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:df6735127783358200b27ef27cea0a0aca9f428e145d194dd62170bdafee4a88
+oid sha256:d25a77322ee75eb0d60f8e297e9ca632b0ad0ad7f762afca55990beaeb6b283a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe59b1fa07b299225b4fb311b50919259132e4593e6425a2442d4bc987d0869
+oid sha256:17dc240ab84dce96393fbf68f860e11ce4b84bf1f7f0eaaff1dc657e7b809b5b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9509098cc0da9660abf64d25cc865085c05f7c1a5c90efc076b3f05fcb039ef4
+oid sha256:da1dd37b6b2b8addac5318dcb02371b7361b0f69dc6bbdf1905c577b6a26438e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73ad0d8046daba0b23053fd2d6fdec3a8c5b9d835d0dc4182a9aa6833def04e
+oid sha256:e969efafa249cbec4294bdb2539d1854c391e83857c421fb290cc1aa7b0216fe
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ce0389f3e6de97b8c6e40c35d9f7ba10915b344cd22f93281191ffbd2c7b29
+oid sha256:e866d585f1c64016aaff00d7fb037b1a9cdc9ff7238c59f38ccd0f7a0ad0d94d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef8b12261ed1d41092030f03363703ff80e98f0082ed4f8d0fe289831390a14
+oid sha256:a721e8893787e487dec8263b0e584658ab22af7687a116af78e62900da6655d4
 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": 0.10687629878520966,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4333694474539545,
+  "best_metric": 0.09838873893022537,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.866738894907909,
   "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": 14.401,
       "eval_steps_per_second": 3.744,
       "step": 25
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 0.08605414628982544,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0314,
+      "step": 26
+    },
+    {
+      "epoch": 0.46803900325027087,
+      "grad_norm": 0.1190139502286911,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0437,
+      "step": 27
+    },
+    {
+      "epoch": 0.48537378114842905,
+      "grad_norm": 0.13927221298217773,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0511,
+      "step": 28
+    },
+    {
+      "epoch": 0.5027085590465872,
+      "grad_norm": 0.20223039388656616,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0631,
+      "step": 29
+    },
+    {
+      "epoch": 0.5200433369447454,
+      "grad_norm": 0.17049828171730042,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0607,
+      "step": 30
+    },
+    {
+      "epoch": 0.5373781148429035,
+      "grad_norm": 0.45451751351356506,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0692,
+      "step": 31
+    },
+    {
+      "epoch": 0.5547128927410617,
+      "grad_norm": 0.22615575790405273,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0783,
+      "step": 32
+    },
+    {
+      "epoch": 0.5720476706392199,
+      "grad_norm": 0.2533192038536072,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0794,
+      "step": 33
+    },
+    {
+      "epoch": 0.5893824485373781,
+      "grad_norm": 0.21578319370746613,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0759,
+      "step": 34
+    },
+    {
+      "epoch": 0.6067172264355363,
+      "grad_norm": 0.26224207878112793,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0896,
+      "step": 35
+    },
+    {
+      "epoch": 0.6240520043336945,
+      "grad_norm": 0.3087189197540283,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.097,
+      "step": 36
+    },
+    {
+      "epoch": 0.6413867822318526,
+      "grad_norm": 0.3518355190753937,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.121,
+      "step": 37
+    },
+    {
+      "epoch": 0.6587215601300108,
+      "grad_norm": 0.1477062702178955,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0455,
+      "step": 38
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 0.1556491106748581,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0385,
+      "step": 39
+    },
+    {
+      "epoch": 0.6933911159263272,
+      "grad_norm": 0.1597602367401123,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0482,
+      "step": 40
+    },
+    {
+      "epoch": 0.7107258938244854,
+      "grad_norm": 0.23317818343639374,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0582,
+      "step": 41
+    },
+    {
+      "epoch": 0.7280606717226435,
+      "grad_norm": 0.2035202533006668,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0653,
+      "step": 42
+    },
+    {
+      "epoch": 0.7453954496208017,
+      "grad_norm": 0.2277495265007019,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.071,
+      "step": 43
+    },
+    {
+      "epoch": 0.7627302275189599,
+      "grad_norm": 0.24984626471996307,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0752,
+      "step": 44
+    },
+    {
+      "epoch": 0.7800650054171181,
+      "grad_norm": 0.19852232933044434,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0763,
+      "step": 45
+    },
+    {
+      "epoch": 0.7973997833152763,
+      "grad_norm": 0.24323515594005585,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0701,
+      "step": 46
+    },
+    {
+      "epoch": 0.8147345612134345,
+      "grad_norm": 0.2687220573425293,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0959,
+      "step": 47
+    },
+    {
+      "epoch": 0.8320693391115926,
+      "grad_norm": 0.2877626121044159,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0928,
+      "step": 48
+    },
+    {
+      "epoch": 0.8494041170097508,
+      "grad_norm": 0.4412320554256439,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1296,
+      "step": 49
+    },
+    {
+      "epoch": 0.866738894907909,
+      "grad_norm": 0.4098319411277771,
+      "learning_rate": 1e-05,
+      "loss": 0.15,
+      "step": 50
+    },
+    {
+      "epoch": 0.866738894907909,
+      "eval_loss": 0.09838873893022537,
+      "eval_runtime": 3.5061,
+      "eval_samples_per_second": 14.261,
+      "eval_steps_per_second": 3.708,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null