 49
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 1.1813966035842896,
+      "learning_rate": 0.0,
+      "loss": 0.8914,
+      "step": 50
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "eval_loss": 1.001587986946106,
+      "eval_runtime": 2.7671,
+      "eval_samples_per_second": 46.619,
+      "eval_steps_per_second": 6.144,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7166368520601600.0,
+  "total_flos": 1.43327370412032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null