Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d53823117a4ed9e29f0a710ecce9a86d8dd9d43be85df5a45614e3cd8720988
+oid sha256:99670247ba5a07b728aa647cbde30a7a795a902176113be28c79c1860a6dfc3f
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed23fdaca0505dee8e073ad52f8548134e4926bb1e4cda921947b6cb2b1956e
+oid sha256:037b0d461d2fcc4a85ec0d43f465f3d62798a5a75138be5ef7d0ef44c101f44d
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb1d8a186d0e74fb305cc24e4875577624a35b4b63ddc6d4cae13b9fbf5dc96
+oid sha256:72af02c3b5e032df2a59c21c10a70b7ea0c4bb4945e037943c58a55fc7ee255f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b120089db0ebb77b040dbec6a471710c823aee73cbc718864dc8d58c7bfc8bd3
+oid sha256:bd459c83a1f2dd27fd118e99bbfb870f56e06d9e7c29c12daf786ebfea487878
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7c3cbe8ce876e9242bc853c38af79b528adc0bc2eaba22b3a4c33fe10a5ad9
+oid sha256:6c24c468de2af80ffb22d2dfca31b323c696f877f38198ca5d57527ec7627599
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce524b8f70c8ed06de19b4e94695b468be82583745cfd15750507f8c1ab675a0
+oid sha256:2b5e22de549666905732d4ad59ea76015e6ce616b13635a23c9734b34c9016c1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2820234298706055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0067409292370953335,
+  "best_metric": 1.241644024848938,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013481858474190667,
   "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": 147.969,
       "eval_steps_per_second": 18.501,
       "step": 25
+    },
+    {
+      "epoch": 0.007010566406579147,
+      "grad_norm": 0.6564807295799255,
+      "learning_rate": 5e-05,
+      "loss": 2.8087,
+      "step": 26
+    },
+    {
+      "epoch": 0.00728020357606296,
+      "grad_norm": 1.2318458557128906,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0502,
+      "step": 27
+    },
+    {
+      "epoch": 0.007549840745546774,
+      "grad_norm": 1.1607344150543213,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6962,
+      "step": 28
+    },
+    {
+      "epoch": 0.007819477915030588,
+      "grad_norm": 1.0790623426437378,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2812,
+      "step": 29
+    },
+    {
+      "epoch": 0.0080891150845144,
+      "grad_norm": 1.0593982934951782,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1717,
+      "step": 30
+    },
+    {
+      "epoch": 0.008358752253998214,
+      "grad_norm": 0.8499507308006287,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2295,
+      "step": 31
+    },
+    {
+      "epoch": 0.008628389423482027,
+      "grad_norm": 0.8501824140548706,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0183,
+      "step": 32
+    },
+    {
+      "epoch": 0.00889802659296584,
+      "grad_norm": 0.820349931716919,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9825,
+      "step": 33
+    },
+    {
+      "epoch": 0.009167663762449653,
+      "grad_norm": 0.7182340025901794,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9338,
+      "step": 34
+    },
+    {
+      "epoch": 0.009437300931933467,
+      "grad_norm": 0.6811063289642334,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7924,
+      "step": 35
+    },
+    {
+      "epoch": 0.00970693810141728,
+      "grad_norm": 0.6988488435745239,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7534,
+      "step": 36
+    },
+    {
+      "epoch": 0.009976575270901093,
+      "grad_norm": 1.3896055221557617,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0053,
+      "step": 37
+    },
+    {
+      "epoch": 0.010246212440384907,
+      "grad_norm": 0.5736123323440552,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6986,
+      "step": 38
+    },
+    {
+      "epoch": 0.01051584960986872,
+      "grad_norm": 0.78612220287323,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.3167,
+      "step": 39
+    },
+    {
+      "epoch": 0.010785486779352534,
+      "grad_norm": 0.8870537281036377,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9921,
+      "step": 40
+    },
+    {
+      "epoch": 0.011055123948836346,
+      "grad_norm": 0.796861469745636,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4515,
+      "step": 41
+    },
+    {
+      "epoch": 0.01132476111832016,
+      "grad_norm": 0.8636763095855713,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.069,
+      "step": 42
+    },
+    {
+      "epoch": 0.011594398287803974,
+      "grad_norm": 0.6601255536079407,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1136,
+      "step": 43
+    },
+    {
+      "epoch": 0.011864035457287788,
+      "grad_norm": 0.6353766918182373,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0235,
+      "step": 44
+    },
+    {
+      "epoch": 0.0121336726267716,
+      "grad_norm": 0.42836466431617737,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9278,
+      "step": 45
+    },
+    {
+      "epoch": 0.012403309796255414,
+      "grad_norm": 0.4276427924633026,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8962,
+      "step": 46
+    },
+    {
+      "epoch": 0.012672946965739227,
+      "grad_norm": 0.4567084312438965,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9417,
+      "step": 47
+    },
+    {
+      "epoch": 0.012942584135223041,
+      "grad_norm": 0.4835442304611206,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8229,
+      "step": 48
+    },
+    {
+      "epoch": 0.013212221304706853,
+      "grad_norm": 0.6143326759338379,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9012,
+      "step": 49
+    },
+    {
+      "epoch": 0.013481858474190667,
+      "grad_norm": 1.483192801475525,
+      "learning_rate": 0.0,
+      "loss": 0.9693,
+      "step": 50
+    },
+    {
+      "epoch": 0.013481858474190667,
+      "eval_loss": 1.241644024848938,
+      "eval_runtime": 168.8547,
+      "eval_samples_per_second": 147.967,
+      "eval_steps_per_second": 18.501,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null