Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b2f9538337d88a2a4a9817a47b6f6dc291bee48cff846a2c5d4b847eef0192
+oid sha256:c36df7dd85061247d5e9909908485f9ceaae1ff4ab10621f8a890dac8e24b5ac
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccb0346e1dbe27eb8c116f8ef7c1108ead80ed53fd2d8aa2b7df3bc160e6af7
+oid sha256:01d9b210439d26cc5bd0f2e4ea45248369e6f12a59e1fcc5c46b966f6a699e8d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0a1cb4f72880b58cfaef917d7af16ec3cbfb1f71f438d146f4a96a09c4d3b0
+oid sha256:cc9c237dc59463ce347deb392fc980bb39de42700fd34a6a1a362ab0aeb59e34
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbcb5542a8db7d89b5054c18465cfe35e6b04ec5df6d082053b3ae40b7b07cc
+oid sha256:0317c1f24d73ba6c9bf975b3d32d8ef526c85518352b775a42e1140d6daf94d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9813fdff6bd4e89e9ef4c6e396ed54d841cdee813d5ad5670c7d13fa966a8d7
+oid sha256:117a910d7e690634a0cb495caaf662610f34ecda01b1a6c2c176e633e5deacd1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0395278ff26051eb4501cfae4fe70eb23ed43cf06f9a3eec0aa1b5bafc1db68
+oid sha256:28335b670d46de1e439728d4356b5221c43f44dc5d89cf9750e38f0c1fec616c
 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": 1.6741125583648682,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07087172218284904,
+  "best_metric": 1.628139853477478,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.14174344436569808,
   "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": 14.852,
       "eval_steps_per_second": 1.862,
       "step": 25
+    },
+    {
+      "epoch": 0.073706591070163,
+      "grad_norm": 22.807870864868164,
+      "learning_rate": 5e-05,
+      "loss": 1.816,
+      "step": 26
+    },
+    {
+      "epoch": 0.07654145995747696,
+      "grad_norm": 23.065021514892578,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7547,
+      "step": 27
+    },
+    {
+      "epoch": 0.07937632884479093,
+      "grad_norm": 22.509727478027344,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7348,
+      "step": 28
+    },
+    {
+      "epoch": 0.08221119773210489,
+      "grad_norm": 24.79450798034668,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7789,
+      "step": 29
+    },
+    {
+      "epoch": 0.08504606661941885,
+      "grad_norm": 20.922771453857422,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6747,
+      "step": 30
+    },
+    {
+      "epoch": 0.08788093550673282,
+      "grad_norm": 21.161157608032227,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7365,
+      "step": 31
+    },
+    {
+      "epoch": 0.09071580439404678,
+      "grad_norm": 21.79657554626465,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6723,
+      "step": 32
+    },
+    {
+      "epoch": 0.09355067328136074,
+      "grad_norm": 21.640913009643555,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.6482,
+      "step": 33
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 22.724075317382812,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.633,
+      "step": 34
+    },
+    {
+      "epoch": 0.09922041105598867,
+      "grad_norm": 22.851327896118164,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5125,
+      "step": 35
+    },
+    {
+      "epoch": 0.10205527994330262,
+      "grad_norm": 22.460840225219727,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5215,
+      "step": 36
+    },
+    {
+      "epoch": 0.10489014883061658,
+      "grad_norm": 25.073806762695312,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5259,
+      "step": 37
+    },
+    {
+      "epoch": 0.10772501771793054,
+      "grad_norm": 22.24521827697754,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6251,
+      "step": 38
+    },
+    {
+      "epoch": 0.1105598866052445,
+      "grad_norm": 23.253215789794922,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8014,
+      "step": 39
+    },
+    {
+      "epoch": 0.11339475549255847,
+      "grad_norm": 20.70416831970215,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6772,
+      "step": 40
+    },
+    {
+      "epoch": 0.11622962437987243,
+      "grad_norm": 22.59032440185547,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.691,
+      "step": 41
+    },
+    {
+      "epoch": 0.11906449326718639,
+      "grad_norm": 20.377567291259766,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6388,
+      "step": 42
+    },
+    {
+      "epoch": 0.12189936215450035,
+      "grad_norm": 20.455690383911133,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.7373,
+      "step": 43
+    },
+    {
+      "epoch": 0.12473423104181432,
+      "grad_norm": 21.72209930419922,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6149,
+      "step": 44
+    },
+    {
+      "epoch": 0.12756909992912827,
+      "grad_norm": 22.001754760742188,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5773,
+      "step": 45
+    },
+    {
+      "epoch": 0.13040396881644223,
+      "grad_norm": 22.714204788208008,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5676,
+      "step": 46
+    },
+    {
+      "epoch": 0.1332388377037562,
+      "grad_norm": 22.13160514831543,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5942,
+      "step": 47
+    },
+    {
+      "epoch": 0.13607370659107015,
+      "grad_norm": 22.511978149414062,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5405,
+      "step": 48
+    },
+    {
+      "epoch": 0.13890857547838412,
+      "grad_norm": 22.759485244750977,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.504,
+      "step": 49
+    },
+    {
+      "epoch": 0.14174344436569808,
+      "grad_norm": 26.86092185974121,
+      "learning_rate": 0.0,
+      "loss": 1.4866,
+      "step": 50
+    },
+    {
+      "epoch": 0.14174344436569808,
+      "eval_loss": 1.628139853477478,
+      "eval_runtime": 160.6454,
+      "eval_samples_per_second": 14.797,
+      "eval_steps_per_second": 1.855,
+      "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": 2.839622685074391e+17,
+  "total_flos": 5.6721728367650406e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null