Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58797087fc7eb9a48e833833f7a25540df9519aa8bc88422b68e43b91d3a860c
+oid sha256:049e0e5cbff75c911e575aecea483928824474f41f154f353e9ac7d58fba196b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297d2866f2be329972ad2d278bd7b969756ac677ca4ca7b35666ee9d4ff1f798
+oid sha256:275c84c9ffea02351ccbaf55ed6d7f41ca17c1e9f05208146ce07d7b1668dfa2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2947d6c4fa85152876f7dc52428467735d91ee8887c2524564a52b86569925b
+oid sha256:e31a7d91581d6784b6c90c9f5ffb2067216590851fa2be056290bcdbfa2d2c7e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4671a706e83e1dd6bf7494118fc0cdde3090a23e2f5b19d21ea0a67efc59d4f9
+oid sha256:d98a01f088a1094059c90fb3c822e80583ae403b07bd558f9d4c5192cff53190
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461950a27b37f249c4101ffc1aec7926476d556f8d90ef5c1bd26f4013e02629
+oid sha256:0d95e9f79d47af3c4c2d1913379efda4471684e97e9c766199d6a063c1b15a70
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008998672695777372,
+  "epoch": 0.017997345391554745,
   "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": 33.716,
       "eval_steps_per_second": 8.766,
       "step": 25
+    },
+    {
+      "epoch": 0.009358619603608467,
+      "grad_norm": NaN,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.009718566511439562,
+      "grad_norm": NaN,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.010078513419270657,
+      "grad_norm": NaN,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.010438460327101752,
+      "grad_norm": NaN,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.010798407234932847,
+      "grad_norm": NaN,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.011158354142763942,
+      "grad_norm": NaN,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.011518301050595037,
+      "grad_norm": NaN,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.011878247958426132,
+      "grad_norm": NaN,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.012238194866257227,
+      "grad_norm": NaN,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.012598141774088321,
+      "grad_norm": NaN,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.012958088681919416,
+      "grad_norm": NaN,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.013318035589750511,
+      "grad_norm": NaN,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.013677982497581606,
+      "grad_norm": NaN,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.014037929405412701,
+      "grad_norm": NaN,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.014397876313243796,
+      "grad_norm": NaN,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01475782322107489,
+      "grad_norm": NaN,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.015117770128905986,
+      "grad_norm": NaN,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.01547771703673708,
+      "grad_norm": NaN,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.015837663944568176,
+      "grad_norm": NaN,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.01619761085239927,
+      "grad_norm": NaN,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.016557557760230365,
+      "grad_norm": NaN,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.01691750466806146,
+      "grad_norm": NaN,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.017277451575892555,
+      "grad_norm": NaN,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.01763739848372365,
+      "grad_norm": NaN,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.017997345391554745,
+      "grad_norm": NaN,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.017997345391554745,
+      "eval_loss": NaN,
+      "eval_runtime": 1.4835,
+      "eval_samples_per_second": 33.704,
+      "eval_steps_per_second": 8.763,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null