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:e891d7f472c05578b1e11cb9a8f155ba81deba816fd82fed601222d321ee8b55
+oid sha256:269e57ed8bb717336b1b94c6127320c63ef4406a0cd07dc09c234c950fb9213b
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03200b4cf7ceef10384b84de8a6a658803bf9aef86f41309d72a31e0d43645d9
+oid sha256:ac1b57314896570d62b32d47220e17f58e732161b49fd928802c6602f4bd0a76
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1013fab26d9f10b2cd7ce9ca6fce490010f925e040647938cd66d039dead508
+oid sha256:2470326e63720b9c2b532e840ba2aa37daeb6c106b95fcdb0e29979c4af37d07
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a43979577f417f5f52529ccd29b04d89e0c6f7076c4680bb2b1c2398c53dc
+oid sha256:ce7d6723f6bf70a0e9b9b2444eaa4e83cdcce7ababf578c2fa2a2d5d73b7405f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3469e9e26082b3400296dbe6c557ba60f63fb947c8d998e7ebc102c0d4ef9a43
+oid sha256:fcb48e3a2249fe0e2cda8ec792bb13f5c38195c570365a1757dd81a2cbac5436
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43fe536ec202674af63e7f35ddde3a5d1cee1ab1d10debc7f3f085a607de6d11
+oid sha256:d896ece4807ef77f7639aae20bd1c38d22d912978931ea25e03186050002542f
 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": 10.823450088500977,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7341772151898733,
+  "epoch": 3.1772151898734178,
   "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": 475.75,
       "eval_steps_per_second": 123.695,
       "step": 25
+    },
+    {
+      "epoch": 1.8016877637130801,
+      "grad_norm": 12.02143383026123,
+      "learning_rate": 4.682634170592537e-05,
+      "loss": 173.4692,
+      "step": 26
+    },
+    {
+      "epoch": 1.869198312236287,
+      "grad_norm": 12.537296295166016,
+      "learning_rate": 4.3617997792374365e-05,
+      "loss": 172.9671,
+      "step": 27
+    },
+    {
+      "epoch": 1.9367088607594938,
+      "grad_norm": 12.867912292480469,
+      "learning_rate": 4.0470381785284936e-05,
+      "loss": 172.5768,
+      "step": 28
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 11.798124313354492,
+      "learning_rate": 3.7400287577942993e-05,
+      "loss": 173.2267,
+      "step": 29
+    },
+    {
+      "epoch": 2.1181434599156117,
+      "grad_norm": 11.980865478515625,
+      "learning_rate": 3.4424095451291274e-05,
+      "loss": 172.9524,
+      "step": 30
+    },
+    {
+      "epoch": 2.1856540084388185,
+      "grad_norm": 12.464712142944336,
+      "learning_rate": 3.155768467804314e-05,
+      "loss": 172.4342,
+      "step": 31
+    },
+    {
+      "epoch": 2.2531645569620253,
+      "grad_norm": 12.398478507995605,
+      "learning_rate": 2.8816348799892133e-05,
+      "loss": 172.3243,
+      "step": 32
+    },
+    {
+      "epoch": 2.320675105485232,
+      "grad_norm": 11.792886734008789,
+      "learning_rate": 2.621471402984991e-05,
+      "loss": 172.8272,
+      "step": 33
+    },
+    {
+      "epoch": 2.388185654008439,
+      "grad_norm": 11.965614318847656,
+      "learning_rate": 2.3766661215071475e-05,
+      "loss": 172.4491,
+      "step": 34
+    },
+    {
+      "epoch": 2.4556962025316453,
+      "grad_norm": 12.57142162322998,
+      "learning_rate": 2.148525177652982e-05,
+      "loss": 171.9388,
+      "step": 35
+    },
+    {
+      "epoch": 2.523206751054852,
+      "grad_norm": 11.402908325195312,
+      "learning_rate": 1.938265802068357e-05,
+      "loss": 172.6287,
+      "step": 36
+    },
+    {
+      "epoch": 2.590717299578059,
+      "grad_norm": 11.887864112854004,
+      "learning_rate": 1.74700981949555e-05,
+      "loss": 172.3424,
+      "step": 37
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 12.034871101379395,
+      "learning_rate": 1.5757776633528655e-05,
+      "loss": 172.0158,
+      "step": 38
+    },
+    {
+      "epoch": 2.7257383966244726,
+      "grad_norm": 12.191680908203125,
+      "learning_rate": 1.4254829312808404e-05,
+      "loss": 171.8472,
+      "step": 39
+    },
+    {
+      "epoch": 2.7932489451476794,
+      "grad_norm": 11.363740921020508,
+      "learning_rate": 1.2969275107035345e-05,
+      "loss": 172.5804,
+      "step": 40
+    },
+    {
+      "epoch": 2.8607594936708862,
+      "grad_norm": 11.75307559967041,
+      "learning_rate": 1.1907973004121738e-05,
+      "loss": 172.0639,
+      "step": 41
+    },
+    {
+      "epoch": 2.928270042194093,
+      "grad_norm": 12.174725532531738,
+      "learning_rate": 1.1076585509983283e-05,
+      "loss": 171.687,
+      "step": 42
+    },
+    {
+      "epoch": 3.042194092827004,
+      "grad_norm": 11.464780807495117,
+      "learning_rate": 1.0479548436620041e-05,
+      "loss": 172.3345,
+      "step": 43
+    },
+    {
+      "epoch": 3.109704641350211,
+      "grad_norm": 11.445940017700195,
+      "learning_rate": 1.0120047235140178e-05,
+      "loss": 172.2803,
+      "step": 44
+    },
+    {
+      "epoch": 3.1772151898734178,
+      "grad_norm": 11.784713745117188,
+      "learning_rate": 1e-05,
+      "loss": 171.8565,
+      "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": 19055561932800.0,
+  "total_flos": 34300011479040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null