Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad05e920b8256ec373516d70d4c0179cd52efe14146859e0e331c8a8e518a90
+oid sha256:92141399d46c589493baa32bc60b49dfacaf17848e49fd6ac86adcb69c744d3b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c05013aee354e206a3638211842a57412c2af26944937ab1f7bb755258d5762
+oid sha256:7970281dc27be36a164e4f1cc76951382a933ba2353f6726ea761db171e850cd
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d3910a6d862e197bb8e5cd63162919721a00b89ef1141a6a637f558cf79ba2
+oid sha256:7d10135b31719b1e63f46aa7b33e5bda4718c4cd279455114d809135bf8d39f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4173017740249634,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00846811753747142,
+  "best_metric": 0.3689563274383545,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01693623507494284,
   "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": 0.948,
       "eval_steps_per_second": 0.474,
       "step": 25
+    },
+    {
+      "epoch": 0.008806842238970276,
+      "grad_norm": 0.2835831344127655,
+      "learning_rate": 0.0001,
+      "loss": 1.553,
+      "step": 26
+    },
+    {
+      "epoch": 0.009145566940469134,
+      "grad_norm": 0.25215256214141846,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.9827,
+      "step": 27
+    },
+    {
+      "epoch": 0.00948429164196799,
+      "grad_norm": 0.34205523133277893,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.6806,
+      "step": 28
+    },
+    {
+      "epoch": 0.009823016343466847,
+      "grad_norm": 0.3410358428955078,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.8845,
+      "step": 29
+    },
+    {
+      "epoch": 0.010161741044965705,
+      "grad_norm": 0.4108333885669708,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.294,
+      "step": 30
+    },
+    {
+      "epoch": 0.01050046574646456,
+      "grad_norm": 0.3529786169528961,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.5982,
+      "step": 31
+    },
+    {
+      "epoch": 0.010839190447963418,
+      "grad_norm": 0.44188639521598816,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.4352,
+      "step": 32
+    },
+    {
+      "epoch": 0.011177915149462274,
+      "grad_norm": 0.412591814994812,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.0171,
+      "step": 33
+    },
+    {
+      "epoch": 0.011516639850961132,
+      "grad_norm": 0.49157121777534485,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.1679,
+      "step": 34
+    },
+    {
+      "epoch": 0.011855364552459988,
+      "grad_norm": 0.46250882744789124,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.0679,
+      "step": 35
+    },
+    {
+      "epoch": 0.012194089253958845,
+      "grad_norm": 0.45197004079818726,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.875,
+      "step": 36
+    },
+    {
+      "epoch": 0.012532813955457701,
+      "grad_norm": 0.7647995948791504,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.5482,
+      "step": 37
+    },
+    {
+      "epoch": 0.012871538656956559,
+      "grad_norm": 0.570399284362793,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.0637,
+      "step": 38
+    },
+    {
+      "epoch": 0.013210263358455415,
+      "grad_norm": 0.6635165810585022,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.8633,
+      "step": 39
+    },
+    {
+      "epoch": 0.013548988059954272,
+      "grad_norm": 0.8030415177345276,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.9288,
+      "step": 40
+    },
+    {
+      "epoch": 0.01388771276145313,
+      "grad_norm": 0.8105241060256958,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.3048,
+      "step": 41
+    },
+    {
+      "epoch": 0.014226437462951986,
+      "grad_norm": 0.7749304175376892,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.4869,
+      "step": 42
+    },
+    {
+      "epoch": 0.014565162164450843,
+      "grad_norm": 0.8955188393592834,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.4531,
+      "step": 43
+    },
+    {
+      "epoch": 0.014903886865949699,
+      "grad_norm": 1.082139492034912,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.4126,
+      "step": 44
+    },
+    {
+      "epoch": 0.015242611567448557,
+      "grad_norm": 1.0183438062667847,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.2606,
+      "step": 45
+    },
+    {
+      "epoch": 0.015581336268947412,
+      "grad_norm": 1.456734299659729,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.3089,
+      "step": 46
+    },
+    {
+      "epoch": 0.015920060970446268,
+      "grad_norm": 1.2570323944091797,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.5638,
+      "step": 47
+    },
+    {
+      "epoch": 0.016258785671945126,
+      "grad_norm": 1.7432653903961182,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.2538,
+      "step": 48
+    },
+    {
+      "epoch": 0.016597510373443983,
+      "grad_norm": 1.8139467239379883,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.8829,
+      "step": 49
+    },
+    {
+      "epoch": 0.01693623507494284,
+      "grad_norm": 1.7850284576416016,
+      "learning_rate": 0.0,
+      "loss": 2.0823,
+      "step": 50
+    },
+    {
+      "epoch": 0.01693623507494284,
+      "eval_loss": 0.3689563274383545,
+      "eval_runtime": 1312.7469,
+      "eval_samples_per_second": 0.948,
+      "eval_steps_per_second": 0.474,
+      "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": 6.3478299623424e+16,
+  "total_flos": 1.26956599246848e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null