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:a138fda6d3273bb16feba3fda586915cc4084633afeafbe9fadf3c4e05685584
+oid sha256:5bbb0c9ec7b4a48a2cc5f9cdf2841f17aefa20bcbc1560672f94e2a367690995
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e99eb88f3f0985d2ffeae2a8160554adf3dec97a1b5af1e2e73dc007e0d3842
+oid sha256:275aed93434c4ae21ef3f42ca92e9f15745ca3c0b3d697d388b4855433f33798
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e646b06b5993ebb098ccf81273aaefdb3ff9c7382b3ee0097560c78b8ddb4045
+oid sha256:13387680e14cb6ebe54af3644232d0b57e8e5f4b1a6cbe511d7650269beb57ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6964d7997b9d4de526f43bbcffa847f8e90a6dc16739dbb72b3bd723952265c
+oid sha256:4cb79ccb4f28702f64c235cb26814886d3c54edde121720d91bfc792d9e8a043
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bf7904874d724c811c04bdf73de041d0a4de1ef36e041e1d9b92c8e27504a4
+oid sha256:2f3cc60e1802c2fea12620871f8ed452fefa471f03a77569495a8f81fffc522b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4868a4bbf607bb612cec596283050203ee92a3c6cb3407212f5474f6d75f5a18
+oid sha256:eb126fe0ecf4bfd94f27002578a397aac8727a3e141baa8fc95359d7f14b7de0
 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": 0.3729974329471588,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7782101167315175,
+  "best_metric": 0.224692702293396,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.556420233463035,
   "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": 49.488,
       "eval_steps_per_second": 12.867,
       "step": 25
+    },
+    {
+      "epoch": 0.8093385214007782,
+      "grad_norm": 6.1687211990356445,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4149,
+      "step": 26
+    },
+    {
+      "epoch": 0.8404669260700389,
+      "grad_norm": 4.363428115844727,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3586,
+      "step": 27
+    },
+    {
+      "epoch": 0.8715953307392996,
+      "grad_norm": 2.75276255607605,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3073,
+      "step": 28
+    },
+    {
+      "epoch": 0.9027237354085603,
+      "grad_norm": 2.7687063217163086,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3206,
+      "step": 29
+    },
+    {
+      "epoch": 0.933852140077821,
+      "grad_norm": 3.324737787246704,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3263,
+      "step": 30
+    },
+    {
+      "epoch": 0.9649805447470817,
+      "grad_norm": 3.30027174949646,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3295,
+      "step": 31
+    },
+    {
+      "epoch": 0.9961089494163424,
+      "grad_norm": 4.5243635177612305,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.353,
+      "step": 32
+    },
+    {
+      "epoch": 1.027237354085603,
+      "grad_norm": 7.758679389953613,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.589,
+      "step": 33
+    },
+    {
+      "epoch": 1.0583657587548638,
+      "grad_norm": 3.8175582885742188,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2994,
+      "step": 34
+    },
+    {
+      "epoch": 1.0894941634241244,
+      "grad_norm": 2.687283992767334,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2773,
+      "step": 35
+    },
+    {
+      "epoch": 1.1206225680933852,
+      "grad_norm": 2.0834670066833496,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2474,
+      "step": 36
+    },
+    {
+      "epoch": 1.1517509727626458,
+      "grad_norm": 2.1409308910369873,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.2538,
+      "step": 37
+    },
+    {
+      "epoch": 1.1828793774319066,
+      "grad_norm": 2.018048048019409,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2499,
+      "step": 38
+    },
+    {
+      "epoch": 1.2140077821011672,
+      "grad_norm": 2.7065320014953613,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2588,
+      "step": 39
+    },
+    {
+      "epoch": 1.245136186770428,
+      "grad_norm": 3.8568458557128906,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2751,
+      "step": 40
+    },
+    {
+      "epoch": 1.2762645914396886,
+      "grad_norm": 1.778807520866394,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2381,
+      "step": 41
+    },
+    {
+      "epoch": 1.3073929961089494,
+      "grad_norm": 1.6081846952438354,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.234,
+      "step": 42
+    },
+    {
+      "epoch": 1.3385214007782102,
+      "grad_norm": 1.3087798357009888,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2232,
+      "step": 43
+    },
+    {
+      "epoch": 1.3696498054474708,
+      "grad_norm": 1.1397979259490967,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2191,
+      "step": 44
+    },
+    {
+      "epoch": 1.4007782101167314,
+      "grad_norm": 1.1176964044570923,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2301,
+      "step": 45
+    },
+    {
+      "epoch": 1.4319066147859922,
+      "grad_norm": 2.2158350944519043,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2631,
+      "step": 46
+    },
+    {
+      "epoch": 1.463035019455253,
+      "grad_norm": 2.2761166095733643,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.248,
+      "step": 47
+    },
+    {
+      "epoch": 1.4941634241245136,
+      "grad_norm": 4.002376556396484,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2715,
+      "step": 48
+    },
+    {
+      "epoch": 1.5252918287937742,
+      "grad_norm": 1.4426534175872803,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2277,
+      "step": 49
+    },
+    {
+      "epoch": 1.556420233463035,
+      "grad_norm": 1.8565995693206787,
+      "learning_rate": 1e-05,
+      "loss": 0.2096,
+      "step": 50
+    },
+    {
+      "epoch": 1.556420233463035,
+      "eval_loss": 0.224692702293396,
+      "eval_runtime": 1.0263,
+      "eval_samples_per_second": 48.717,
+      "eval_steps_per_second": 12.666,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null