Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793dfc603f2c7a7c15dcdf4bb51da84a72125a8219b19ce1cbd254729d64737e
+oid sha256:5b9e6029b8e20ffea46f0a63f305f8a19b4b8d4c222505c00dd1756a2c05e327
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856e7d4eb9bd346bf124dff87a8946f1671a604bfd7531d553ff39abb77add29
+oid sha256:c5ac99cd1c2daa03a4004e768b1475426edc7b4b4d2c5f4eaebb8ae60fbdc45c
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c54bf62083df637d1530b0f4e42da7a5383f1440dcf59914ac070a0cc961306
+oid sha256:9cd119cfb8d5f79126ee024c0402e15266cdde51590656c9bfff6d4c1906f5f2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b3ae6d3c75fc9a883598570634d2d02e94adb288116ee96016d8e66593f33c
+oid sha256:bcdfaa06a050154a02b7db40937ce5ed5fadd7e1cdcda101cef6fda76cd4aa3b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4e985a3b2ce7e77c43587f7b4ad3d34862356bce8859e611d669cac953ad1a
+oid sha256:f1dce42a6c12395909ff288b85ec6528b48ce766f999f9454df6e9b03a18ef1d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2338ab34fe89067e42575e3154cbe5a7bc3334783ac35e5c51d9e7df9a240fec
+oid sha256:05d6bba347f596d22ebf95e8935e06faf3787342cd6c72879bba6c7d46f04e1a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.8887457847595215,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.024680693527488123,
+  "best_metric": 6.879824638366699,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.03702104029123218,
   "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": 586.013,
       "eval_steps_per_second": 152.363,
       "step": 50
+    },
+    {
+      "epoch": 0.025174307398037884,
+      "grad_norm": 0.1739850789308548,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 6.8971,
+      "step": 51
+    },
+    {
+      "epoch": 0.02566792126858765,
+      "grad_norm": 0.1729678362607956,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 6.8957,
+      "step": 52
+    },
+    {
+      "epoch": 0.02616153513913741,
+      "grad_norm": 0.178720623254776,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 6.8935,
+      "step": 53
+    },
+    {
+      "epoch": 0.02665514900968717,
+      "grad_norm": 0.1674613654613495,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 6.8948,
+      "step": 54
+    },
+    {
+      "epoch": 0.027148762880236935,
+      "grad_norm": 0.15328410267829895,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 6.8912,
+      "step": 55
+    },
+    {
+      "epoch": 0.027642376750786696,
+      "grad_norm": 0.16422665119171143,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 6.8897,
+      "step": 56
+    },
+    {
+      "epoch": 0.02813599062133646,
+      "grad_norm": 0.1450253576040268,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 6.8908,
+      "step": 57
+    },
+    {
+      "epoch": 0.028629604491886222,
+      "grad_norm": 0.15350405871868134,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 6.8917,
+      "step": 58
+    },
+    {
+      "epoch": 0.029123218362435983,
+      "grad_norm": 0.16251219809055328,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 6.8909,
+      "step": 59
+    },
+    {
+      "epoch": 0.029616832232985748,
+      "grad_norm": 0.1406952440738678,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 6.8922,
+      "step": 60
+    },
+    {
+      "epoch": 0.03011044610353551,
+      "grad_norm": 0.15078043937683105,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 6.8862,
+      "step": 61
+    },
+    {
+      "epoch": 0.03060405997408527,
+      "grad_norm": 0.15306660532951355,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 6.8878,
+      "step": 62
+    },
+    {
+      "epoch": 0.031097673844635035,
+      "grad_norm": 0.14538978040218353,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 6.8888,
+      "step": 63
+    },
+    {
+      "epoch": 0.031591287715184796,
+      "grad_norm": 0.1452692747116089,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 6.8895,
+      "step": 64
+    },
+    {
+      "epoch": 0.03208490158573456,
+      "grad_norm": 0.14324979484081268,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 6.8897,
+      "step": 65
+    },
+    {
+      "epoch": 0.03257851545628432,
+      "grad_norm": 0.1350090503692627,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 6.8859,
+      "step": 66
+    },
+    {
+      "epoch": 0.033072129326834086,
+      "grad_norm": 0.12386202067136765,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 6.8881,
+      "step": 67
+    },
+    {
+      "epoch": 0.03356574319738385,
+      "grad_norm": 0.12516862154006958,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 6.8903,
+      "step": 68
+    },
+    {
+      "epoch": 0.03405935706793361,
+      "grad_norm": 0.1329328715801239,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 6.888,
+      "step": 69
+    },
+    {
+      "epoch": 0.03455297093848337,
+      "grad_norm": 0.12640073895454407,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 6.8854,
+      "step": 70
+    },
+    {
+      "epoch": 0.03504658480903313,
+      "grad_norm": 0.13168954849243164,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 6.8887,
+      "step": 71
+    },
+    {
+      "epoch": 0.0355401986795829,
+      "grad_norm": 0.13239482045173645,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.8874,
+      "step": 72
+    },
+    {
+      "epoch": 0.03603381255013266,
+      "grad_norm": 0.11545424908399582,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 6.8883,
+      "step": 73
+    },
+    {
+      "epoch": 0.03652742642068242,
+      "grad_norm": 0.12295694649219513,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 6.8867,
+      "step": 74
+    },
+    {
+      "epoch": 0.03702104029123218,
+      "grad_norm": 0.13138267397880554,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 6.885,
+      "step": 75
+    },
+    {
+      "epoch": 0.03702104029123218,
+      "eval_loss": 6.879824638366699,
+      "eval_runtime": 0.0753,
+      "eval_samples_per_second": 663.996,
+      "eval_steps_per_second": 172.639,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5705957376000.0,
+  "total_flos": 8558936064000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null