Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0243739d7234437280d6d6acc558ec78ff05d5bb455d9446ff3a92e550748d
+oid sha256:869549ce07a3ea7650662b157fd746b253ac6955bbc7a631b49808e299128e63
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9ce26cd6cb7597ac8e38b232252c0255213705a7cf5aa6d7b4e3592b7f721a
+oid sha256:42e002101439c9db67fafe487ade423679d20e82ae9bb353e9e1fc897d9541e6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d3c14498426ade58c588ad688d79c4152b96f1b2a00367f32697940d06af86
+oid sha256:66f9a42faaae21610ab8e08dc5353731d3cce135fbbbb7c2f746e78dc063a96b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de2e8eadcfe860f4e23dded4999d6540c4bc0b284cf7975c1e26bbcf9e8922b
+oid sha256:0ca4973c38071556ba5da02303d7577fc8c5131a4c7870ae9a3c102ff9caeff4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb5e2d9fcff1b79ab0b75fd410d6dca510aae4c2aeda7e05c393fe21bb6994d
+oid sha256:cb25f8e70596d5704cdbd6f56b65e697699063e588b6d00c730f63e624daa5bc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c13cb0323d7065705d590003ec0bb68a10f2ec87a295ccc4fd2c1bc203be259
+oid sha256:418440d39ab803bb1f6ef5be239140cac25476d37b30b6c4cca2cefa83019347
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9965410232543945,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.2668250197941409,
+  "best_metric": 1.9676353931427002,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.9002375296912115,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 11.464,
       "eval_steps_per_second": 2.981,
       "step": 50
+    },
+    {
+      "epoch": 1.2921615201900236,
+      "grad_norm": 0.6857823729515076,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9029,
+      "step": 51
+    },
+    {
+      "epoch": 1.3174980205859066,
+      "grad_norm": 0.6684339642524719,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 1.7395,
+      "step": 52
+    },
+    {
+      "epoch": 1.3428345209817893,
+      "grad_norm": 0.6476242542266846,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 1.8194,
+      "step": 53
+    },
+    {
+      "epoch": 1.3681710213776723,
+      "grad_norm": 0.6561811566352844,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.8019,
+      "step": 54
+    },
+    {
+      "epoch": 1.393507521773555,
+      "grad_norm": 0.655868649482727,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 1.6997,
+      "step": 55
+    },
+    {
+      "epoch": 1.4188440221694378,
+      "grad_norm": 0.6722643375396729,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 1.926,
+      "step": 56
+    },
+    {
+      "epoch": 1.4441805225653206,
+      "grad_norm": 0.6922515034675598,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.9037,
+      "step": 57
+    },
+    {
+      "epoch": 1.4695170229612033,
+      "grad_norm": 0.7588927149772644,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 1.9156,
+      "step": 58
+    },
+    {
+      "epoch": 1.4948535233570863,
+      "grad_norm": 0.6962288618087769,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 1.835,
+      "step": 59
+    },
+    {
+      "epoch": 1.520190023752969,
+      "grad_norm": 0.7170149683952332,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.7774,
+      "step": 60
+    },
+    {
+      "epoch": 1.545526524148852,
+      "grad_norm": 0.677159309387207,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 1.8,
+      "step": 61
+    },
+    {
+      "epoch": 1.5708630245447348,
+      "grad_norm": 0.7060984969139099,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 1.8481,
+      "step": 62
+    },
+    {
+      "epoch": 1.5961995249406176,
+      "grad_norm": 0.8111439943313599,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.772,
+      "step": 63
+    },
+    {
+      "epoch": 1.6215360253365003,
+      "grad_norm": 0.6780772805213928,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 1.7634,
+      "step": 64
+    },
+    {
+      "epoch": 1.646872525732383,
+      "grad_norm": 0.6579707860946655,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 1.8308,
+      "step": 65
+    },
+    {
+      "epoch": 1.672209026128266,
+      "grad_norm": 0.6961445808410645,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.8009,
+      "step": 66
+    },
+    {
+      "epoch": 1.6975455265241488,
+      "grad_norm": 0.7140675187110901,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 1.7937,
+      "step": 67
+    },
+    {
+      "epoch": 1.7228820269200318,
+      "grad_norm": 0.817320704460144,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 1.7937,
+      "step": 68
+    },
+    {
+      "epoch": 1.7482185273159145,
+      "grad_norm": 0.6845941543579102,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.699,
+      "step": 69
+    },
+    {
+      "epoch": 1.7735550277117973,
+      "grad_norm": 0.6956932544708252,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 1.8236,
+      "step": 70
+    },
+    {
+      "epoch": 1.79889152810768,
+      "grad_norm": 0.6442613005638123,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 1.7499,
+      "step": 71
+    },
+    {
+      "epoch": 1.8242280285035628,
+      "grad_norm": 0.7191362380981445,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8782,
+      "step": 72
+    },
+    {
+      "epoch": 1.8495645288994458,
+      "grad_norm": 0.697597324848175,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 1.8019,
+      "step": 73
+    },
+    {
+      "epoch": 1.8749010292953285,
+      "grad_norm": 0.7081029415130615,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 1.8513,
+      "step": 74
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "grad_norm": 0.6932956576347351,
+      "learning_rate": 1e-05,
+      "loss": 1.7828,
+      "step": 75
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "eval_loss": 1.9676353931427002,
+      "eval_runtime": 4.4978,
+      "eval_samples_per_second": 11.116,
+      "eval_steps_per_second": 2.89,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.968083617316864e+17,
+  "total_flos": 8.952125425975296e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null