Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5033ce9456051eb49ea347692c3d509efbebaf2a6d23aeb2fcdce44a077f8b61
+oid sha256:2ad07ac709ff3da5c43b3aca3201d5b2505b80d367de90f2e3a055d901612bd4
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5d9ce27f953e3db774ee7f463d6f71c0bc9daf5f0c17e5e48a61875906d34b
+oid sha256:079fa32db54c6464060220fb7738d68b1c39d17b44e853b13a8820232f19467d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1cc34234e2fa41abea50bda3ffdf4653c3e3b921eb986f86e84aa48c6063eb
+oid sha256:c8b915206690dcdffeb1f6267f784a521639fbd9e17998afb88b2d8803a09b2c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fce5358f4defef97fd020339af1efa7d07aa7dbf853e73136237c0655e644ad
+oid sha256:771479d27a48888cd0f003c141a5fc046877ac9a6b946c957e0d41c4b5e0434a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95575dd4d0b2bef1cb53fd0f709d2abe25f52ccc68d5337c211b2282dd7f37da
+oid sha256:d6856723a64ed5031893d6c345ede314a63122bbfb5e6284692f76e557cb41e9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a8b32b62f34c0032fd5b5a49605c9404cfd19be7cc1d4f6010add12e56a923
+oid sha256:7c09f08f2d554d609cd5286a14fe91d93e2ab7bd0bb69dccd138822e5be92adb
 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": 0.20966766774654388,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10188487009679063,
+  "best_metric": 0.10608885437250137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.20376974019358127,
   "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": 10.221,
       "eval_steps_per_second": 2.658,
       "step": 25
+    },
+    {
+      "epoch": 0.10596026490066225,
+      "grad_norm": 14.012548446655273,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.1354,
+      "step": 26
+    },
+    {
+      "epoch": 0.11003565970453388,
+      "grad_norm": 12.140026092529297,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.2918,
+      "step": 27
+    },
+    {
+      "epoch": 0.1141110545084055,
+      "grad_norm": 7.307669639587402,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.8834,
+      "step": 28
+    },
+    {
+      "epoch": 0.11818644931227713,
+      "grad_norm": 6.482525825500488,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.2235,
+      "step": 29
+    },
+    {
+      "epoch": 0.12226184411614875,
+      "grad_norm": 6.61669921875,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0302,
+      "step": 30
+    },
+    {
+      "epoch": 0.12633723892002038,
+      "grad_norm": 14.014857292175293,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.6282,
+      "step": 31
+    },
+    {
+      "epoch": 0.130412633723892,
+      "grad_norm": 44.7835693359375,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3638,
+      "step": 32
+    },
+    {
+      "epoch": 0.13448802852776362,
+      "grad_norm": 7.154061317443848,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.2156,
+      "step": 33
+    },
+    {
+      "epoch": 0.13856342333163527,
+      "grad_norm": 7.64763879776001,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.2094,
+      "step": 34
+    },
+    {
+      "epoch": 0.14263881813550688,
+      "grad_norm": 8.679080963134766,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.1754,
+      "step": 35
+    },
+    {
+      "epoch": 0.1467142129393785,
+      "grad_norm": 8.896808624267578,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.2206,
+      "step": 36
+    },
+    {
+      "epoch": 0.15078960774325012,
+      "grad_norm": 6.064028263092041,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.7617,
+      "step": 37
+    },
+    {
+      "epoch": 0.15486500254712177,
+      "grad_norm": 14.632406234741211,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.3032,
+      "step": 38
+    },
+    {
+      "epoch": 0.15894039735099338,
+      "grad_norm": 3.615339994430542,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.0701,
+      "step": 39
+    },
+    {
+      "epoch": 0.163015792154865,
+      "grad_norm": 3.444420099258423,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.3679,
+      "step": 40
+    },
+    {
+      "epoch": 0.16709118695873662,
+      "grad_norm": 3.5726735591888428,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.3856,
+      "step": 41
+    },
+    {
+      "epoch": 0.17116658176260827,
+      "grad_norm": 5.774728298187256,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2382,
+      "step": 42
+    },
+    {
+      "epoch": 0.17524197656647988,
+      "grad_norm": 7.59352970123291,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3525,
+      "step": 43
+    },
+    {
+      "epoch": 0.1793173713703515,
+      "grad_norm": 12.746742248535156,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.4931,
+      "step": 44
+    },
+    {
+      "epoch": 0.18339276617422312,
+      "grad_norm": 32.45207214355469,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.3111,
+      "step": 45
+    },
+    {
+      "epoch": 0.18746816097809477,
+      "grad_norm": 9.602239608764648,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5958,
+      "step": 46
+    },
+    {
+      "epoch": 0.19154355578196638,
+      "grad_norm": 5.826984882354736,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.6729,
+      "step": 47
+    },
+    {
+      "epoch": 0.195618950585838,
+      "grad_norm": 8.131805419921875,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.7031,
+      "step": 48
+    },
+    {
+      "epoch": 0.19969434538970962,
+      "grad_norm": 8.51675033569336,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.7887,
+      "step": 49
+    },
+    {
+      "epoch": 0.20376974019358127,
+      "grad_norm": 10.093128204345703,
+      "learning_rate": 1e-05,
+      "loss": 1.5667,
+      "step": 50
+    },
+    {
+      "epoch": 0.20376974019358127,
+      "eval_loss": 0.10608885437250137,
+      "eval_runtime": 4.8603,
+      "eval_samples_per_second": 10.287,
+      "eval_steps_per_second": 2.675,
+      "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": 4.1382580590739456e+17,
+  "total_flos": 8.238716314986742e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null