Training in progress, step 47, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7cb338c9e4f52e185611fa5ebdeb2fcc09ec96085c3ba20364802b27d452e2
+oid sha256:fca7d4bf27d019529667eeb03d9514e1b0d8cb2beff46f8868395ea75d529c54
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3016cc1472c18e010ba7901f93b7899bc9af298175d1f1c11b4b804170e05328
+oid sha256:040b590b03d63b6f70dd36f44d1ab902b3d5ff26e9fd7afe27af2e4c81fcdb04
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999c7023dd74a9189700b85bf8e897fb71f48363106caa42c4c653f1d0803bfb
+oid sha256:4c0eaca07fd3c1afba6c26369aab668e1e5a207788a357d2eae6017e966551b6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692a625985a08985b4dbd43ee431876ebe941fc466669efcacc41e693a63c6ea
+oid sha256:f17c3ef129bde43126e5cc6deb1d6497e9b8a6578161070020489f2058b9e681
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead6f9482ed51015a12bb67d002b22e48b78cc984aae379e34934c5284a1b922
+oid sha256:ead8f03f7b71abf48441a5f4a5add3373f19a96d4aa4266991fbaee2431e3959
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd1e9eb3518cb595de2abfd538b63c35bc4b6da1cbc3260da720045ae6e9bd6
+oid sha256:ba6a55615dc406ba4ab712210ff78d01aec254d42fc95771a1e235d0a386bab2
 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": 10.767499923706055,
   "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": 366.634,
       "eval_steps_per_second": 95.325,
       "step": 25
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": 29.69610023498535,
+      "learning_rate": 5.0296219152955604e-05,
+      "loss": 344.3281,
+      "step": 26
+    },
+    {
+      "epoch": 1.7419354838709677,
+      "grad_norm": 28.275226593017578,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 344.4609,
+      "step": 27
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 28.87457275390625,
+      "learning_rate": 4.411351469801496e-05,
+      "loss": 343.75,
+      "step": 28
+    },
+    {
+      "epoch": 1.870967741935484,
+      "grad_norm": 28.58711051940918,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 343.9453,
+      "step": 29
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 26.832551956176758,
+      "learning_rate": 3.814270329628396e-05,
+      "loss": 343.8203,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 25.824234008789062,
+      "learning_rate": 3.5273298394491515e-05,
+      "loss": 344.0703,
+      "step": 31
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 27.011585235595703,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 343.4297,
+      "step": 32
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": 25.50615692138672,
+      "learning_rate": 2.98363193438164e-05,
+      "loss": 343.1797,
+      "step": 33
+    },
+    {
+      "epoch": 2.193548387096774,
+      "grad_norm": 25.1122989654541,
+      "learning_rate": 2.729523361034538e-05,
+      "loss": 343.3906,
+      "step": 34
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 24.4768009185791,
+      "learning_rate": 2.4889122713851394e-05,
+      "loss": 343.5859,
+      "step": 35
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 24.391756057739258,
+      "learning_rate": 2.2629708984760708e-05,
+      "loss": 342.9453,
+      "step": 36
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 24.137502670288086,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 343.3906,
+      "step": 37
+    },
+    {
+      "epoch": 2.4516129032258065,
+      "grad_norm": 23.468700408935547,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 343.0078,
+      "step": 38
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 24.317951202392578,
+      "learning_rate": 1.6837835672960835e-05,
+      "loss": 343.1641,
+      "step": 39
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 22.979093551635742,
+      "learning_rate": 1.526735832134829e-05,
+      "loss": 343.2578,
+      "step": 40
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": 23.326814651489258,
+      "learning_rate": 1.389045440608296e-05,
+      "loss": 343.3594,
+      "step": 41
+    },
+    {
+      "epoch": 2.709677419354839,
+      "grad_norm": 25.22893524169922,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 343.1016,
+      "step": 42
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 24.642864227294922,
+      "learning_rate": 1.174322368277565e-05,
+      "loss": 342.8438,
+      "step": 43
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 23.94510269165039,
+      "learning_rate": 1.0983357966978745e-05,
+      "loss": 342.8516,
+      "step": 44
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 24.486724853515625,
+      "learning_rate": 1.0437936906629336e-05,
+      "loss": 343.0625,
+      "step": 45
+    },
+    {
+      "epoch": 2.967741935483871,
+      "grad_norm": 22.408733367919922,
+      "learning_rate": 1.0109617738307912e-05,
+      "loss": 343.1406,
+      "step": 46
+    },
+    {
+      "epoch": 3.032258064516129,
+      "grad_norm": 22.481307983398438,
+      "learning_rate": 1e-05,
+      "loss": 342.8672,
+      "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": 2101346304000.0,
+  "total_flos": 3950531051520.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null