Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035228dbceb214bea1ebd1bfa76ccd21cbc6c3607c919ced8635d4cc1a199f08
+oid sha256:4da952c3e35f59eeec963c50802ddabc067f82d9440f780c78661944b8acc669
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd1990331421781fbbc782956997435611730978edbd62c3fd9b04c5f0fc3ff
+oid sha256:5159278cbebe3f62b1c4d0670391a48747cde3eb434f59c6c75f7179d72b7226
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28b62a802a5e58526f1c88c42e378236938a9f5dd4b0018e7158a8127cb666e
+oid sha256:8b9a380f0adae541e5b02a1c610430ceb4922967cd56b7ce514382f12c91aa4e
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9fbc8ffc4a6fa98e9e82478dcf5d9b02110afff3859761ffde294b6429ec439
+oid sha256:e60e0593bdf8c797e0c776bc79c9ef042bec56ab10e209a2961c51824afe2324
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6841c5b4769c8bd1d6988c9eb125d2e8c322f29c073c9fc49d2a6a2be8b0f31
+oid sha256:2ce20da9a7eebc7944598e826bef6904d610db6b25e3c16b0008e785775b3e5c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c77357bab35fa43769246e5a3e6c6fe86280409c6bbe734de5663703ac8ec7
+oid sha256:c29a0ee2f7d3a95183874e7b3c0d1c0d58def8796dc00171924822e03d165ad6
 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": 10.581374168395996,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3404255319148936,
+  "best_metric": 10.343125343322754,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6808510638297872,
   "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": 141.661,
       "eval_steps_per_second": 36.832,
       "step": 25
+    },
+    {
+      "epoch": 0.35404255319148936,
+      "grad_norm": 33.990882873535156,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 168.028,
+      "step": 26
+    },
+    {
+      "epoch": 0.3676595744680851,
+      "grad_norm": 35.0228385925293,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 167.0524,
+      "step": 27
+    },
+    {
+      "epoch": 0.38127659574468087,
+      "grad_norm": 33.29133224487305,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 167.292,
+      "step": 28
+    },
+    {
+      "epoch": 0.3948936170212766,
+      "grad_norm": 31.941789627075195,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 167.1951,
+      "step": 29
+    },
+    {
+      "epoch": 0.4085106382978723,
+      "grad_norm": 30.474773406982422,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 167.147,
+      "step": 30
+    },
+    {
+      "epoch": 0.4221276595744681,
+      "grad_norm": 30.455781936645508,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 166.9363,
+      "step": 31
+    },
+    {
+      "epoch": 0.4357446808510638,
+      "grad_norm": 29.7111873626709,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 166.833,
+      "step": 32
+    },
+    {
+      "epoch": 0.4493617021276596,
+      "grad_norm": 29.804931640625,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 166.6142,
+      "step": 33
+    },
+    {
+      "epoch": 0.46297872340425533,
+      "grad_norm": 29.273719787597656,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 166.5084,
+      "step": 34
+    },
+    {
+      "epoch": 0.4765957446808511,
+      "grad_norm": 28.390575408935547,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 166.8301,
+      "step": 35
+    },
+    {
+      "epoch": 0.4902127659574468,
+      "grad_norm": 28.319622039794922,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 166.4397,
+      "step": 36
+    },
+    {
+      "epoch": 0.5038297872340426,
+      "grad_norm": 27.683088302612305,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 166.8986,
+      "step": 37
+    },
+    {
+      "epoch": 0.5174468085106383,
+      "grad_norm": 33.09490203857422,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 169.1795,
+      "step": 38
+    },
+    {
+      "epoch": 0.531063829787234,
+      "grad_norm": 32.074981689453125,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 164.2301,
+      "step": 39
+    },
+    {
+      "epoch": 0.5446808510638298,
+      "grad_norm": 34.14289474487305,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 163.6617,
+      "step": 40
+    },
+    {
+      "epoch": 0.5582978723404255,
+      "grad_norm": 29.819684982299805,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 164.8387,
+      "step": 41
+    },
+    {
+      "epoch": 0.5719148936170213,
+      "grad_norm": 29.242847442626953,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 164.9634,
+      "step": 42
+    },
+    {
+      "epoch": 0.585531914893617,
+      "grad_norm": 29.04056167602539,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 164.6975,
+      "step": 43
+    },
+    {
+      "epoch": 0.5991489361702128,
+      "grad_norm": 28.505887985229492,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 164.7266,
+      "step": 44
+    },
+    {
+      "epoch": 0.6127659574468085,
+      "grad_norm": 28.198604583740234,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 164.8328,
+      "step": 45
+    },
+    {
+      "epoch": 0.6263829787234042,
+      "grad_norm": 27.653589248657227,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 165.505,
+      "step": 46
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 27.47649383544922,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 164.8701,
+      "step": 47
+    },
+    {
+      "epoch": 0.6536170212765957,
+      "grad_norm": 27.234596252441406,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 165.0507,
+      "step": 48
+    },
+    {
+      "epoch": 0.6672340425531915,
+      "grad_norm": 26.7624454498291,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 165.8583,
+      "step": 49
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 34.30644607543945,
+      "learning_rate": 1e-05,
+      "loss": 169.6575,
+      "step": 50
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "eval_loss": 10.343125343322754,
+      "eval_runtime": 0.3469,
+      "eval_samples_per_second": 144.115,
+      "eval_steps_per_second": 37.47,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null