Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a979887c2a90219cfd7c74cb73ae05b278bb8cb4e40b637116391575d5c4f87
+oid sha256:137add320f6e5fddd54550245a0664594365c0bdb786ec6815decb957cdedef6
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf18ee2f9ee7a1c70493f9fe170974543779a4ffe68474ddabd477c5d5cee9a
+oid sha256:6dd8a08b8da96eda5538cdc0b6883fcc57397564eba1d4153895576d8ae6bef0
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487a416c08616739437554bc1e64b7a42925248a47025dea53ebda2624d7f54a
+oid sha256:930e2ec71c65cc7c5ffd66064b18f07719a3cc53f541ed54ffc249d59fd34407
 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": 1.0510051250457764,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005465376837732962,
+  "best_metric": 1.049103021621704,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010930753675465924,
   "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": 13.492,
       "eval_steps_per_second": 1.686,
       "step": 25
+    },
+    {
+      "epoch": 0.00568399191124228,
+      "grad_norm": 0.7088556289672852,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.2678,
+      "step": 26
+    },
+    {
+      "epoch": 0.005902606984751598,
+      "grad_norm": 0.7126575112342834,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.315,
+      "step": 27
+    },
+    {
+      "epoch": 0.006121222058260917,
+      "grad_norm": 0.7205974459648132,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.2119,
+      "step": 28
+    },
+    {
+      "epoch": 0.006339837131770235,
+      "grad_norm": 0.6830354332923889,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.2151,
+      "step": 29
+    },
+    {
+      "epoch": 0.006558452205279554,
+      "grad_norm": 0.6415659785270691,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.2253,
+      "step": 30
+    },
+    {
+      "epoch": 0.0067770672787888725,
+      "grad_norm": 0.6351765990257263,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.1,
+      "step": 31
+    },
+    {
+      "epoch": 0.006995682352298191,
+      "grad_norm": 0.6895049810409546,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.1679,
+      "step": 32
+    },
+    {
+      "epoch": 0.00721429742580751,
+      "grad_norm": 0.6956767439842224,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.1575,
+      "step": 33
+    },
+    {
+      "epoch": 0.007432912499316828,
+      "grad_norm": 0.795951247215271,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.1705,
+      "step": 34
+    },
+    {
+      "epoch": 0.007651527572826147,
+      "grad_norm": 1.151456594467163,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2722,
+      "step": 35
+    },
+    {
+      "epoch": 0.007870142646335464,
+      "grad_norm": 1.0940009355545044,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.2685,
+      "step": 36
+    },
+    {
+      "epoch": 0.008088757719844783,
+      "grad_norm": 1.43516206741333,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2708,
+      "step": 37
+    },
+    {
+      "epoch": 0.008307372793354102,
+      "grad_norm": 1.237060308456421,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4588,
+      "step": 38
+    },
+    {
+      "epoch": 0.00852598786686342,
+      "grad_norm": 0.879013180732727,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2302,
+      "step": 39
+    },
+    {
+      "epoch": 0.008744602940372739,
+      "grad_norm": 0.793963611125946,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2223,
+      "step": 40
+    },
+    {
+      "epoch": 0.008963218013882057,
+      "grad_norm": 1.5157628059387207,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.261,
+      "step": 41
+    },
+    {
+      "epoch": 0.009181833087391376,
+      "grad_norm": 2.050135374069214,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3103,
+      "step": 42
+    },
+    {
+      "epoch": 0.009400448160900694,
+      "grad_norm": 1.0070862770080566,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2538,
+      "step": 43
+    },
+    {
+      "epoch": 0.009619063234410013,
+      "grad_norm": 1.5608525276184082,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2355,
+      "step": 44
+    },
+    {
+      "epoch": 0.009837678307919331,
+      "grad_norm": 2.536520004272461,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3299,
+      "step": 45
+    },
+    {
+      "epoch": 0.01005629338142865,
+      "grad_norm": 2.5030901432037354,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3479,
+      "step": 46
+    },
+    {
+      "epoch": 0.010274908454937969,
+      "grad_norm": 2.2683932781219482,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2691,
+      "step": 47
+    },
+    {
+      "epoch": 0.010493523528447287,
+      "grad_norm": 2.113285779953003,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2866,
+      "step": 48
+    },
+    {
+      "epoch": 0.010712138601956606,
+      "grad_norm": 1.0461803674697876,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.9829,
+      "step": 49
+    },
+    {
+      "epoch": 0.010930753675465924,
+      "grad_norm": 1.0210597515106201,
+      "learning_rate": 0.0,
+      "loss": 0.2243,
+      "step": 50
+    },
+    {
+      "epoch": 0.010930753675465924,
+      "eval_loss": 1.049103021621704,
+      "eval_runtime": 570.7917,
+      "eval_samples_per_second": 13.497,
+      "eval_steps_per_second": 1.687,
+      "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": 3.77128394686464e+16,
+  "total_flos": 7.42942937532334e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null