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:c581700fa4ab55ebe308dfe4dcc58aa6135eeff6f5af953c8ab419a54046e32c
+oid sha256:2c80f27fffdf1a286fcb5a7ff8e8dae95fe6316c7500502da1bb7998928cdebf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac96cab380816a824dcdd451c81442f2915fd21d16bcd637c108250452e9a709
+oid sha256:ceb63af7201e9c1d866770a3f1f234a28d1cbc89267785cd6eb0f223865478a2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6811746453bdcacf3fd1f290c6a5a694ed03b2afb23349a83dc7a1d3c312e45
+oid sha256:a75dd38dce9ac015ed3e13399b5f587fc884bce6328b4e3a18efd97a18c31e34
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c07f5a1f1ff72bd3e5fd29b5573b56bd4aed6adf49e3c3d80fccaa15928314
+oid sha256:69c1f5f66610209ca4d39f6e0d0a1538dde7b295ddab6645b5878d5c8a3d1a9b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fbad34681c18e0c3fcfee2d574babbad5d3714005bdd01005229c370c8a25c
+oid sha256:fcb009d0d05c2e1062751d2665a6954da1be99546a1e8b844f7d85d35c3fa8ac
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe221a01b00e31e142d4c7cf08cf2bac5ee75ea59b4def120a7c79826104e46
+oid sha256:873abf8482fc9f9717e76712adc933b1a0c6638715cd8c0f2bb5ff2d1d7a4cb6
 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": 0.555499255657196,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004427423460916919,
+  "best_metric": 0.4569474458694458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.008854846921833838,
   "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": 24.29,
       "eval_steps_per_second": 3.037,
       "step": 25
+    },
+    {
+      "epoch": 0.004604520399353596,
+      "grad_norm": 37.32914352416992,
+      "learning_rate": 5e-05,
+      "loss": 0.6278,
+      "step": 26
+    },
+    {
+      "epoch": 0.004781617337790273,
+      "grad_norm": 30.841808319091797,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.526,
+      "step": 27
+    },
+    {
+      "epoch": 0.00495871427622695,
+      "grad_norm": 26.814208984375,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5521,
+      "step": 28
+    },
+    {
+      "epoch": 0.005135811214663627,
+      "grad_norm": 22.27334976196289,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5206,
+      "step": 29
+    },
+    {
+      "epoch": 0.005312908153100303,
+      "grad_norm": 18.109580993652344,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4236,
+      "step": 30
+    },
+    {
+      "epoch": 0.00549000509153698,
+      "grad_norm": 21.037906646728516,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4845,
+      "step": 31
+    },
+    {
+      "epoch": 0.005667102029973657,
+      "grad_norm": 21.314884185791016,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4973,
+      "step": 32
+    },
+    {
+      "epoch": 0.005844198968410334,
+      "grad_norm": 23.060914993286133,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.503,
+      "step": 33
+    },
+    {
+      "epoch": 0.00602129590684701,
+      "grad_norm": 21.678466796875,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5009,
+      "step": 34
+    },
+    {
+      "epoch": 0.006198392845283687,
+      "grad_norm": 22.18929672241211,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4831,
+      "step": 35
+    },
+    {
+      "epoch": 0.006375489783720364,
+      "grad_norm": 21.511735916137695,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4702,
+      "step": 36
+    },
+    {
+      "epoch": 0.006552586722157041,
+      "grad_norm": 27.066511154174805,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5608,
+      "step": 37
+    },
+    {
+      "epoch": 0.006729683660593717,
+      "grad_norm": 22.099491119384766,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5373,
+      "step": 38
+    },
+    {
+      "epoch": 0.006906780599030394,
+      "grad_norm": 21.110164642333984,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.51,
+      "step": 39
+    },
+    {
+      "epoch": 0.007083877537467071,
+      "grad_norm": 18.117944717407227,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4379,
+      "step": 40
+    },
+    {
+      "epoch": 0.007260974475903748,
+      "grad_norm": 17.371549606323242,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4025,
+      "step": 41
+    },
+    {
+      "epoch": 0.007438071414340425,
+      "grad_norm": 18.518346786499023,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4477,
+      "step": 42
+    },
+    {
+      "epoch": 0.007615168352777101,
+      "grad_norm": 19.548995971679688,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4838,
+      "step": 43
+    },
+    {
+      "epoch": 0.007792265291213778,
+      "grad_norm": 20.07686424255371,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5081,
+      "step": 44
+    },
+    {
+      "epoch": 0.007969362229650456,
+      "grad_norm": 20.308269500732422,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4412,
+      "step": 45
+    },
+    {
+      "epoch": 0.008146459168087131,
+      "grad_norm": 20.340423583984375,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4678,
+      "step": 46
+    },
+    {
+      "epoch": 0.008323556106523808,
+      "grad_norm": 20.577301025390625,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4283,
+      "step": 47
+    },
+    {
+      "epoch": 0.008500653044960485,
+      "grad_norm": 22.188573837280273,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.471,
+      "step": 48
+    },
+    {
+      "epoch": 0.008677749983397163,
+      "grad_norm": 24.928325653076172,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5276,
+      "step": 49
+    },
+    {
+      "epoch": 0.008854846921833838,
+      "grad_norm": 27.5335636138916,
+      "learning_rate": 0.0,
+      "loss": 0.4987,
+      "step": 50
+    },
+    {
+      "epoch": 0.008854846921833838,
+      "eval_loss": 0.4569474458694458,
+      "eval_runtime": 1567.1076,
+      "eval_samples_per_second": 24.275,
+      "eval_steps_per_second": 3.035,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null