Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9956b17eb6edecaedad09d6fc2bac91e393bcebfc5cfe7e93ef1969ed35bc1a7
+oid sha256:52c5a117069e91efb331d4be0da6cb08b7437539b7c7cc29ecff1790b036393e
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d027212f78f0fb972606f1a4c91ddde789aab4f37021a7c228443880b60d26
+oid sha256:ac401ff882921981d293983ac594e94028d70827cda690da07065a00bba4095e
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8497e2dfd6cdd94b957fa367bbb0fb1e5a205de32951a2d6b92b38d3709d06
+oid sha256:898f43b066fdbe3bfd6f517a46381f9c6a35006091bba02bc49e7641fe022adc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c855a970e911d5a2884c6d5b13fde78de630b71faaf3f49bfbdc0c11c72c3a
+oid sha256:d80e1ac448cbdc2ec9bbd5a0f208c9a73136674888818820496c826c86b9fc8e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8961ee511f8374e5a892d115f056e0316f707d650a2635d68c3a08ba6148a829
+oid sha256:c109fc573ae379e95c2c91fd6a89a8829b17cf63d199d9614b233041e0175e90
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f174f9c9b73218734eceb55a4c0af3b35a7f2b2ed56b3af27b2d3a9469f1b796
+oid sha256:a85f60443b94f9237bf37095f04a4e5e5407c04803d1b9906e0aa837a7025bdc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8222213983535767,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02767208578346593,
+  "best_metric": 0.810174822807312,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05534417156693186,
   "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": 68.22,
       "eval_steps_per_second": 8.529,
       "step": 25
+    },
+    {
+      "epoch": 0.028778969214804564,
+      "grad_norm": 2.719294548034668,
+      "learning_rate": 5e-05,
+      "loss": 0.896,
+      "step": 26
+    },
+    {
+      "epoch": 0.029885852646143202,
+      "grad_norm": 2.636077642440796,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8329,
+      "step": 27
+    },
+    {
+      "epoch": 0.03099273607748184,
+      "grad_norm": 2.847155809402466,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8251,
+      "step": 28
+    },
+    {
+      "epoch": 0.032099619508820475,
+      "grad_norm": 2.0352649688720703,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8154,
+      "step": 29
+    },
+    {
+      "epoch": 0.033206502940159116,
+      "grad_norm": 0.7650236487388611,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8079,
+      "step": 30
+    },
+    {
+      "epoch": 0.03431338637149775,
+      "grad_norm": 2.32476544380188,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8349,
+      "step": 31
+    },
+    {
+      "epoch": 0.03542026980283639,
+      "grad_norm": 1.8150771856307983,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8164,
+      "step": 32
+    },
+    {
+      "epoch": 0.036527153234175026,
+      "grad_norm": 2.106776475906372,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8064,
+      "step": 33
+    },
+    {
+      "epoch": 0.03763403666551366,
+      "grad_norm": 1.8922873735427856,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8115,
+      "step": 34
+    },
+    {
+      "epoch": 0.0387409200968523,
+      "grad_norm": 0.8627958297729492,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8152,
+      "step": 35
+    },
+    {
+      "epoch": 0.039847803528190937,
+      "grad_norm": 1.8673175573349,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8271,
+      "step": 36
+    },
+    {
+      "epoch": 0.04095468695952958,
+      "grad_norm": 1.2413160800933838,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8219,
+      "step": 37
+    },
+    {
+      "epoch": 0.04206157039086821,
+      "grad_norm": 7.430208683013916,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.907,
+      "step": 38
+    },
+    {
+      "epoch": 0.04316845382220685,
+      "grad_norm": 1.2367589473724365,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8171,
+      "step": 39
+    },
+    {
+      "epoch": 0.04427533725354549,
+      "grad_norm": 0.9270449280738831,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8097,
+      "step": 40
+    },
+    {
+      "epoch": 0.04538222068488412,
+      "grad_norm": 1.416707992553711,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8108,
+      "step": 41
+    },
+    {
+      "epoch": 0.04648910411622276,
+      "grad_norm": 1.3523006439208984,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8149,
+      "step": 42
+    },
+    {
+      "epoch": 0.0475959875475614,
+      "grad_norm": 1.1008036136627197,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8135,
+      "step": 43
+    },
+    {
+      "epoch": 0.04870287097890003,
+      "grad_norm": 2.912865161895752,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8138,
+      "step": 44
+    },
+    {
+      "epoch": 0.049809754410238674,
+      "grad_norm": 1.1399955749511719,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.808,
+      "step": 45
+    },
+    {
+      "epoch": 0.05091663784157731,
+      "grad_norm": 2.1416749954223633,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8049,
+      "step": 46
+    },
+    {
+      "epoch": 0.05202352127291594,
+      "grad_norm": 1.4024479389190674,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8255,
+      "step": 47
+    },
+    {
+      "epoch": 0.053130404704254584,
+      "grad_norm": 1.4611579179763794,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8113,
+      "step": 48
+    },
+    {
+      "epoch": 0.05423728813559322,
+      "grad_norm": 1.3440361022949219,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.808,
+      "step": 49
+    },
+    {
+      "epoch": 0.05534417156693186,
+      "grad_norm": 1.4476083517074585,
+      "learning_rate": 0.0,
+      "loss": 0.8002,
+      "step": 50
+    },
+    {
+      "epoch": 0.05534417156693186,
+      "eval_loss": 0.810174822807312,
+      "eval_runtime": 89.657,
+      "eval_samples_per_second": 67.892,
+      "eval_steps_per_second": 8.488,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.280112884822835e+16,
+  "total_flos": 1.6535390389692006e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null