Training in progress, step 47, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24983b1cd53a8d2c6ce310b72e3bafcef3837703378d3c3a2fb92dfb4ae92ed
+oid sha256:ee09aec7a162d96f128ad2740f436a015fef670042dc381af9a3e8b576b751e3
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b638b0efe5ca13f5f91c944820fd06763528f7fe2845d1f5e3805274330255
+oid sha256:a357d61cd75ac1eb3919611834c23e574768cef294bb4bf80cc8491ce2169688
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:353cfc9ab073168d083716b479beaa628d66dbfcbefc96a8f211cb9535d8b924
+oid sha256:8fdcaad1583c12ede1cb10b4d1cced2c311311df000c261221c563dcf5b56395
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978a72f368efc715e72e7b84ec51631c400b9579e4fc7f083f1a636cb16e5ce4
+oid sha256:61d6e6358d2b79829c40d0f403eaa4a490c3bee5b1f11ec3bf05fb6788a09007
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fcb228050e76ff5d8741bdf2c7cf05dd3ce3320c43f73840774c160b11dd25f
+oid sha256:abde73cdc5a674d8ba414581849ce4f061f8d8d22b076474d82b2af938881a4e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a25230216c7a49e9024a60f6b2ba44b71176046374fb4d551a7f778d26456d
+oid sha256:0450ceb846581ea6cc2effaa1b64a4cf3fc14799532fcc3c887a5695b8adb55d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6129032258064515,
+  "epoch": 3.032258064516129,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 47,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,160 @@
       "eval_samples_per_second": 16.409,
       "eval_steps_per_second": 4.266,
       "step": 25
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": NaN,
+      "learning_rate": 5.0296219152955604e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.7419354838709677,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": NaN,
+      "learning_rate": 4.411351469801496e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.870967741935484,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": NaN,
+      "learning_rate": 3.814270329628396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": NaN,
+      "learning_rate": 3.5273298394491515e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": NaN,
+      "learning_rate": 2.98363193438164e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.193548387096774,
+      "grad_norm": NaN,
+      "learning_rate": 2.729523361034538e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": NaN,
+      "learning_rate": 2.4889122713851394e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": NaN,
+      "learning_rate": 2.2629708984760708e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": NaN,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.4516129032258065,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": NaN,
+      "learning_rate": 1.6837835672960835e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": NaN,
+      "learning_rate": 1.526735832134829e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": NaN,
+      "learning_rate": 1.389045440608296e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.709677419354839,
+      "grad_norm": NaN,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": NaN,
+      "learning_rate": 1.174322368277565e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": NaN,
+      "learning_rate": 1.0983357966978745e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": NaN,
+      "learning_rate": 1.0437936906629336e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.967741935483871,
+      "grad_norm": NaN,
+      "learning_rate": 1.0109617738307912e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 3.032258064516129,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 47
     }
   ],
   "logging_steps": 1,
@@ -221,12 +375,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.629578157719552e+17,
+  "total_flos": 4.943606936512758e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null