Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9afec031ecb2d4cd3cff8e70435581a3484f1e07e22fc36acb505fa0900687
+oid sha256:f9569f95c283cb88cadaef15858e48d6531f52149c35abe3cae03a1bcfc4df90
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648d87e6800ccd74dae10655bb75a186b61bbac8f0e39492203d4f1eeb5ff40c
+oid sha256:1a5c6348fdb1aa07ffdf2fd06cd3129665c10c826acf0761155b2e2b8669eeca
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe21db14a8c718c82386d3d645a254635d7d96562d0fae30e641a2c338180ad
+oid sha256:ef3f1fe3a8fab33e10903a3ae9c4dbabbe797829d2383e56fc906f3b70b67482
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd1be78f9a07d2a6f51aa93a0afd384e88a0f69906ac6aff92c52a48783940a
+oid sha256:6c60c57087d6f9e2fc25bf89c86f813f34e957e68a7d4c364d174ea49cad09d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0674b59030f9636da4722bf4555d9b1d850a339498d56f852435ba17825fc05b
+oid sha256:b31aade6a3d6aa0334faf0f34d5bb90bf97c055df778b750eef2a15c83c7ced8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0883baed497b0c8200323fe979ba79c29d4f1ad32580ccf91827b6612dc377fa
+oid sha256:f44b16a19080a683a25ab6ce6cedeefc44b1dc48011226fabfb86bd8b66e6623
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.286402940750122,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11554015020219527,
+  "best_metric": 3.235640048980713,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.23108030040439054,
   "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": 14.274,
       "eval_steps_per_second": 3.711,
       "step": 25
+    },
+    {
+      "epoch": 0.12016175621028308,
+      "grad_norm": 0.938728928565979,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.0604,
+      "step": 26
+    },
+    {
+      "epoch": 0.12478336221837089,
+      "grad_norm": 0.9429075717926025,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.0813,
+      "step": 27
+    },
+    {
+      "epoch": 0.1294049682264587,
+      "grad_norm": 0.8533148169517517,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.1886,
+      "step": 28
+    },
+    {
+      "epoch": 0.1340265742345465,
+      "grad_norm": 0.9134799242019653,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.1899,
+      "step": 29
+    },
+    {
+      "epoch": 0.1386481802426343,
+      "grad_norm": 0.8826208114624023,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.1444,
+      "step": 30
+    },
+    {
+      "epoch": 0.14326978625072212,
+      "grad_norm": 0.9371979832649231,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.1263,
+      "step": 31
+    },
+    {
+      "epoch": 0.14789139225880993,
+      "grad_norm": 1.0243139266967773,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.1062,
+      "step": 32
+    },
+    {
+      "epoch": 0.15251299826689774,
+      "grad_norm": 1.1637766361236572,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.1219,
+      "step": 33
+    },
+    {
+      "epoch": 0.15713460427498555,
+      "grad_norm": 1.1408770084381104,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.143,
+      "step": 34
+    },
+    {
+      "epoch": 0.16175621028307338,
+      "grad_norm": 1.1354902982711792,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.064,
+      "step": 35
+    },
+    {
+      "epoch": 0.1663778162911612,
+      "grad_norm": 1.3348374366760254,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.1534,
+      "step": 36
+    },
+    {
+      "epoch": 0.170999422299249,
+      "grad_norm": 1.4398350715637207,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.258,
+      "step": 37
+    },
+    {
+      "epoch": 0.1756210283073368,
+      "grad_norm": 0.8603622317314148,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.1599,
+      "step": 38
+    },
+    {
+      "epoch": 0.18024263431542462,
+      "grad_norm": 0.8389877080917358,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.1301,
+      "step": 39
+    },
+    {
+      "epoch": 0.18486424032351242,
+      "grad_norm": 0.8191156387329102,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.173,
+      "step": 40
+    },
+    {
+      "epoch": 0.18948584633160023,
+      "grad_norm": 0.8949576020240784,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.1418,
+      "step": 41
+    },
+    {
+      "epoch": 0.19410745233968804,
+      "grad_norm": 0.8386082053184509,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.1326,
+      "step": 42
+    },
+    {
+      "epoch": 0.19872905834777585,
+      "grad_norm": 0.9333357810974121,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.0901,
+      "step": 43
+    },
+    {
+      "epoch": 0.20335066435586366,
+      "grad_norm": 1.0320864915847778,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.2603,
+      "step": 44
+    },
+    {
+      "epoch": 0.20797227036395147,
+      "grad_norm": 1.0339475870132446,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.0254,
+      "step": 45
+    },
+    {
+      "epoch": 0.21259387637203928,
+      "grad_norm": 0.9975182414054871,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.0393,
+      "step": 46
+    },
+    {
+      "epoch": 0.21721548238012708,
+      "grad_norm": 1.1470623016357422,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.0811,
+      "step": 47
+    },
+    {
+      "epoch": 0.2218370883882149,
+      "grad_norm": 1.1090809106826782,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.1109,
+      "step": 48
+    },
+    {
+      "epoch": 0.22645869439630273,
+      "grad_norm": 1.3140599727630615,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.1859,
+      "step": 49
+    },
+    {
+      "epoch": 0.23108030040439054,
+      "grad_norm": 1.4181642532348633,
+      "learning_rate": 1e-05,
+      "loss": 3.1877,
+      "step": 50
+    },
+    {
+      "epoch": 0.23108030040439054,
+      "eval_loss": 3.235640048980713,
+      "eval_runtime": 3.4891,
+      "eval_samples_per_second": 14.33,
+      "eval_steps_per_second": 3.726,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null