Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ad8cb16a9c3ce9df6cdcabf93556449d22778da54b87dcd2aa55e1c712d549
+oid sha256:3fdfea562ed117b0f0a6aa09a8e712053815dada64078fbd832a37bdb47c560b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43bb7479d3e2826b70b2fa71414269a2414bf07b9470e8b9b11fc2e0e568b892
+oid sha256:01df707eee622d10af731286a4dc57b587f417970d63ab91d76b1fdd0f53b328
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca3f749e748ab602c07591ae9d61df72e5709495d0ed54dc7f9f7b8e38d1f52
+oid sha256:a92cc19839144006d0b1bea40e4e77ad8c6ab443719d7516df07ef9aa91c64a5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d03c013789f95776005807c916ec810746d83c3eb0d085f25aa7e9298201a082
+oid sha256:1938d50f46120f39e5abdfc90d7f40330c614d9ef81d9a3ae8c31100a60a599f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b59e8aa9904739f5588592838cdcaf3524030bad86f6323689b1c4673fa6a390
+oid sha256:6431e099fdfb276beb8ad5dd3a41c09c98fd42633a3d7e82fbdc46bced3c4b1f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b21cd3608b94bb9499f2b40f341787d7986660189088f53a96f29b49e02d8d8
+oid sha256:7c2b71659a629d3021beb22a82451fe5e5a28771130d28ebf768b27f962daabc
 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": 1.374174952507019,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5734767025089605,
+  "best_metric": 1.3130438327789307,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1541218637992832,
   "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": 10.414,
       "eval_steps_per_second": 2.708,
       "step": 25
+    },
+    {
+      "epoch": 0.596415770609319,
+      "grad_norm": 58.53727722167969,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 46.5847,
+      "step": 26
+    },
+    {
+      "epoch": 0.6193548387096774,
+      "grad_norm": 55.56049346923828,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 45.1878,
+      "step": 27
+    },
+    {
+      "epoch": 0.6422939068100358,
+      "grad_norm": 63.621734619140625,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 46.4274,
+      "step": 28
+    },
+    {
+      "epoch": 0.6652329749103942,
+      "grad_norm": 61.650733947753906,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 42.2788,
+      "step": 29
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 59.424530029296875,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 42.7856,
+      "step": 30
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 65.62605285644531,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 45.3296,
+      "step": 31
+    },
+    {
+      "epoch": 0.7340501792114695,
+      "grad_norm": 62.037506103515625,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 38.7791,
+      "step": 32
+    },
+    {
+      "epoch": 0.7569892473118279,
+      "grad_norm": 54.389366149902344,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 43.6419,
+      "step": 33
+    },
+    {
+      "epoch": 0.7799283154121864,
+      "grad_norm": 48.2963981628418,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 47.0971,
+      "step": 34
+    },
+    {
+      "epoch": 0.8028673835125448,
+      "grad_norm": 47.147064208984375,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 43.7131,
+      "step": 35
+    },
+    {
+      "epoch": 0.8258064516129032,
+      "grad_norm": 49.53687286376953,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 44.4156,
+      "step": 36
+    },
+    {
+      "epoch": 0.8487455197132616,
+      "grad_norm": 47.156898498535156,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 39.8579,
+      "step": 37
+    },
+    {
+      "epoch": 0.8716845878136201,
+      "grad_norm": 49.07862854003906,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 42.7801,
+      "step": 38
+    },
+    {
+      "epoch": 0.8946236559139785,
+      "grad_norm": 54.775672912597656,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 43.8881,
+      "step": 39
+    },
+    {
+      "epoch": 0.9175627240143369,
+      "grad_norm": 53.687408447265625,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 40.9659,
+      "step": 40
+    },
+    {
+      "epoch": 0.9405017921146953,
+      "grad_norm": 62.848514556884766,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 42.5454,
+      "step": 41
+    },
+    {
+      "epoch": 0.9634408602150538,
+      "grad_norm": 62.29214096069336,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 39.6969,
+      "step": 42
+    },
+    {
+      "epoch": 0.9863799283154122,
+      "grad_norm": 70.89318084716797,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 40.2985,
+      "step": 43
+    },
+    {
+      "epoch": 1.0164874551971326,
+      "grad_norm": 46.05546188354492,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 40.5047,
+      "step": 44
+    },
+    {
+      "epoch": 1.039426523297491,
+      "grad_norm": 55.51439666748047,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 38.4444,
+      "step": 45
+    },
+    {
+      "epoch": 1.0623655913978494,
+      "grad_norm": 42.752933502197266,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 36.3928,
+      "step": 46
+    },
+    {
+      "epoch": 1.0853046594982079,
+      "grad_norm": 44.83907699584961,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 38.2118,
+      "step": 47
+    },
+    {
+      "epoch": 1.1082437275985664,
+      "grad_norm": 48.16358184814453,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 33.5141,
+      "step": 48
+    },
+    {
+      "epoch": 1.1311827956989247,
+      "grad_norm": 45.349609375,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 31.2986,
+      "step": 49
+    },
+    {
+      "epoch": 1.1541218637992832,
+      "grad_norm": 46.83755874633789,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 33.2819,
+      "step": 50
+    },
+    {
+      "epoch": 1.1541218637992832,
+      "eval_loss": 1.3130438327789307,
+      "eval_runtime": 4.775,
+      "eval_samples_per_second": 10.471,
+      "eval_steps_per_second": 2.723,
+      "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