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:bd85eae4563d08f6deea624ac62d6c377e01129afb8c512e96f694b66b14fbfc
+oid sha256:b9e52ab4049fb88bf6300474783e1923795fe4e5207e28f7002b5b7874f44631
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265d475b371feb5a718774e35654e9361c71b3378dd0463a905ed61819bc330c
+oid sha256:8877dc1759b8c492143c13c9df19728ec9efdca27600077af5eb112cc7657981
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9843d8402d9ee188134d84f42e2342b68e4053c1a2eccbbb12b015b0c6575ba8
+oid sha256:4fe1c00cbd476b58cc11c2f05045f79eb656fa77c7b0dd5d7eeeda199050c61b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3578774929046631,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.4296455424274973,
+  "epoch": 0.644468313641246,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 7.839,
       "eval_steps_per_second": 1.96,
       "step": 50
+    },
+    {
+      "epoch": 0.43823845327604727,
+      "grad_norm": 5.766439914703369,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 4.9625,
+      "step": 51
+    },
+    {
+      "epoch": 0.44683136412459723,
+      "grad_norm": 5.521291255950928,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 4.9848,
+      "step": 52
+    },
+    {
+      "epoch": 0.45542427497314714,
+      "grad_norm": 6.785717487335205,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.913,
+      "step": 53
+    },
+    {
+      "epoch": 0.4640171858216971,
+      "grad_norm": 6.411205768585205,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 5.3654,
+      "step": 54
+    },
+    {
+      "epoch": 0.47261009667024706,
+      "grad_norm": 5.137513637542725,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 4.7431,
+      "step": 55
+    },
+    {
+      "epoch": 0.48120300751879697,
+      "grad_norm": 6.2091755867004395,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 4.7387,
+      "step": 56
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 6.7059173583984375,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 5.7861,
+      "step": 57
+    },
+    {
+      "epoch": 0.4983888292158969,
+      "grad_norm": 7.024590969085693,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 5.8263,
+      "step": 58
+    },
+    {
+      "epoch": 0.5069817400644469,
+      "grad_norm": 6.100332736968994,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 4.9064,
+      "step": 59
+    },
+    {
+      "epoch": 0.5155746509129968,
+      "grad_norm": 5.492628574371338,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 4.977,
+      "step": 60
+    },
+    {
+      "epoch": 0.5241675617615468,
+      "grad_norm": 6.51470947265625,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 4.8705,
+      "step": 61
+    },
+    {
+      "epoch": 0.5327604726100966,
+      "grad_norm": 5.699104309082031,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 5.0406,
+      "step": 62
+    },
+    {
+      "epoch": 0.5413533834586466,
+      "grad_norm": 5.825130939483643,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 5.1809,
+      "step": 63
+    },
+    {
+      "epoch": 0.5499462943071965,
+      "grad_norm": 6.401869773864746,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.0405,
+      "step": 64
+    },
+    {
+      "epoch": 0.5585392051557465,
+      "grad_norm": 6.119671821594238,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 5.5007,
+      "step": 65
+    },
+    {
+      "epoch": 0.5671321160042965,
+      "grad_norm": 6.092080593109131,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 4.8658,
+      "step": 66
+    },
+    {
+      "epoch": 0.5757250268528464,
+      "grad_norm": 5.349208831787109,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 4.3778,
+      "step": 67
+    },
+    {
+      "epoch": 0.5843179377013964,
+      "grad_norm": 5.576518535614014,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 4.7543,
+      "step": 68
+    },
+    {
+      "epoch": 0.5929108485499462,
+      "grad_norm": 5.412608623504639,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 4.2394,
+      "step": 69
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 5.888413906097412,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 5.4023,
+      "step": 70
+    },
+    {
+      "epoch": 0.6100966702470462,
+      "grad_norm": 5.344703197479248,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 4.2625,
+      "step": 71
+    },
+    {
+      "epoch": 0.6186895810955961,
+      "grad_norm": 5.677237033843994,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 4.9872,
+      "step": 72
+    },
+    {
+      "epoch": 0.6272824919441461,
+      "grad_norm": 6.14519739151001,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 4.9022,
+      "step": 73
+    },
+    {
+      "epoch": 0.635875402792696,
+      "grad_norm": 5.074471950531006,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 4.4077,
+      "step": 74
+    },
+    {
+      "epoch": 0.644468313641246,
+      "grad_norm": 5.900351047515869,
+      "learning_rate": 0.0,
+      "loss": 5.002,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.661017318326272e+17,
+  "total_flos": 3.991525977489408e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null