Training in progress, step 43, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:162f246c6adc3a443e9166b16828f975e75d302abaedb7f66a8e0766b13debbf
+oid sha256:501727b2907ea39b429a68100a00e332a4f87d4f9cc6be7a2815a2706129b74c
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5c0fc699e4a84bd20a5db050d3325c15510d8a0646518521770398f23b2bb1
+oid sha256:497f6e327a4df5b91387bdd5a5bbe0eedc009cac1877614d3bccffae9eaaf407
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a828325a58bc744cb4d0ecef7c7b4b8aa50cd4bef0cdbc0cdac1f9dae32740d
+oid sha256:2f4b14777f08565c9faf305fd6bc5b0ac63c862a66842f6001553e92868f815f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c79849e7e7ccefcc8213faac7e2b0c494ccf961e07e9f4289e8702b994c706
+oid sha256:5aec49109d4a24b63ed77ec025b5e972916d05f73c0cc5b69480227411b5ebb7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377fdbdd15df914f1dcdc6c32f078e4226c7905ab6027e54c22ed62d69579d1b
+oid sha256:64d10defdae3223de7f0dcfe5041b2f2277296d11ade06d4d56f403247a2d6d8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7510917030567685,
+  "epoch": 3.017467248908297,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 68.323,
       "eval_steps_per_second": 17.764,
       "step": 25
+    },
+    {
+      "epoch": 1.8209606986899565,
+      "grad_norm": NaN,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.890829694323144,
+      "grad_norm": NaN,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.960698689956332,
+      "grad_norm": NaN,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.034934497816594,
+      "grad_norm": NaN,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.1048034934497815,
+      "grad_norm": NaN,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.1746724890829694,
+      "grad_norm": NaN,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.2445414847161573,
+      "grad_norm": NaN,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.314410480349345,
+      "grad_norm": NaN,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.3842794759825328,
+      "grad_norm": NaN,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.4541484716157207,
+      "grad_norm": NaN,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.524017467248908,
+      "grad_norm": NaN,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.593886462882096,
+      "grad_norm": NaN,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.6637554585152836,
+      "grad_norm": NaN,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.7336244541484715,
+      "grad_norm": NaN,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.8034934497816595,
+      "grad_norm": NaN,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.8733624454148474,
+      "grad_norm": NaN,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.943231441048035,
+      "grad_norm": NaN,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 3.017467248908297,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "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": 9.112012643421389e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null