Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c67860dcaf2439298cef812980e3615cff5ad811bcbe60f99392c82dbb61cc
+oid sha256:1fd6bd14a4bd9aeb65b8c0cfc08a0bc062e480a7319bbbb02bff3df224c7b796
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6e0805b22483819234d1b02957e1b6607a686bf2862c09bacfa39c79e13254
+oid sha256:55335180b41dba9386f509f6a6652bdfb710eb655457d6f1587f51f075477022
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95a5e35abafb5c516a93cb28230e3c9e20c424b7736e18f552f268b6a3cc791
+oid sha256:fba41c83797779d13308b6490e3948112be5cc81ad2e4ad3102f676415c8ac22
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f387b0a7a59a1a9d465d741521363ce3d089d89c22e19a8a2d64e716488f5d
+oid sha256:e6f284accce65d2ede65b0bb66f4935f6d266e142f2dbafafdf8e291dc52e6ef
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f893fc5d34910020eeb8f28c154b90d418bcc8fd5e622c36e39205c232eca08
+oid sha256:04073f63101cc92cdf747d9546f6ab9d7e9f2de0add0393843e4344e2287bc45
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738af7d9c836dd428287a21bafed4625fe02f726aae0703006caf4cbfe1ba76f
+oid sha256:3d5cbe6c848f023bf0a2ea634e1f40a56528e5919d5e670c1c186358d693d28e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6227145195007324,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3510311540149188,
+  "best_metric": 2.51250958442688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7020623080298376,
   "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": 99.066,
       "eval_steps_per_second": 25.757,
       "step": 25
+    },
+    {
+      "epoch": 0.36507240017551557,
+      "grad_norm": 0.5822151303291321,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 2.2137,
+      "step": 26
+    },
+    {
+      "epoch": 0.37911364633611233,
+      "grad_norm": 0.612755298614502,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 1.8046,
+      "step": 27
+    },
+    {
+      "epoch": 0.3931548924967091,
+      "grad_norm": 0.6512185335159302,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 2.0374,
+      "step": 28
+    },
+    {
+      "epoch": 0.40719613865730586,
+      "grad_norm": 0.9296779036521912,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 2.2375,
+      "step": 29
+    },
+    {
+      "epoch": 0.42123738481790257,
+      "grad_norm": 1.1704964637756348,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 2.4913,
+      "step": 30
+    },
+    {
+      "epoch": 0.43527863097849934,
+      "grad_norm": 1.2606786489486694,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 2.6343,
+      "step": 31
+    },
+    {
+      "epoch": 0.4493198771390961,
+      "grad_norm": 1.8587498664855957,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 3.0057,
+      "step": 32
+    },
+    {
+      "epoch": 0.46336112329969287,
+      "grad_norm": 1.7915164232254028,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 3.0309,
+      "step": 33
+    },
+    {
+      "epoch": 0.4774023694602896,
+      "grad_norm": 2.1659657955169678,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 3.1982,
+      "step": 34
+    },
+    {
+      "epoch": 0.49144361562088634,
+      "grad_norm": 2.6619133949279785,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 3.3039,
+      "step": 35
+    },
+    {
+      "epoch": 0.5054848617814831,
+      "grad_norm": 3.697298288345337,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 3.6746,
+      "step": 36
+    },
+    {
+      "epoch": 0.5195261079420799,
+      "grad_norm": 5.550060749053955,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 3.8725,
+      "step": 37
+    },
+    {
+      "epoch": 0.5335673541026766,
+      "grad_norm": 0.6753820180892944,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 2.2385,
+      "step": 38
+    },
+    {
+      "epoch": 0.5476086002632734,
+      "grad_norm": 1.0300302505493164,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 1.7155,
+      "step": 39
+    },
+    {
+      "epoch": 0.5616498464238702,
+      "grad_norm": 1.5170297622680664,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 1.858,
+      "step": 40
+    },
+    {
+      "epoch": 0.5756910925844668,
+      "grad_norm": 2.700623035430908,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 2.2176,
+      "step": 41
+    },
+    {
+      "epoch": 0.5897323387450636,
+      "grad_norm": 3.4165198802948,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 2.4351,
+      "step": 42
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 2.0354185104370117,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 2.4769,
+      "step": 43
+    },
+    {
+      "epoch": 0.6178148310662571,
+      "grad_norm": 1.5906285047531128,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 2.8552,
+      "step": 44
+    },
+    {
+      "epoch": 0.6318560772268539,
+      "grad_norm": 1.8608163595199585,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 2.8639,
+      "step": 45
+    },
+    {
+      "epoch": 0.6458973233874507,
+      "grad_norm": 2.8141560554504395,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 2.8932,
+      "step": 46
+    },
+    {
+      "epoch": 0.6599385695480474,
+      "grad_norm": 4.370851993560791,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 3.1846,
+      "step": 47
+    },
+    {
+      "epoch": 0.6739798157086442,
+      "grad_norm": 4.608976364135742,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 3.3674,
+      "step": 48
+    },
+    {
+      "epoch": 0.688021061869241,
+      "grad_norm": 6.83935022354126,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 3.7393,
+      "step": 49
+    },
+    {
+      "epoch": 0.7020623080298376,
+      "grad_norm": 11.380165100097656,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 4.2031,
+      "step": 50
+    },
+    {
+      "epoch": 0.7020623080298376,
+      "eval_loss": 2.51250958442688,
+      "eval_runtime": 0.5058,
+      "eval_samples_per_second": 98.857,
+      "eval_steps_per_second": 25.703,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null