Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f81e6e8d9cf67fb121fb45a8e43765778aa57e94a0567d466361bf38b2d77e8
+oid sha256:7e1ee680d7b7627c4d773a5c694ac05461fca2e2cd005fcc5db6eb0d8c4b45ed
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff940a8625023f5dd9e8ef1e50c4401a8e3a31bcea02931167c1687bc67f9b7
+oid sha256:badc052e5e51889cfe01e36892f200aecbdb019630c78226e08e06fbaa698787
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764657b588c7abcecc9038a860b277d001da3e7bc8d8b97aa8559e30c0c6888a
+oid sha256:fe49e8e0555f58cdb6bfabf1f23d60441fc05105ca5cfa21fc9003cbee03b001
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5d0f13fc880b80175d459a857ab58a9799f82b3e2dc72f5fe7fb12e207fef0
+oid sha256:32bdd0c9eb73074337ecf71cb0112ec208eeb85d5bd67a6bc9f812cbdcdcc76f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0e0d8970019045b753082d9f44fc99bd4b3d56a9360aac104dde0233bb7714
+oid sha256:84c82bf2afa11dfabf99ab7214d2b93b0925b724cf2f40f16842a026028b8904
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ef890c46cc11df42991e281afd32264bfc5bd1c59b5107fcefc9b146bee4ba
+oid sha256:b39fb49eb25937c70bfb3f8df38ab45a7c74c48dff975543d7363364a0fbbb28
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2167118787765503,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0618190248048837,
+  "best_metric": 1.126763105392456,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1236380496097674,
   "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": 21.672,
       "eval_steps_per_second": 5.635,
       "step": 25
+    },
+    {
+      "epoch": 0.06429178579707905,
+      "grad_norm": 37.73557662963867,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 39.1072,
+      "step": 26
+    },
+    {
+      "epoch": 0.0667645467892744,
+      "grad_norm": 39.4856071472168,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 40.2629,
+      "step": 27
+    },
+    {
+      "epoch": 0.06923730778146975,
+      "grad_norm": 33.05232620239258,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 38.4942,
+      "step": 28
+    },
+    {
+      "epoch": 0.07171006877366509,
+      "grad_norm": 29.005043029785156,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 38.0044,
+      "step": 29
+    },
+    {
+      "epoch": 0.07418282976586045,
+      "grad_norm": 29.954980850219727,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 38.3598,
+      "step": 30
+    },
+    {
+      "epoch": 0.0766555907580558,
+      "grad_norm": 31.648218154907227,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 38.6649,
+      "step": 31
+    },
+    {
+      "epoch": 0.07912835175025114,
+      "grad_norm": 43.9088134765625,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 37.3321,
+      "step": 32
+    },
+    {
+      "epoch": 0.08160111274244648,
+      "grad_norm": 45.55607604980469,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 34.0225,
+      "step": 33
+    },
+    {
+      "epoch": 0.08407387373464184,
+      "grad_norm": 74.37454986572266,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 36.4667,
+      "step": 34
+    },
+    {
+      "epoch": 0.08654663472683718,
+      "grad_norm": 66.72908782958984,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 33.7556,
+      "step": 35
+    },
+    {
+      "epoch": 0.08901939571903253,
+      "grad_norm": 82.05652618408203,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 35.8552,
+      "step": 36
+    },
+    {
+      "epoch": 0.09149215671122789,
+      "grad_norm": 118.45052337646484,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 41.1993,
+      "step": 37
+    },
+    {
+      "epoch": 0.09396491770342323,
+      "grad_norm": 105.6920394897461,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 40.8987,
+      "step": 38
+    },
+    {
+      "epoch": 0.09643767869561858,
+      "grad_norm": 34.49168014526367,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 36.2643,
+      "step": 39
+    },
+    {
+      "epoch": 0.09891043968781392,
+      "grad_norm": 24.8678035736084,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 37.1254,
+      "step": 40
+    },
+    {
+      "epoch": 0.10138320068000928,
+      "grad_norm": 24.664064407348633,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 37.3573,
+      "step": 41
+    },
+    {
+      "epoch": 0.10385596167220462,
+      "grad_norm": 24.782764434814453,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 37.732,
+      "step": 42
+    },
+    {
+      "epoch": 0.10632872266439997,
+      "grad_norm": 27.32329750061035,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 37.1562,
+      "step": 43
+    },
+    {
+      "epoch": 0.10880148365659531,
+      "grad_norm": 30.12747573852539,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 37.8521,
+      "step": 44
+    },
+    {
+      "epoch": 0.11127424464879067,
+      "grad_norm": 42.28104019165039,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 36.7405,
+      "step": 45
+    },
+    {
+      "epoch": 0.11374700564098601,
+      "grad_norm": 81.71856689453125,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 33.6306,
+      "step": 46
+    },
+    {
+      "epoch": 0.11621976663318136,
+      "grad_norm": 55.820823669433594,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 34.3689,
+      "step": 47
+    },
+    {
+      "epoch": 0.11869252762537671,
+      "grad_norm": 68.78173065185547,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 36.5956,
+      "step": 48
+    },
+    {
+      "epoch": 0.12116528861757206,
+      "grad_norm": 112.97760772705078,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 40.6305,
+      "step": 49
+    },
+    {
+      "epoch": 0.1236380496097674,
+      "grad_norm": 154.30474853515625,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 48.397,
+      "step": 50
+    },
+    {
+      "epoch": 0.1236380496097674,
+      "eval_loss": 1.126763105392456,
+      "eval_runtime": 2.3094,
+      "eval_samples_per_second": 21.651,
+      "eval_steps_per_second": 5.629,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null