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:ea08fcb945e8337d5d4eb57f6a34b4303ec6ebe70c777637bdfbfc9e1476472d
+oid sha256:d0f63593151cc36c7e14e22ba97a79caa34ba498e4efddb3dbbbbce0c5b1781e
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705488b453632e51b8d26eb4a52646c62c34dfe55cb6c123e4113d4b11b231fa
+oid sha256:c9f14839ee669a449683ab70d2d9cca2c8829f7d444b59ff198d51f583ba2ee2
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd80e296e1c3c9a5add1cfdba9c92e1c8b86df5ed4bf9d30b4969b1177ec1ff
+oid sha256:e61a97895a589bb551eebe14ca96f8a6ddc0824bf17d3e639acd5e0a8bd0b276
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196a28fedfc247d54e324241d082e59d1d16544cf5417f3f82bb33d871b2d223
+oid sha256:8dc1887e8603f2b5aaee824815c12056e20544c807b80c6bd05ac5423e50de82
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf3a132631e3cb9b17daac81ffa2b3c61c25d3c6d77307b365b7a267f015193
+oid sha256:bf1d75fe770f1ecdcbea06301ac63dbf5a3bcf245093ce3e4b1e5c3c56fd9e88
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5feaae9bad220ce96453a5ff7cb9f9427cb0a242d6428cc9d26b243d415f079b
+oid sha256:fa1ac28e177c6a7d11040ec4fc04bc06983068c5af4d3e66eccb8554f52044e7
 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": 1.1732544898986816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2035623409669211,
+  "best_metric": 1.146162748336792,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4071246819338422,
   "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": 15.452,
       "eval_steps_per_second": 4.018,
       "step": 25
+    },
+    {
+      "epoch": 0.21170483460559797,
+      "grad_norm": 0.47239935398101807,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4729,
+      "step": 26
+    },
+    {
+      "epoch": 0.2198473282442748,
+      "grad_norm": 0.5448411703109741,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4152,
+      "step": 27
+    },
+    {
+      "epoch": 0.22798982188295167,
+      "grad_norm": 0.4144279658794403,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3087,
+      "step": 28
+    },
+    {
+      "epoch": 0.2361323155216285,
+      "grad_norm": 0.43465501070022583,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2266,
+      "step": 29
+    },
+    {
+      "epoch": 0.24427480916030533,
+      "grad_norm": 0.3278026282787323,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1868,
+      "step": 30
+    },
+    {
+      "epoch": 0.25241730279898217,
+      "grad_norm": 0.32642263174057007,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.178,
+      "step": 31
+    },
+    {
+      "epoch": 0.26055979643765903,
+      "grad_norm": 0.30465167760849,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2446,
+      "step": 32
+    },
+    {
+      "epoch": 0.2687022900763359,
+      "grad_norm": 0.3416752815246582,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0719,
+      "step": 33
+    },
+    {
+      "epoch": 0.2768447837150127,
+      "grad_norm": 0.34141701459884644,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0569,
+      "step": 34
+    },
+    {
+      "epoch": 0.28498727735368956,
+      "grad_norm": 0.417844295501709,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.022,
+      "step": 35
+    },
+    {
+      "epoch": 0.2931297709923664,
+      "grad_norm": 0.4493633806705475,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0213,
+      "step": 36
+    },
+    {
+      "epoch": 0.30127226463104323,
+      "grad_norm": 0.5586698055267334,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8832,
+      "step": 37
+    },
+    {
+      "epoch": 0.3094147582697201,
+      "grad_norm": 0.3204140067100525,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3685,
+      "step": 38
+    },
+    {
+      "epoch": 0.31755725190839695,
+      "grad_norm": 0.24755215644836426,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3834,
+      "step": 39
+    },
+    {
+      "epoch": 0.3256997455470738,
+      "grad_norm": 0.2518017888069153,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.3252,
+      "step": 40
+    },
+    {
+      "epoch": 0.3338422391857506,
+      "grad_norm": 0.2561423182487488,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2411,
+      "step": 41
+    },
+    {
+      "epoch": 0.3419847328244275,
+      "grad_norm": 0.2716136872768402,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2071,
+      "step": 42
+    },
+    {
+      "epoch": 0.35012722646310435,
+      "grad_norm": 0.2563495337963104,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1695,
+      "step": 43
+    },
+    {
+      "epoch": 0.35826972010178115,
+      "grad_norm": 0.2868095934391022,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2058,
+      "step": 44
+    },
+    {
+      "epoch": 0.366412213740458,
+      "grad_norm": 0.30007317662239075,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.125,
+      "step": 45
+    },
+    {
+      "epoch": 0.3745547073791349,
+      "grad_norm": 0.29985371232032776,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0624,
+      "step": 46
+    },
+    {
+      "epoch": 0.3826972010178117,
+      "grad_norm": 0.31994521617889404,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0312,
+      "step": 47
+    },
+    {
+      "epoch": 0.39083969465648855,
+      "grad_norm": 0.32543620467185974,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9651,
+      "step": 48
+    },
+    {
+      "epoch": 0.3989821882951654,
+      "grad_norm": 0.3547946512699127,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8825,
+      "step": 49
+    },
+    {
+      "epoch": 0.4071246819338422,
+      "grad_norm": 0.38324517011642456,
+      "learning_rate": 1e-05,
+      "loss": 0.8323,
+      "step": 50
+    },
+    {
+      "epoch": 0.4071246819338422,
+      "eval_loss": 1.146162748336792,
+      "eval_runtime": 3.2267,
+      "eval_samples_per_second": 15.496,
+      "eval_steps_per_second": 4.029,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null