Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923f533186de0119e76bf657e15aad0414f3e9037dba8e44efdf5b1e62825458
+oid sha256:981feb8047778ae68296495b132b548ba7b93f00f25f85fda6fb3f5f5df89e9c
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8571739d060b0e45f1734cddb275dd06a8921cbf8b851fbc641ea85f48cd9461
+oid sha256:0d5467144f5fbb07bcf61f8ee3af1f327411774318ecbe1ae612df342905fdfa
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14d5a39c17c42f3371fba2037f75d03f7453e378a313472dcba91cb6ec4b212c
+oid sha256:62ac16c95319cfe9cb0955b122f12e1893eb0b53d40865c8350cee4e36224573
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0094d530a1519fe8545d18012862a0412da22be843396dc0cdf84b71059f7020
+oid sha256:f69d56bf56c7d442e99b2170efc340d1de6a5cf88eb06548f6e0afe9bed7cc14
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf173a743bf84648a698e4b59e2197b91920f9745af67bcc65d178fc7a5e9f8
+oid sha256:c62937014df33eaf7ef381a46387ba06d57ac5e085a90dfca6039f870ca94c24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8170de44fd577cd7a292309d3b8f615b8f29122784be803bf452f81562b38b
+oid sha256:7d5e2259d91f0b5b3e5f2b9f1108f486e81ee4923b969afb6d8114e057b7c9f3
 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": 0.23994900286197662,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15168752370117558,
+  "best_metric": 0.22630853950977325,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.30337504740235116,
   "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": 12.351,
       "eval_steps_per_second": 3.211,
       "step": 25
+    },
+    {
+      "epoch": 0.1577550246492226,
+      "grad_norm": 0.7292701005935669,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1866,
+      "step": 26
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.46785980463027954,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3407,
+      "step": 27
+    },
+    {
+      "epoch": 0.16989002654531665,
+      "grad_norm": 0.39624592661857605,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2456,
+      "step": 28
+    },
+    {
+      "epoch": 0.17595752749336366,
+      "grad_norm": 0.5996044874191284,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2868,
+      "step": 29
+    },
+    {
+      "epoch": 0.1820250284414107,
+      "grad_norm": 0.6050768494606018,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3026,
+      "step": 30
+    },
+    {
+      "epoch": 0.18809252938945772,
+      "grad_norm": 0.5520008206367493,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3086,
+      "step": 31
+    },
+    {
+      "epoch": 0.19416003033750473,
+      "grad_norm": 0.5303773283958435,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.342,
+      "step": 32
+    },
+    {
+      "epoch": 0.20022753128555176,
+      "grad_norm": 0.6441546678543091,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3525,
+      "step": 33
+    },
+    {
+      "epoch": 0.2062950322335988,
+      "grad_norm": 0.5183490514755249,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2628,
+      "step": 34
+    },
+    {
+      "epoch": 0.2123625331816458,
+      "grad_norm": 0.5794525146484375,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2773,
+      "step": 35
+    },
+    {
+      "epoch": 0.21843003412969283,
+      "grad_norm": 1.2633119821548462,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3883,
+      "step": 36
+    },
+    {
+      "epoch": 0.22449753507773987,
+      "grad_norm": 2.0984978675842285,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.422,
+      "step": 37
+    },
+    {
+      "epoch": 0.23056503602578687,
+      "grad_norm": 0.7109975814819336,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1681,
+      "step": 38
+    },
+    {
+      "epoch": 0.2366325369738339,
+      "grad_norm": 0.4398191273212433,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2961,
+      "step": 39
+    },
+    {
+      "epoch": 0.2427000379218809,
+      "grad_norm": 0.2695257365703583,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2445,
+      "step": 40
+    },
+    {
+      "epoch": 0.24876753886992795,
+      "grad_norm": 0.4018322825431824,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2565,
+      "step": 41
+    },
+    {
+      "epoch": 0.25483503981797495,
+      "grad_norm": 0.44669589400291443,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3254,
+      "step": 42
+    },
+    {
+      "epoch": 0.260902540766022,
+      "grad_norm": 0.3876776397228241,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2492,
+      "step": 43
+    },
+    {
+      "epoch": 0.266970041714069,
+      "grad_norm": 0.44162696599960327,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2914,
+      "step": 44
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.401747465133667,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2792,
+      "step": 45
+    },
+    {
+      "epoch": 0.2791050436101631,
+      "grad_norm": 0.3714073598384857,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.296,
+      "step": 46
+    },
+    {
+      "epoch": 0.28517254455821006,
+      "grad_norm": 0.39308562874794006,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2146,
+      "step": 47
+    },
+    {
+      "epoch": 0.2912400455062571,
+      "grad_norm": 0.49879807233810425,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2932,
+      "step": 48
+    },
+    {
+      "epoch": 0.29730754645430413,
+      "grad_norm": 0.8610867261886597,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3741,
+      "step": 49
+    },
+    {
+      "epoch": 0.30337504740235116,
+      "grad_norm": 0.6880888342857361,
+      "learning_rate": 1e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 0.30337504740235116,
+      "eval_loss": 0.22630853950977325,
+      "eval_runtime": 4.0151,
+      "eval_samples_per_second": 12.453,
+      "eval_steps_per_second": 3.238,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null