Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bbe0f56dcbb5789c4b5a3765af8c8eb4aefdab5fa77b4b8b7e2ea4e497c8658
+oid sha256:4a0829c05678a90eab71189be6f29b9448e3ef930f0c85e061a8f9bee98674c5
 size 78504446

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6ed06d75b11f875d39b0cb77eac014f1231b343bb981b32bcee2dcd7c1804f
+oid sha256:139e60a056a45a3b0927b6774f933785e21dcd7e5726d7616c1d5910291f4e97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729c0e69aa7d9319b688db4d0989039b1d75cf90aab64df4a7b079009e411ef9
+oid sha256:b03fca981590360b80402991384ae5c6e4b772ce2d817de7c453da637e6a02fb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa90cb3a8dfe4360b8269494f74ebc496f6459b3cd616893d83b9683876f4fc9
+oid sha256:94b7b64decfa1e509190d91d0d40a0f2b7aa9b25bb003aae5b2d86e9371cf898
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0e3f815b1467a6f53fc066fcea356b41ba79282676adb1802a286a798361ab
+oid sha256:45949e7f9c449d8218673fe7bd9b5dde9124e09d555d5a8af79c40de7d70c740
 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": 0.21668472372697725,
+  "epoch": 0.4333694474539545,
   "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": 88.18,
       "eval_steps_per_second": 22.927,
       "step": 25
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": NaN,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.23401950162513543,
+      "grad_norm": NaN,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.24268689057421453,
+      "grad_norm": NaN,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.2513542795232936,
+      "grad_norm": NaN,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.2600216684723727,
+      "grad_norm": NaN,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.26868905742145177,
+      "grad_norm": NaN,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.27735644637053086,
+      "grad_norm": NaN,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.28602383531960995,
+      "grad_norm": NaN,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.29469122426868904,
+      "grad_norm": NaN,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.30335861321776814,
+      "grad_norm": NaN,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.3120260021668472,
+      "grad_norm": NaN,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.3206933911159263,
+      "grad_norm": NaN,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.3293607800650054,
+      "grad_norm": NaN,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": NaN,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.3466955579631636,
+      "grad_norm": NaN,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.3553629469122427,
+      "grad_norm": NaN,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.3640303358613218,
+      "grad_norm": NaN,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.37269772481040087,
+      "grad_norm": NaN,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.38136511375947996,
+      "grad_norm": NaN,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.39003250270855905,
+      "grad_norm": NaN,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.39869989165763814,
+      "grad_norm": NaN,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.40736728060671723,
+      "grad_norm": NaN,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.4160346695557963,
+      "grad_norm": NaN,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.4247020585048754,
+      "grad_norm": NaN,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.4333694474539545,
+      "grad_norm": NaN,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.4333694474539545,
+      "eval_loss": NaN,
+      "eval_runtime": 0.5598,
+      "eval_samples_per_second": 89.311,
+      "eval_steps_per_second": 23.221,
+      "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": 4573046580969472.0,
+  "total_flos": 9144668088434688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null