Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b8b1f1168f127a9bdac5ce3ad6bb7fa16e43c5965cfa3e72e904ec2f684586
+oid sha256:96fbb912cd5c3df153e4da3a3d714f10ddac356ae3806f7ad54cc1bfadf7cf88
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05312886c348736b016ad6839e8806cfd3a7087ee1f1e56645c3283c7dfbbb3f
+oid sha256:928979973ec55beb7aa86c9622f220fb14ab0c33c0af3ab9931a2fd519ae9b3e
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a8659a77d65735006ee128ef7b5dc140f65c691f942608fbc52cd4047044c6
+oid sha256:4a377a52f2826f64307b4c7ff60bfffb776e472e41372f8317bdf0e006cb4b85
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2cec44585a4c72501cba96ddf88cce7d990493429865f28d6964ada234a8985
+oid sha256:68a981493dec0d2669b4ca57ef58bea2209743debe619d952d563b13c3134710
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3d52778731d1568a509852e53aff4e8decd33bbb70bcc642ed20fd471cb827
+oid sha256:8e219f3ad6cbb0ea50f0b6abf75555b2b9cfeb6ab1472416d3180e5ca81e9289
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a929f824fcc1c81c0e486cb8616273ff04180d409ac70bf931b946c1b87ae0db
+oid sha256:9c99e993597d768d571fd76119518a238a13e8d6f8239e48045f95a98b5684de
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5932f02b06a65aacca0ded89aafb425697452084c748289b931e7e8346b34b2c
+oid sha256:c3600e4c65714fcf564a26d6b51957f0ef944b5f09e5fcde2090208d40d8ef43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.674420356750488,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8867924528301887,
+  "epoch": 3.018867924528302,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,111 @@
       "eval_samples_per_second": 441.851,
       "eval_steps_per_second": 114.881,
       "step": 25
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 27.86113929748535,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 169.3305,
+      "step": 26
+    },
+    {
+      "epoch": 2.0377358490566038,
+      "grad_norm": 19.5020809173584,
+      "learning_rate": 3.358236731333169e-05,
+      "loss": 171.0887,
+      "step": 27
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "grad_norm": 20.567012786865234,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 171.2371,
+      "step": 28
+    },
+    {
+      "epoch": 2.188679245283019,
+      "grad_norm": 26.858049392700195,
+      "learning_rate": 2.736042792896495e-05,
+      "loss": 169.3462,
+      "step": 29
+    },
+    {
+      "epoch": 2.2641509433962264,
+      "grad_norm": 24.104114532470703,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 169.4767,
+      "step": 30
+    },
+    {
+      "epoch": 2.339622641509434,
+      "grad_norm": 18.2357234954834,
+      "learning_rate": 2.189242401970908e-05,
+      "loss": 171.2782,
+      "step": 31
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "grad_norm": 24.269392013549805,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 169.5011,
+      "step": 32
+    },
+    {
+      "epoch": 2.490566037735849,
+      "grad_norm": 27.363483428955078,
+      "learning_rate": 1.7327508478186218e-05,
+      "loss": 168.39,
+      "step": 33
+    },
+    {
+      "epoch": 2.5660377358490565,
+      "grad_norm": 17.812620162963867,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 171.4145,
+      "step": 34
+    },
+    {
+      "epoch": 2.641509433962264,
+      "grad_norm": 20.519203186035156,
+      "learning_rate": 1.3790200300522413e-05,
+      "loss": 169.7659,
+      "step": 35
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "grad_norm": 26.273950576782227,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 168.288,
+      "step": 36
+    },
+    {
+      "epoch": 2.7924528301886795,
+      "grad_norm": 18.332481384277344,
+      "learning_rate": 1.1376988032730134e-05,
+      "loss": 170.6672,
+      "step": 37
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 20.2203311920166,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 169.821,
+      "step": 38
+    },
+    {
+      "epoch": 2.9433962264150946,
+      "grad_norm": 26.442291259765625,
+      "learning_rate": 1.0153697814699859e-05,
+      "loss": 168.0069,
+      "step": 39
+    },
+    {
+      "epoch": 3.018867924528302,
+      "grad_norm": 21.066753387451172,
+      "learning_rate": 1e-05,
+      "loss": 169.3049,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -221,12 +326,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21794798960640.0,
+  "total_flos": 34883588063232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null