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:ecec8ac997fa8fa65b28d8e510f06b566fbc03b713183a8fbd9c0f0748ee6331
+oid sha256:19c2a57e8cd2241657c4c5f0b2c660c95cfe2846f564e923e7433702f0278c4e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fce0f489a42c93a56fabb9e85e96a3c28e8107027e5ff702633fc9e001399c
+oid sha256:f545ce2fa4dbef89c368e7eb79f8fc33bb1396c4baa9b285b7459fb5debbc312
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f2fe1790db27ec340675d86f668ee8c2fb526a7c3a43a5ca198da2711be77f
+oid sha256:a18952cd0e2897b6e49670a89b563ab0e49500c78b330598ed8d419dd251fdd1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455fd1228b395276315ca562e5a6c8efb278e54e28a3da689790fe071828eaa4
+oid sha256:f8e0dc53edfcdf4c7f9609c6f315392a635124566dbd7f3fad7166c47fb1d8c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6007655c906bb10bcfb17630dde1a3040722f923b4aadc11f955622461fff959
+oid sha256:28505173f92ecdd362339a246f12ab227649ef446fbaec229aeb7c09b000661c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f709279770bc215c0fffddff1a0e8eb71a398aa6cac41d545f1676127e298e
+oid sha256:4e4ecfc65ee3aa2116aaa3457452a1958ff70a50cbd7b48886189b98bdad0596
 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": 0.19639895856380463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28188865398167723,
+  "best_metric": 0.11933062225580215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5637773079633545,
   "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": 20.016,
       "eval_steps_per_second": 5.204,
       "step": 25
+    },
+    {
+      "epoch": 0.29316420014094435,
+      "grad_norm": 2.109933614730835,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4934,
+      "step": 26
+    },
+    {
+      "epoch": 0.3044397463002114,
+      "grad_norm": 0.022254984825849533,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0002,
+      "step": 27
+    },
+    {
+      "epoch": 0.3157152924594785,
+      "grad_norm": 0.05473516136407852,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.3269908386187456,
+      "grad_norm": 0.028082022443413734,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0002,
+      "step": 29
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 0.17534944415092468,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0022,
+      "step": 30
+    },
+    {
+      "epoch": 0.34954193093727975,
+      "grad_norm": 0.0239122174680233,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0003,
+      "step": 31
+    },
+    {
+      "epoch": 0.3608174770965469,
+      "grad_norm": 0.006109355948865414,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0001,
+      "step": 32
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.09741108864545822,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0004,
+      "step": 33
+    },
+    {
+      "epoch": 0.383368569415081,
+      "grad_norm": 0.12838013470172882,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0008,
+      "step": 34
+    },
+    {
+      "epoch": 0.39464411557434814,
+      "grad_norm": 0.004765228368341923,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.4059196617336152,
+      "grad_norm": 0.005345562938600779,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.41719520789288234,
+      "grad_norm": 0.002657412551343441,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.4284707540521494,
+      "grad_norm": 1.4992165565490723,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3407,
+      "step": 38
+    },
+    {
+      "epoch": 0.4397463002114165,
+      "grad_norm": 0.03090500459074974,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0004,
+      "step": 39
+    },
+    {
+      "epoch": 0.4510218463706836,
+      "grad_norm": 0.023092983290553093,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0003,
+      "step": 40
+    },
+    {
+      "epoch": 0.46229739252995067,
+      "grad_norm": 0.03314114734530449,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0004,
+      "step": 41
+    },
+    {
+      "epoch": 0.47357293868921774,
+      "grad_norm": 0.008977651596069336,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.01702510006725788,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0003,
+      "step": 43
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 0.02620372734963894,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 0.23229342699050903,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0032,
+      "step": 45
+    },
+    {
+      "epoch": 0.5186751233262861,
+      "grad_norm": 0.010418013669550419,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0002,
+      "step": 46
+    },
+    {
+      "epoch": 0.5299506694855532,
+      "grad_norm": 0.015945376828312874,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0003,
+      "step": 47
+    },
+    {
+      "epoch": 0.5412262156448203,
+      "grad_norm": 0.017018966376781464,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0003,
+      "step": 48
+    },
+    {
+      "epoch": 0.5525017618040874,
+      "grad_norm": 0.010695608332753181,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0002,
+      "step": 49
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "grad_norm": 0.004107787273824215,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "eval_loss": 0.11933062225580215,
+      "eval_runtime": 2.4961,
+      "eval_samples_per_second": 20.031,
+      "eval_steps_per_second": 5.208,
+      "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": 3.010152160391332e+17,
+  "total_flos": 6.02216935664386e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null