Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6914269dd038a1dbdecaa321b89b2d8e25f05d52ec365f8dcf514487a9a3d8c2
+oid sha256:54ee43fc5f58124c21e3a4c0d8b1586e9d7e38283b8d7213fd2c7b6f24d55304
 size 83444

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f44e1191c733443a42bce87f06f49aafde9eb5cb2d833a1903f201b53f92eab
+oid sha256:25748f80b13dedfa7d5e79c2e484111f2933cb5c568597862b720f427690dd66
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ed465a4fc200765e8ccd6acf838ca4c0ae77689f42ffcf76faf48dd5c5ab4a
+oid sha256:ce674f7ec381d9bbad2cbedb1a5115b5d56671d5d1fe436e4c1c2e845ec95538
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b6baf2a8fccd5423d0609e5ebcfbcb203654ca1a8401b31dca5443188276f2
+oid sha256:6e1d4d5498d6c5ef2c0360df62e5551aac1f65bd684d5a035fc8282c3ab587ef
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35131e2c4997b8fe5849a1090f7901d786340dcf9cb292a401a5d48ee9a841f2
+oid sha256:682fc985f8a446cb1a569aa45e2c5ae187cc6abc66956380f56c7481279b8e3f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc88e7d65559f7afaefa8b145d1c44dc0ee30279ded33e0aa9088f4dd3e6ebe9
+oid sha256:5944ca453651b578debe25abafd3e4df9d88b7d02679eedc512f6c282a4eb97c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1764705882352942,
+  "epoch": 2.3529411764705883,
   "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": 185.803,
       "eval_steps_per_second": 48.309,
       "step": 25
+    },
+    {
+      "epoch": 1.223529411764706,
+      "grad_norm": NaN,
+      "learning_rate": 7.062873637801692e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.2705882352941176,
+      "grad_norm": NaN,
+      "learning_rate": 6.847134053380112e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.3176470588235294,
+      "grad_norm": NaN,
+      "learning_rate": 6.627936395164243e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.3647058823529412,
+      "grad_norm": NaN,
+      "learning_rate": 6.40584334039897e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": NaN,
+      "learning_rate": 6.181424998770595e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.4588235294117646,
+      "grad_norm": NaN,
+      "learning_rate": 5.955257448943445e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.5058823529411764,
+      "grad_norm": NaN,
+      "learning_rate": 5.727921259774208e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.5529411764705883,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": NaN,
+      "learning_rate": 5.2720787402257935e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": NaN,
+      "learning_rate": 5.044742551056556e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.6941176470588235,
+      "grad_norm": NaN,
+      "learning_rate": 4.8185750012294065e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.7411764705882353,
+      "grad_norm": NaN,
+      "learning_rate": 4.594156659601029e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.788235294117647,
+      "grad_norm": NaN,
+      "learning_rate": 4.372063604835758e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.835294117647059,
+      "grad_norm": NaN,
+      "learning_rate": 4.152865946619889e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": NaN,
+      "learning_rate": 3.93712636219831e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.9294117647058824,
+      "grad_norm": NaN,
+      "learning_rate": 3.725398651990067e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.9764705882352942,
+      "grad_norm": NaN,
+      "learning_rate": 3.518226317990646e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.023529411764706,
+      "grad_norm": NaN,
+      "learning_rate": 3.3161411686101364e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.070588235294118,
+      "grad_norm": NaN,
+      "learning_rate": 3.119661953528671e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": NaN,
+      "learning_rate": 2.9292930320734335e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.164705882352941,
+      "grad_norm": NaN,
+      "learning_rate": 2.745523078535517e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.211764705882353,
+      "grad_norm": NaN,
+      "learning_rate": 2.568823827750001e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.2588235294117647,
+      "grad_norm": NaN,
+      "learning_rate": 2.39964886415941e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.3058823529411763,
+      "grad_norm": NaN,
+      "learning_rate": 2.2384324574689612e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": NaN,
+      "learning_rate": 2.0855884478824412e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": NaN,
+      "eval_runtime": 0.283,
+      "eval_samples_per_second": 176.67,
+      "eval_steps_per_second": 45.934,
+      "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": 468027310080.0,
+  "total_flos": 938425712640.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null