Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559429c3ee90e3238ec87edb1cfd08e30b03a98da3a4d36222b204133bb44d13
+oid sha256:f1a331f836e2e019bbb3e7f2faaae8e8c00e3a82a55fdf257d799ab73c914def
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c27b746810488c476845cb67ff8beac146be7356456ff41d336946dee387a2
+oid sha256:d2a73eaffc87121dd76a2d6c1f6114438920304a50621f3d03f514199cda9c0a
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c72c13244d15ce7fdda540ac30e772068868893ddd0796bd38448744a7db221
+oid sha256:3e755c6594a946b4945bde1c934f9f3a09b001981c825c7673f77b59d5ec89e1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13015125584ef123e0ce88bae39d287754e88d7858c4f8f5698c718f929be116
+oid sha256:061eb0273e4f432c8ff701482727200103700653aa8ab58ec730dbc9f8d92b5b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68227fe3ad680298d9aa7a83eb28e7f6549b63068d869f94284095d0551bd09a
+oid sha256:35a05616c6986b4b7ce08fd54882d0a5ec4db61f972abd1b0f3a287c3ceefc7d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6f139664b9acca2006b6c827fae7e1d2929cb50e006e89d59e92e2e14f80a8
+oid sha256:647364e35e1ef15b282dc12dd32394833a9909ee83f3e76f6b81e9041c8d30d6
 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": 1.0045443773269653,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.054945054945054944,
+  "best_metric": 0.9883686304092407,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10989010989010989,
   "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": 39.086,
       "eval_steps_per_second": 4.897,
       "step": 25
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 0.09802141785621643,
+      "learning_rate": 5e-05,
+      "loss": 0.823,
+      "step": 26
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.11979875713586807,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9298,
+      "step": 27
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 0.1262291818857193,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9278,
+      "step": 28
+    },
+    {
+      "epoch": 0.06373626373626373,
+      "grad_norm": 0.17378444969654083,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9793,
+      "step": 29
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.1964533030986786,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9949,
+      "step": 30
+    },
+    {
+      "epoch": 0.06813186813186813,
+      "grad_norm": 0.23401343822479248,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0134,
+      "step": 31
+    },
+    {
+      "epoch": 0.07032967032967033,
+      "grad_norm": 0.27215376496315,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0036,
+      "step": 32
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.28907185792922974,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0007,
+      "step": 33
+    },
+    {
+      "epoch": 0.07472527472527472,
+      "grad_norm": 0.32493874430656433,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9872,
+      "step": 34
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.3924579620361328,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0338,
+      "step": 35
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.47148391604423523,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0448,
+      "step": 36
+    },
+    {
+      "epoch": 0.08131868131868132,
+      "grad_norm": 0.4807720482349396,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0927,
+      "step": 37
+    },
+    {
+      "epoch": 0.08351648351648351,
+      "grad_norm": 0.1292668879032135,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7478,
+      "step": 38
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.10818104445934296,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9199,
+      "step": 39
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 0.1117909699678421,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9365,
+      "step": 40
+    },
+    {
+      "epoch": 0.09010989010989011,
+      "grad_norm": 0.11949420720338821,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9528,
+      "step": 41
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.12232491374015808,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.002,
+      "step": 42
+    },
+    {
+      "epoch": 0.0945054945054945,
+      "grad_norm": 0.13565704226493835,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0043,
+      "step": 43
+    },
+    {
+      "epoch": 0.0967032967032967,
+      "grad_norm": 0.15927337110042572,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0353,
+      "step": 44
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.16521680355072021,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9845,
+      "step": 45
+    },
+    {
+      "epoch": 0.1010989010989011,
+      "grad_norm": 0.19532620906829834,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0449,
+      "step": 46
+    },
+    {
+      "epoch": 0.10329670329670329,
+      "grad_norm": 0.22346635162830353,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0922,
+      "step": 47
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.27541524171829224,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.1076923076923077,
+      "grad_norm": 0.34510836005210876,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0629,
+      "step": 49
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 0.6853547692298889,
+      "learning_rate": 0.0,
+      "loss": 1.0682,
+      "step": 50
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "eval_loss": 0.9883686304092407,
+      "eval_runtime": 78.1741,
+      "eval_samples_per_second": 39.207,
+      "eval_steps_per_second": 4.912,
+      "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": 2.8155439495092634e+17,
+  "total_flos": 5.634602943203246e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null