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:c442f969bd7ca2e4f3d807384145aa684b8e7091e03c5076f9e510e23a6b4294
+oid sha256:b0f94e42ec6826e5aef3918a920ad83a03aec26aa6937e9f151c26c70912389f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f5939e2f4dfacc86c76daf492376adf9c64cd40d42ce88198c7a86382732fd
+oid sha256:02fac7bb0da75718b27e96ddcd73d472bb9a9bf4128666bb9c20835c575f5627
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ef70e6ebfe011439b438db0c6ee750fba6df7f7689886aa97afd1a5cfe2ed5
+oid sha256:dd249b5d7b84f30766eff276020b5d032ccd9bbc8f51847cee829618aaad3819
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce544096056420d1ff1a6fa95ffcb8913cdf91121e467d0983e3e6e17d7e1a2a
+oid sha256:e0a09bad533cbd91ca6e9390670cf07b1f27e89e5cd115fe7cdd74d0f9595cb9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf035159807c3be88d3378ccba50c84e2606ccc8e230035c783db9f4b4c44edb
+oid sha256:0b2a2f82dc24a7b071e49a97ba4177c9d50e438cbd95b777b350432ce73ca2d7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1d7971fc99bf8cab5b6b2744a6c1299347ad22bc48c3bcee500e35b61404fd
+oid sha256:84b952b2f0c90a736ad9ce8aa09f7c688745b57b47fdfe680df648a3b5128c35
 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": 3.1171445846557617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.0956284153005464,
+  "best_metric": 3.0746829509735107,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.191256830601093,
   "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": 24.509,
       "eval_steps_per_second": 6.372,
       "step": 25
+    },
+    {
+      "epoch": 1.139344262295082,
+      "grad_norm": 0.8861986398696899,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.905,
+      "step": 26
+    },
+    {
+      "epoch": 1.1830601092896176,
+      "grad_norm": 0.926170289516449,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.8752,
+      "step": 27
+    },
+    {
+      "epoch": 1.226775956284153,
+      "grad_norm": 0.6107288599014282,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.7151,
+      "step": 28
+    },
+    {
+      "epoch": 1.2704918032786885,
+      "grad_norm": 1.5895434617996216,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.2106,
+      "step": 29
+    },
+    {
+      "epoch": 1.314207650273224,
+      "grad_norm": 1.176580786705017,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.1129,
+      "step": 30
+    },
+    {
+      "epoch": 1.3579234972677596,
+      "grad_norm": 0.8539705872535706,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8404,
+      "step": 31
+    },
+    {
+      "epoch": 1.401639344262295,
+      "grad_norm": 0.8638070225715637,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.8358,
+      "step": 32
+    },
+    {
+      "epoch": 1.4453551912568305,
+      "grad_norm": 0.8372650742530823,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.767,
+      "step": 33
+    },
+    {
+      "epoch": 1.489071038251366,
+      "grad_norm": 0.9196673035621643,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.9233,
+      "step": 34
+    },
+    {
+      "epoch": 1.5327868852459017,
+      "grad_norm": 1.2137387990951538,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.3744,
+      "step": 35
+    },
+    {
+      "epoch": 1.5765027322404372,
+      "grad_norm": 0.9855496287345886,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.8643,
+      "step": 36
+    },
+    {
+      "epoch": 1.6202185792349728,
+      "grad_norm": 0.9541515707969666,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.9213,
+      "step": 37
+    },
+    {
+      "epoch": 1.6639344262295082,
+      "grad_norm": 0.9766571521759033,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.9292,
+      "step": 38
+    },
+    {
+      "epoch": 1.7076502732240437,
+      "grad_norm": 0.7789756655693054,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.789,
+      "step": 39
+    },
+    {
+      "epoch": 1.751366120218579,
+      "grad_norm": 1.3762660026550293,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.2738,
+      "step": 40
+    },
+    {
+      "epoch": 1.7950819672131146,
+      "grad_norm": 0.9097878932952881,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.9783,
+      "step": 41
+    },
+    {
+      "epoch": 1.8387978142076502,
+      "grad_norm": 0.8889710903167725,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.8984,
+      "step": 42
+    },
+    {
+      "epoch": 1.8825136612021858,
+      "grad_norm": 0.8106191754341125,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8922,
+      "step": 43
+    },
+    {
+      "epoch": 1.9262295081967213,
+      "grad_norm": 0.827426016330719,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.8096,
+      "step": 44
+    },
+    {
+      "epoch": 1.969945355191257,
+      "grad_norm": 0.7913272380828857,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.9234,
+      "step": 45
+    },
+    {
+      "epoch": 2.0163934426229506,
+      "grad_norm": 1.123631238937378,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.5046,
+      "step": 46
+    },
+    {
+      "epoch": 2.060109289617486,
+      "grad_norm": 1.1768923997879028,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.0788,
+      "step": 47
+    },
+    {
+      "epoch": 2.1038251366120218,
+      "grad_norm": 0.8141267895698547,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.7541,
+      "step": 48
+    },
+    {
+      "epoch": 2.1475409836065573,
+      "grad_norm": 0.8230898380279541,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.8372,
+      "step": 49
+    },
+    {
+      "epoch": 2.191256830601093,
+      "grad_norm": 0.8030880093574524,
+      "learning_rate": 1e-05,
+      "loss": 2.8268,
+      "step": 50
+    },
+    {
+      "epoch": 2.191256830601093,
+      "eval_loss": 3.0746829509735107,
+      "eval_runtime": 2.0349,
+      "eval_samples_per_second": 24.571,
+      "eval_steps_per_second": 6.388,
+      "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