Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325956f2951bca7d7d185c7c41ddb74f586cb7b7a7a26be7470617b97fa9c131
+oid sha256:0a17a34c7402fb0486ea7990436d30622f3c31cd6f9818464f801d901d1bbf0d
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64415f111a05dda52299054e5b286234b2cb72b05dda911731eef4d43f7eace4
+oid sha256:5201d34a952207d9901c2f1c091cb324299f40c5e374de4f70eb6d4531573871
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00145a1e7abcb8761324ca9e03fe09250cc601708c2a8c3b8dcc3f592c79f673
+oid sha256:878b59f5b4e3fa5346842a7e4ecd8dcfc78aa3250328173faf9aac35b878a9af
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d64c99890123d30cbea5f7c4dba151ca5290499d3d4f9ffbcb8115381e1cac
+oid sha256:72f709b1de2cb26a283a4ca5af1a3f9988ef3cf350edd17bcc4d167aadfdb7f9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdd3fbd86ec23945adfe12d301b5866b58c00b5835cdae7cd6a58d90630efb9
+oid sha256:2e42419fa4e23e50ec4587e34ee92b9cdf6a2552a4c7e459ace3225ece42bc25
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52356394fa12408b76a7e5c4abec46214465b055dfb733c9ece9ed2a0e5ff6da
+oid sha256:01ad3daa3984c41630e2af60ca21861dca3bbab76367b2f68dd158b8dcaab316
 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": 0.7074735760688782,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05355469272995046,
+  "best_metric": 0.7001811861991882,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10710938545990092,
   "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": 26.393,
       "eval_steps_per_second": 6.862,
       "step": 25
+    },
+    {
+      "epoch": 0.05569688043914848,
+      "grad_norm": 7.93866491317749,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 22.9822,
+      "step": 26
+    },
+    {
+      "epoch": 0.0578390681483465,
+      "grad_norm": 3.1443004608154297,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 22.786,
+      "step": 27
+    },
+    {
+      "epoch": 0.05998125585754452,
+      "grad_norm": 2.8703548908233643,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 22.4311,
+      "step": 28
+    },
+    {
+      "epoch": 0.062123443566742535,
+      "grad_norm": 2.1649084091186523,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 22.4676,
+      "step": 29
+    },
+    {
+      "epoch": 0.06426563127594055,
+      "grad_norm": 1.565459966659546,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 22.4245,
+      "step": 30
+    },
+    {
+      "epoch": 0.06640781898513858,
+      "grad_norm": 1.9081851243972778,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 22.479,
+      "step": 31
+    },
+    {
+      "epoch": 0.06855000669433658,
+      "grad_norm": 1.3694819211959839,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 22.4532,
+      "step": 32
+    },
+    {
+      "epoch": 0.07069219440353461,
+      "grad_norm": 1.3111183643341064,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 22.4501,
+      "step": 33
+    },
+    {
+      "epoch": 0.07283438211273263,
+      "grad_norm": 1.5006563663482666,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 22.4873,
+      "step": 34
+    },
+    {
+      "epoch": 0.07497656982193064,
+      "grad_norm": 5.990767955780029,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 22.5241,
+      "step": 35
+    },
+    {
+      "epoch": 0.07711875753112866,
+      "grad_norm": 1.6189005374908447,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 22.4759,
+      "step": 36
+    },
+    {
+      "epoch": 0.07926094524032669,
+      "grad_norm": 1.4039047956466675,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 22.445,
+      "step": 37
+    },
+    {
+      "epoch": 0.0814031329495247,
+      "grad_norm": 1.4595952033996582,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 22.4729,
+      "step": 38
+    },
+    {
+      "epoch": 0.08354532065872272,
+      "grad_norm": 4.050112247467041,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 22.478,
+      "step": 39
+    },
+    {
+      "epoch": 0.08568750836792074,
+      "grad_norm": 3.0547168254852295,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 22.411,
+      "step": 40
+    },
+    {
+      "epoch": 0.08782969607711875,
+      "grad_norm": 1.3965966701507568,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 22.4308,
+      "step": 41
+    },
+    {
+      "epoch": 0.08997188378631678,
+      "grad_norm": 1.4640690088272095,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 22.4479,
+      "step": 42
+    },
+    {
+      "epoch": 0.09211407149551479,
+      "grad_norm": 2.038416624069214,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 22.442,
+      "step": 43
+    },
+    {
+      "epoch": 0.09425625920471281,
+      "grad_norm": 1.304911732673645,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 22.4374,
+      "step": 44
+    },
+    {
+      "epoch": 0.09639844691391083,
+      "grad_norm": 1.4404685497283936,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 22.4142,
+      "step": 45
+    },
+    {
+      "epoch": 0.09854063462310884,
+      "grad_norm": 1.2715855836868286,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 22.3841,
+      "step": 46
+    },
+    {
+      "epoch": 0.10068282233230687,
+      "grad_norm": 0.9410794973373413,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 22.4332,
+      "step": 47
+    },
+    {
+      "epoch": 0.10282501004150489,
+      "grad_norm": 1.003109335899353,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 22.4137,
+      "step": 48
+    },
+    {
+      "epoch": 0.1049671977507029,
+      "grad_norm": 1.374916911125183,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 22.4539,
+      "step": 49
+    },
+    {
+      "epoch": 0.10710938545990092,
+      "grad_norm": 0.7090279459953308,
+      "learning_rate": 1e-05,
+      "loss": 22.4465,
+      "step": 50
+    },
+    {
+      "epoch": 0.10710938545990092,
+      "eval_loss": 0.7001811861991882,
+      "eval_runtime": 1.8911,
+      "eval_samples_per_second": 26.44,
+      "eval_steps_per_second": 6.874,
+      "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": 3.039627994810286e+17,
+  "total_flos": 6.059534154779853e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null