Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871be95bf71db9138b7e097d40f79e5c8523de983f8f0ba61f3c8c25b9938c9d
+oid sha256:019e18add6ab50033a92825df292bfb8941dc2c843e2ac22c9a4f1ba55c4482d
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b4296140da1d4f845b19ad6ff6d86103b7b18e0e3c8d8f388686bf3c8073630
+oid sha256:e5677fa6aa787c6498da3db391b4f71b60cc9216406a245d152ee858eb92498f
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4804cf6371185859667fb5b0fa4d43a9812a9bd3ab8b634638133d18aa929836
+oid sha256:dc29e05449f31d2e94394fe59c01418c1e6241105ae91a574118848146584415
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3671b4d31690114bcb2d3d21e46ebb94897ddd1b52e483e18e8d3e5027e39585
+oid sha256:0b697b807dd856c5585e6f159ccc2fe3304e089d2f6a459585cd4bb7d8fc8c45
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a509c06aa9aa8994390b832621ef1df7afbbe1ea85af2cb9d738b26a4ac119
+oid sha256:37348e8f1362242ee92b948ae1f313a93d616b75b1564899f7d36babda63ac7a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3def97aa272b8007a3a152648b9f21f696b29a91fabb8b7041dec4a935a84d
+oid sha256:90956b7fee71f0ca23ef07e1ec38592ba5c343271f722210bb44be50c5179e66
 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": 2.653991460800171,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7714561234329798,
+  "best_metric": 2.457026958465576,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5429122468659595,
   "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": 48.978,
       "eval_steps_per_second": 12.734,
       "step": 25
+    },
+    {
+      "epoch": 0.8023143683702989,
+      "grad_norm": 0.6692939400672913,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 2.6014,
+      "step": 26
+    },
+    {
+      "epoch": 0.8331726133076182,
+      "grad_norm": 0.6837179660797119,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 2.614,
+      "step": 27
+    },
+    {
+      "epoch": 0.8640308582449373,
+      "grad_norm": 0.7611942291259766,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 2.6286,
+      "step": 28
+    },
+    {
+      "epoch": 0.8948891031822566,
+      "grad_norm": 0.8610087633132935,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 2.7091,
+      "step": 29
+    },
+    {
+      "epoch": 0.9257473481195757,
+      "grad_norm": 0.9536398649215698,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 2.6736,
+      "step": 30
+    },
+    {
+      "epoch": 0.9566055930568949,
+      "grad_norm": 1.5485323667526245,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 2.7427,
+      "step": 31
+    },
+    {
+      "epoch": 0.9874638379942141,
+      "grad_norm": 2.791057586669922,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 2.9027,
+      "step": 32
+    },
+    {
+      "epoch": 1.0183220829315334,
+      "grad_norm": 1.133805274963379,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 4.2342,
+      "step": 33
+    },
+    {
+      "epoch": 1.0491803278688525,
+      "grad_norm": 0.5696182250976562,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 2.4703,
+      "step": 34
+    },
+    {
+      "epoch": 1.0800385728061717,
+      "grad_norm": 0.7950026988983154,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 2.5597,
+      "step": 35
+    },
+    {
+      "epoch": 1.1108968177434908,
+      "grad_norm": 0.8173376321792603,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 2.6145,
+      "step": 36
+    },
+    {
+      "epoch": 1.14175506268081,
+      "grad_norm": 0.7578170895576477,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 2.4873,
+      "step": 37
+    },
+    {
+      "epoch": 1.1726133076181293,
+      "grad_norm": 0.9220737814903259,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 2.6142,
+      "step": 38
+    },
+    {
+      "epoch": 1.2034715525554485,
+      "grad_norm": 1.000977635383606,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 2.7668,
+      "step": 39
+    },
+    {
+      "epoch": 1.2343297974927676,
+      "grad_norm": 1.9137243032455444,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 2.6618,
+      "step": 40
+    },
+    {
+      "epoch": 1.2651880424300868,
+      "grad_norm": 1.144348382949829,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 2.2853,
+      "step": 41
+    },
+    {
+      "epoch": 1.296046287367406,
+      "grad_norm": 0.494349867105484,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 2.4441,
+      "step": 42
+    },
+    {
+      "epoch": 1.326904532304725,
+      "grad_norm": 0.6220836639404297,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 2.4758,
+      "step": 43
+    },
+    {
+      "epoch": 1.3577627772420444,
+      "grad_norm": 0.6606362462043762,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 2.5194,
+      "step": 44
+    },
+    {
+      "epoch": 1.3886210221793636,
+      "grad_norm": 0.7131364345550537,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 2.4692,
+      "step": 45
+    },
+    {
+      "epoch": 1.4194792671166827,
+      "grad_norm": 0.7623465061187744,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 2.4903,
+      "step": 46
+    },
+    {
+      "epoch": 1.4503375120540019,
+      "grad_norm": 0.8568875193595886,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 2.6904,
+      "step": 47
+    },
+    {
+      "epoch": 1.4811957569913212,
+      "grad_norm": 1.716271162033081,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 2.6191,
+      "step": 48
+    },
+    {
+      "epoch": 1.5120540019286404,
+      "grad_norm": 1.0471079349517822,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.2445,
+      "step": 49
+    },
+    {
+      "epoch": 1.5429122468659595,
+      "grad_norm": 0.5166476368904114,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 2.3682,
+      "step": 50
+    },
+    {
+      "epoch": 1.5429122468659595,
+      "eval_loss": 2.457026958465576,
+      "eval_runtime": 1.0293,
+      "eval_samples_per_second": 48.575,
+      "eval_steps_per_second": 12.63,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.169686374888243e+16,
+  "total_flos": 8.34067497043886e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null