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:d1469b3d66b5635f84a255b562c7817785be3b4db7bf89ffc6f9e5b413762c34
+oid sha256:c832d6d01d713408c9af82f1cd9c9020879fbb7d073aa58a15ceaacee67b918f
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac746282af0ddb1044d7c887c466f8cbf6c85f426bfd42e7c6f8db653d6443a
+oid sha256:b08088ecaf127a70d95a1b468b6ab7ff42b7ada6ea2eaed0607a52987df2e491
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43328c39abe79bc0b12b345119a5b6370cf6baad3917860461fa745d555fc41
+oid sha256:f887c826632aa6f07458690eb74d2d7bf9cf83e7eaf291f99f594ed46e74f7b2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f67052561608a0d72ceafb329099246445f48bd007d975ef3cd7b2820d560e
+oid sha256:cd0a6f97f145cc0df0d3da798899b095140650ea5c8cdf26c3999533469a92d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3245650919e8ae4274af8805601473c10d065a5fb98d295eb499222cde5d994f
+oid sha256:09f0e7929bc8cf9b217de4b37e48c650761783ca0453f16209d66e3614b071e9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5cce9b82fec4287d9af8c9f0d6281be163f55ca909cd00912dfad720cf64a7b
+oid sha256:942cd20ce73ca29d17dc9e29fef84bd0d86763eb0f27d7d1591b77ec28b56a0b
 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": 4.563230037689209,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04139501190106592,
+  "best_metric": 4.192285060882568,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08279002380213184,
   "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": 15.686,
       "eval_steps_per_second": 4.078,
       "step": 25
+    },
+    {
+      "epoch": 0.04305081237710856,
+      "grad_norm": 13.002767562866211,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.5723,
+      "step": 26
+    },
+    {
+      "epoch": 0.044706612853151195,
+      "grad_norm": 11.251646995544434,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.9891,
+      "step": 27
+    },
+    {
+      "epoch": 0.04636241332919383,
+      "grad_norm": 9.315027236938477,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.458,
+      "step": 28
+    },
+    {
+      "epoch": 0.04801821380523647,
+      "grad_norm": 7.1844916343688965,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.5533,
+      "step": 29
+    },
+    {
+      "epoch": 0.04967401428127911,
+      "grad_norm": 6.5660529136657715,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.3428,
+      "step": 30
+    },
+    {
+      "epoch": 0.05132981475732174,
+      "grad_norm": 4.740668773651123,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.3628,
+      "step": 31
+    },
+    {
+      "epoch": 0.052985615233364376,
+      "grad_norm": 4.048844337463379,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.4662,
+      "step": 32
+    },
+    {
+      "epoch": 0.05464141570940702,
+      "grad_norm": 5.773531913757324,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.2979,
+      "step": 33
+    },
+    {
+      "epoch": 0.05629721618544965,
+      "grad_norm": 5.650273323059082,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.2232,
+      "step": 34
+    },
+    {
+      "epoch": 0.05795301666149229,
+      "grad_norm": 7.855549335479736,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.5748,
+      "step": 35
+    },
+    {
+      "epoch": 0.05960881713753493,
+      "grad_norm": 6.9513163566589355,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.5689,
+      "step": 36
+    },
+    {
+      "epoch": 0.061264617613577564,
+      "grad_norm": 7.774838447570801,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.7269,
+      "step": 37
+    },
+    {
+      "epoch": 0.0629204180896202,
+      "grad_norm": 4.152009963989258,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.7467,
+      "step": 38
+    },
+    {
+      "epoch": 0.06457621856566284,
+      "grad_norm": 5.257497787475586,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.7762,
+      "step": 39
+    },
+    {
+      "epoch": 0.06623201904170548,
+      "grad_norm": 5.551874160766602,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.1862,
+      "step": 40
+    },
+    {
+      "epoch": 0.06788781951774811,
+      "grad_norm": 4.915943622589111,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.1091,
+      "step": 41
+    },
+    {
+      "epoch": 0.06954361999379075,
+      "grad_norm": 4.883779525756836,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.2785,
+      "step": 42
+    },
+    {
+      "epoch": 0.07119942046983338,
+      "grad_norm": 3.6552951335906982,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.1205,
+      "step": 43
+    },
+    {
+      "epoch": 0.07285522094587603,
+      "grad_norm": 3.0899415016174316,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.1338,
+      "step": 44
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "grad_norm": 3.9144699573516846,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1751,
+      "step": 45
+    },
+    {
+      "epoch": 0.0761668218979613,
+      "grad_norm": 3.444018602371216,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.1967,
+      "step": 46
+    },
+    {
+      "epoch": 0.07782262237400393,
+      "grad_norm": 6.361255168914795,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.4975,
+      "step": 47
+    },
+    {
+      "epoch": 0.07947842285004657,
+      "grad_norm": 4.913413047790527,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.4034,
+      "step": 48
+    },
+    {
+      "epoch": 0.0811342233260892,
+      "grad_norm": 5.116950988769531,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.42,
+      "step": 49
+    },
+    {
+      "epoch": 0.08279002380213184,
+      "grad_norm": 8.649046897888184,
+      "learning_rate": 1e-05,
+      "loss": 4.4341,
+      "step": 50
+    },
+    {
+      "epoch": 0.08279002380213184,
+      "eval_loss": 4.192285060882568,
+      "eval_runtime": 3.273,
+      "eval_samples_per_second": 15.277,
+      "eval_steps_per_second": 3.972,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null