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:f018780a2592117eee287fe2c00fddcb70ea7e609b70d17e03f5b347fadd64a7
+oid sha256:83db0d6a8acc3422ccc6b338a6c8cb26d9e1a09b50fb74308c58451429bc5060
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09df2ca8702f709fb7ca1c40c94ba2f2eb0ccfa5ed181998daf41fbfc10e6dbe
+oid sha256:bb76643d5c85fddecd8dcaac111af21e49b792f421b45056f9bd77c80c123a3e
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4317f01ae2e7b59d6ff4c68261def9859381a2349c7e5299e2c3b70fe2043c2
+oid sha256:d7e5bf92a98adb5f0c75de3b0c9f0e114f746ce65779cc1bcb1d42740aeb8829
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c294811f28537892efff391577daa39de57cb167a282f57f67ceb1973aefce
+oid sha256:279db2ae3cb30d1c831be4b7af65db32e2f5095f59fdd0538b41025e42d1e32e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e0cc3b79f944a3974cd295177b17903c581aec9aa6134c383ad766ac218fa5
+oid sha256:fa42a9a53239df8245a8af17c8e563d8bc75d438862355bf891db72014f08162
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c5727e5e53ca7ef51d25ec677df71cf2b15af45c484ce5661b480f7679ac33
+oid sha256:a57b6b3eb394dd91091dd586788d1fc3392677c33a497a1ad856626a38929710
 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": 10.675261497497559,
   "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": 396.832,
       "eval_steps_per_second": 103.176,
       "step": 25
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 28.307985305786133,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 169.2845,
+      "step": 26
+    },
+    {
+      "epoch": 2.0377358490566038,
+      "grad_norm": 19.4202938079834,
+      "learning_rate": 3.358236731333169e-05,
+      "loss": 171.071,
+      "step": 27
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "grad_norm": 20.111217498779297,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 171.2749,
+      "step": 28
+    },
+    {
+      "epoch": 2.188679245283019,
+      "grad_norm": 27.161666870117188,
+      "learning_rate": 2.736042792896495e-05,
+      "loss": 169.209,
+      "step": 29
+    },
+    {
+      "epoch": 2.2641509433962264,
+      "grad_norm": 24.207616806030273,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 169.4579,
+      "step": 30
+    },
+    {
+      "epoch": 2.339622641509434,
+      "grad_norm": 17.929601669311523,
+      "learning_rate": 2.189242401970908e-05,
+      "loss": 171.2735,
+      "step": 31
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "grad_norm": 24.393522262573242,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 169.3934,
+      "step": 32
+    },
+    {
+      "epoch": 2.490566037735849,
+      "grad_norm": 27.657506942749023,
+      "learning_rate": 1.7327508478186218e-05,
+      "loss": 168.3053,
+      "step": 33
+    },
+    {
+      "epoch": 2.5660377358490565,
+      "grad_norm": 17.512022018432617,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 171.456,
+      "step": 34
+    },
+    {
+      "epoch": 2.641509433962264,
+      "grad_norm": 20.39818000793457,
+      "learning_rate": 1.3790200300522413e-05,
+      "loss": 169.7444,
+      "step": 35
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "grad_norm": 26.587793350219727,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 168.1875,
+      "step": 36
+    },
+    {
+      "epoch": 2.7924528301886795,
+      "grad_norm": 18.13593101501465,
+      "learning_rate": 1.1376988032730134e-05,
+      "loss": 170.666,
+      "step": 37
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 19.847274780273438,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 169.8308,
+      "step": 38
+    },
+    {
+      "epoch": 2.9433962264150946,
+      "grad_norm": 26.68253517150879,
+      "learning_rate": 1.0153697814699859e-05,
+      "loss": 167.9355,
+      "step": 39
+    },
+    {
+      "epoch": 3.018867924528302,
+      "grad_norm": 20.943115234375,
+      "learning_rate": 1e-05,
+      "loss": 169.3668,
+      "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