Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ced2e74c6679d2ac80c760852650459a60cc2da84fa39a4e7ac2ce334db946
+oid sha256:4b79d4ed598dc28a533adcfa8d039d4417f423af7f8b6826497f753633419dcf
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff85b135550200065f0e6b969516acf96b5a54b4c3b9c45449821d82f1d7d921
+oid sha256:3534b4e1fd5497b2146a9c33b902b1f4b51ba5fed7d18d649d0394befc066030
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b3381b335f602890461bd05168a4491511a615e7aa209ecfd0925b0b6db317
+oid sha256:6ce493e57681fc37e3ff5b95e8027c3f80955725288ff08d9b06668535db5635
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54cca545148e67306864518a04156cdba94dfc100a47ce7cd708743f970729c
+oid sha256:e12277bd91374fb806b6ae7b37905de7eb73d683910017d2c1cdb1a6631ba39d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da71f16dc4ec26ee10e2764eb40b80b8f27b079e7541a7c293afa6cdf782c204
+oid sha256:583f819abde01f18bc36049c7dc0d751817b83dec1e2532df403a4756a9754b1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006142458979891125,
+  "epoch": 0.01228491795978225,
   "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": 23.935,
       "eval_steps_per_second": 6.223,
       "step": 25
+    },
+    {
+      "epoch": 0.00638815733908677,
+      "grad_norm": NaN,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.006633855698282415,
+      "grad_norm": NaN,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00687955405747806,
+      "grad_norm": NaN,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0071252524166737045,
+      "grad_norm": NaN,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.00737095077586935,
+      "grad_norm": NaN,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.007616649135064995,
+      "grad_norm": NaN,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.00786234749426064,
+      "grad_norm": NaN,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.008108045853456284,
+      "grad_norm": NaN,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.00835374421265193,
+      "grad_norm": NaN,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.008599442571847575,
+      "grad_norm": NaN,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.00884514093104322,
+      "grad_norm": NaN,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.009090839290238864,
+      "grad_norm": NaN,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.00933653764943451,
+      "grad_norm": NaN,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.009582236008630155,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0098279343678258,
+      "grad_norm": NaN,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.010073632727021446,
+      "grad_norm": NaN,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.01031933108621709,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.010565029445412735,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.010810727804608379,
+      "grad_norm": NaN,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.011056426163804025,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.01130212452299967,
+      "grad_norm": NaN,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.011547822882195314,
+      "grad_norm": NaN,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.01179352124139096,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.012039219600586605,
+      "grad_norm": NaN,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.01228491795978225,
+      "grad_norm": NaN,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.01228491795978225,
+      "eval_loss": NaN,
+      "eval_runtime": 2.0916,
+      "eval_samples_per_second": 23.905,
+      "eval_steps_per_second": 6.215,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null