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:a85a2035c9f0e0ac3f92fab6d2f0d5acb3f5da3a748fe71cd630505ff7d23e27
+oid sha256:f4575680cf8bf491633fdfe8203dfef58f7764b7240fd0a51dd09bf20bb83325
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a867cc1b23074bf965fd809b1d789f88e1d4ad87239c75eba6aea83fe038e110
+oid sha256:77bbbd80e4f8882fbe09be5b754c26938ed9b91633c15f3a7a5ed1850b574887
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f25a1099ec8b720c5b57340ea27b2f9805c54a156eb5d2a0b35a7e429573e8
+oid sha256:1f14a6088ce605a3f86cb835e52b5aef084b0349efbafbbcdaac4cf662b549b3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8857fa8fb095afc59b4b5f5d3c291cb549707cfe8e57be94bc8a0ed7cfc14b
+oid sha256:4e0ca59f6e6295071ac9690c710e3cdba0eeb34eef4c3225d2a26ea9d2d401b7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4933fe021cffb15af2d228651f400682210f4d6eaa874076acd73313cf83c6b
+oid sha256:5698be97b428cd86b64cb212e4957a78127218e4a13f991c263c8dce35e170d5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd39e5578725a7ea5c69fce57fa26854ca7588fb713388768e2e6c4f23e0d3b7
+oid sha256:d47d386e5e40ff73e89cf622ca072b0c95826fe6ea8643bab97dc18950d1751e
 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": 0.9022783637046814,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.23446658851113716,
+  "best_metric": 0.864888072013855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.46893317702227433,
   "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": 33.025,
       "eval_steps_per_second": 4.14,
       "step": 25
+    },
+    {
+      "epoch": 0.24384525205158264,
+      "grad_norm": 1.026550531387329,
+      "learning_rate": 5e-05,
+      "loss": 1.0879,
+      "step": 26
+    },
+    {
+      "epoch": 0.2532239155920281,
+      "grad_norm": 1.003537893295288,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0284,
+      "step": 27
+    },
+    {
+      "epoch": 0.26260257913247365,
+      "grad_norm": 0.7942367792129517,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9807,
+      "step": 28
+    },
+    {
+      "epoch": 0.2719812426729191,
+      "grad_norm": 0.5820752382278442,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9545,
+      "step": 29
+    },
+    {
+      "epoch": 0.2813599062133646,
+      "grad_norm": 0.45629891753196716,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8808,
+      "step": 30
+    },
+    {
+      "epoch": 0.29073856975381007,
+      "grad_norm": 0.6787412762641907,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9189,
+      "step": 31
+    },
+    {
+      "epoch": 0.30011723329425555,
+      "grad_norm": 0.7377832531929016,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8183,
+      "step": 32
+    },
+    {
+      "epoch": 0.3094958968347011,
+      "grad_norm": 0.7037996649742126,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8804,
+      "step": 33
+    },
+    {
+      "epoch": 0.31887456037514655,
+      "grad_norm": 0.6749622225761414,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7713,
+      "step": 34
+    },
+    {
+      "epoch": 0.32825322391559203,
+      "grad_norm": 0.6450227499008179,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8081,
+      "step": 35
+    },
+    {
+      "epoch": 0.3376318874560375,
+      "grad_norm": 0.6441214084625244,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8022,
+      "step": 36
+    },
+    {
+      "epoch": 0.347010550996483,
+      "grad_norm": 0.6708666086196899,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7003,
+      "step": 37
+    },
+    {
+      "epoch": 0.3563892145369285,
+      "grad_norm": 0.6430343389511108,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0176,
+      "step": 38
+    },
+    {
+      "epoch": 0.365767878077374,
+      "grad_norm": 0.7903113961219788,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.986,
+      "step": 39
+    },
+    {
+      "epoch": 0.37514654161781946,
+      "grad_norm": 0.7977195382118225,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9674,
+      "step": 40
+    },
+    {
+      "epoch": 0.38452520515826494,
+      "grad_norm": 0.7614197134971619,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9324,
+      "step": 41
+    },
+    {
+      "epoch": 0.3939038686987104,
+      "grad_norm": 0.708970844745636,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9519,
+      "step": 42
+    },
+    {
+      "epoch": 0.40328253223915594,
+      "grad_norm": 0.5555177927017212,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9016,
+      "step": 43
+    },
+    {
+      "epoch": 0.4126611957796014,
+      "grad_norm": 0.5195717215538025,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8353,
+      "step": 44
+    },
+    {
+      "epoch": 0.4220398593200469,
+      "grad_norm": 0.5150408148765564,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8043,
+      "step": 45
+    },
+    {
+      "epoch": 0.43141852286049237,
+      "grad_norm": 0.4650251269340515,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.771,
+      "step": 46
+    },
+    {
+      "epoch": 0.44079718640093785,
+      "grad_norm": 0.48360204696655273,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7692,
+      "step": 47
+    },
+    {
+      "epoch": 0.4501758499413834,
+      "grad_norm": 0.5229669809341431,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8185,
+      "step": 48
+    },
+    {
+      "epoch": 0.45955451348182885,
+      "grad_norm": 0.5888627171516418,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7044,
+      "step": 49
+    },
+    {
+      "epoch": 0.46893317702227433,
+      "grad_norm": 0.861103355884552,
+      "learning_rate": 0.0,
+      "loss": 0.7366,
+      "step": 50
+    },
+    {
+      "epoch": 0.46893317702227433,
+      "eval_loss": 0.864888072013855,
+      "eval_runtime": 21.7296,
+      "eval_samples_per_second": 33.042,
+      "eval_steps_per_second": 4.142,
+      "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