Training in progress, step 41, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4bb5e14e592797900f9828ecd62e75298eb9db6a493f528dfa4bf2add9878ed
+oid sha256:36854da82eebc6281470a8f98759334be3028312727cf6f7c3ef7111ed34ccf2
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b800eb6b07d5f608865e110d85562e4874f7f7d50d721bea5d1af5a5bef8ca
+oid sha256:6a67b36221154d01dcdfe1d5a965278859e1a0b9d5f2e471766e085b8573386a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7fa24dd339f02eaf48c538fb4068b5df21da0e6ac754d8f37bcee599eae6d5
+oid sha256:9205b1b712796c0cee6cc9e94c01022b48ec463c8cbb5d3a05af9e958a2b0bdf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e35481f632a8fde4f21e2b928a87e59f63ee97da06c7ff9ddf4309a57a6ff938
+oid sha256:2aa03cfdb460331126f61902abf4e9733bb6ea90f1e9c2147c28e1f559319153
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a40cbf2d19b21a23676917dbe8144796f8784860cbdb93b0c2d0080098b0dc
+oid sha256:122b95b809248b81e4a1a5e06af2523f74a0398d3ba658b5e6892cd9ec6030cf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6b77c0cbcc35c1c43ee60e2766b6027d2e111edae589e45f75af1b1040b32d
+oid sha256:84fc982e8229d2121603832a24f4c07bbdbf63985ed1d38e11762164a04dad3b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8755760368663594,
+  "epoch": 3.119815668202765,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 41,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,118 @@
       "eval_samples_per_second": 55.52,
       "eval_steps_per_second": 7.242,
       "step": 25
+    },
+    {
+      "epoch": 1.9493087557603688,
+      "grad_norm": NaN,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.055299539170507,
+      "grad_norm": NaN,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.2027649769585254,
+      "grad_norm": NaN,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.2764976958525347,
+      "grad_norm": NaN,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.3502304147465436,
+      "grad_norm": NaN,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.423963133640553,
+      "grad_norm": NaN,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.4976958525345623,
+      "grad_norm": NaN,
+      "learning_rate": 1.0027861829824952e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": NaN,
+      "learning_rate": 7.740495722810271e-06,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": NaN,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.71889400921659,
+      "grad_norm": NaN,
+      "learning_rate": 4.001027817058789e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.792626728110599,
+      "grad_norm": NaN,
+      "learning_rate": 2.573177902642726e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.8663594470046085,
+      "grad_norm": NaN,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.9400921658986174,
+      "grad_norm": NaN,
+      "learning_rate": 6.474868681043578e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 3.046082949308756,
+      "grad_norm": NaN,
+      "learning_rate": 1.6213459328950352e-07,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 3.119815668202765,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 41
     }
   ],
   "logging_steps": 1,
@@ -221,12 +333,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 1.827986893480919e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null