Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d8a4012dc45192840ebb4cf6a71e4d3672089b6e4e341316432da6f74b3df5
+oid sha256:b44d60fc00e24757574f197b9291e9f58d34e66a18242dd58d09f3244a6c3ca9
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61aa72bd6384e0f94f2da01b1df2705afe8ce98534ab5e1044d7ae6899ee23a7
+oid sha256:40ba959fa79f91f51f866807664abaa0c69a95704d3338638ee0e0e44fcab6a2
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00426f9d312d38fed4d5a7dae87d688d728cdb569d7f6c595182f9d7399a424
+oid sha256:6ec2765f119c07d840dc50c46ad02b6deced7e424cf56c217e74709a28430f46
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902b764ae55b23a576245e078964502cec38db947846cdef44ae392316ef4ed5
+oid sha256:9ae8c1038d5ea986f2da50bcc7da9928c0063cf199cb8e361f0bb7ac40c66098
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f93b92f147ef611e1352967d1926c27c56a1525be330c852425970620f438f7
+oid sha256:66eb8bf40d34545d9a68de94006c8dd7f03890f46a42e1990a8ad8418273e108
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733ccd530505e32e37c5ef26efc8c5ba16646bd3cdcc1303471187a82694bbe5
+oid sha256:a56adeb08ed90b4db82d43f909336b86a5bb0d9dd811adf93768570e70c43e65
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3177ea4b394d20689f047a52c65a4c736ff1c10b2534d22548525087dc2bae5a
+oid sha256:69229c49401e88b3b3378c31d82dab5bb5c4af56b04c5c6fd06f1abbc7474757
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.757043838500977,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.694915254237288,
+  "epoch": 3.0508474576271185,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,146 @@
       "eval_samples_per_second": 402.037,
       "eval_steps_per_second": 104.53,
       "step": 25
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": 0.12495192885398865,
+      "learning_rate": 4.682634170592537e-05,
+      "loss": 13.6564,
+      "step": 26
+    },
+    {
+      "epoch": 1.8305084745762712,
+      "grad_norm": 0.1118931695818901,
+      "learning_rate": 4.3617997792374365e-05,
+      "loss": 11.6316,
+      "step": 27
+    },
+    {
+      "epoch": 1.8983050847457628,
+      "grad_norm": 0.11347147822380066,
+      "learning_rate": 4.0470381785284936e-05,
+      "loss": 12.0775,
+      "step": 28
+    },
+    {
+      "epoch": 1.9661016949152543,
+      "grad_norm": 0.13937610387802124,
+      "learning_rate": 3.7400287577942993e-05,
+      "loss": 13.7082,
+      "step": 29
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": 0.11871737241744995,
+      "learning_rate": 3.4424095451291274e-05,
+      "loss": 13.0724,
+      "step": 30
+    },
+    {
+      "epoch": 2.1016949152542375,
+      "grad_norm": 0.1116810292005539,
+      "learning_rate": 3.155768467804314e-05,
+      "loss": 11.3104,
+      "step": 31
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.11251462250947952,
+      "learning_rate": 2.8816348799892133e-05,
+      "loss": 11.7289,
+      "step": 32
+    },
+    {
+      "epoch": 2.23728813559322,
+      "grad_norm": 0.08083707094192505,
+      "learning_rate": 2.621471402984991e-05,
+      "loss": 7.9908,
+      "step": 33
+    },
+    {
+      "epoch": 2.305084745762712,
+      "grad_norm": 0.14848583936691284,
+      "learning_rate": 2.3766661215071475e-05,
+      "loss": 15.5103,
+      "step": 34
+    },
+    {
+      "epoch": 2.3728813559322033,
+      "grad_norm": 0.12374146282672882,
+      "learning_rate": 2.148525177652982e-05,
+      "loss": 11.6638,
+      "step": 35
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 0.1271556317806244,
+      "learning_rate": 1.938265802068357e-05,
+      "loss": 12.3677,
+      "step": 36
+    },
+    {
+      "epoch": 2.5084745762711864,
+      "grad_norm": 0.1158226951956749,
+      "learning_rate": 1.74700981949555e-05,
+      "loss": 11.62,
+      "step": 37
+    },
+    {
+      "epoch": 2.576271186440678,
+      "grad_norm": 0.12057599425315857,
+      "learning_rate": 1.5757776633528655e-05,
+      "loss": 11.3604,
+      "step": 38
+    },
+    {
+      "epoch": 2.6440677966101696,
+      "grad_norm": 0.12079162150621414,
+      "learning_rate": 1.4254829312808404e-05,
+      "loss": 11.7273,
+      "step": 39
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 0.09226712584495544,
+      "learning_rate": 1.2969275107035345e-05,
+      "loss": 8.0331,
+      "step": 40
+    },
+    {
+      "epoch": 2.7796610169491527,
+      "grad_norm": 0.15772119164466858,
+      "learning_rate": 1.1907973004121738e-05,
+      "loss": 15.5725,
+      "step": 41
+    },
+    {
+      "epoch": 2.847457627118644,
+      "grad_norm": 0.12561185657978058,
+      "learning_rate": 1.1076585509983283e-05,
+      "loss": 11.6187,
+      "step": 42
+    },
+    {
+      "epoch": 2.915254237288136,
+      "grad_norm": 0.1435082107782364,
+      "learning_rate": 1.0479548436620041e-05,
+      "loss": 12.1482,
+      "step": 43
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 0.15611915290355682,
+      "learning_rate": 1.0120047235140178e-05,
+      "loss": 14.161,
+      "step": 44
+    },
+    {
+      "epoch": 3.0508474576271185,
+      "grad_norm": 0.1359080821275711,
+      "learning_rate": 1e-05,
+      "loss": 12.1284,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -221,12 +361,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81943068672000.0,
+  "total_flos": 147497523609600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null