Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238c74fd1d5b9dc8b97396b62fdbddaf4a289c24d2bbaa99e0668e43ff5c58a1
+oid sha256:0c0ba1399881edebe9e1762457b8a282076827632b12f237ee0fb747b06bcb34
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81af94569e4dac39bbfd660b19e6d9cb7ec7584b02046870926d5f1b11ca2e36
+oid sha256:ac05179301785010edd1ca1343ef9ddcc30eed954df21b27e81567a35478ebe1
 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": 0.22036908566951752,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10188487009679063,
+  "best_metric": 0.1133032962679863,
+  "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": 10.29,
       "eval_steps_per_second": 2.675,
       "step": 25
+    },
+    {
+      "epoch": 0.10596026490066225,
+      "grad_norm": 14.292779922485352,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.1882,
+      "step": 26
+    },
+    {
+      "epoch": 0.11003565970453388,
+      "grad_norm": 12.268036842346191,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.3339,
+      "step": 27
+    },
+    {
+      "epoch": 0.1141110545084055,
+      "grad_norm": 7.059298038482666,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9095,
+      "step": 28
+    },
+    {
+      "epoch": 0.11818644931227713,
+      "grad_norm": 6.473829746246338,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.2704,
+      "step": 29
+    },
+    {
+      "epoch": 0.12226184411614875,
+      "grad_norm": 7.172585487365723,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0769,
+      "step": 30
+    },
+    {
+      "epoch": 0.12633723892002038,
+      "grad_norm": 13.269759178161621,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.7104,
+      "step": 31
+    },
+    {
+      "epoch": 0.130412633723892,
+      "grad_norm": 45.20688247680664,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.5883,
+      "step": 32
+    },
+    {
+      "epoch": 0.13448802852776362,
+      "grad_norm": 7.162100791931152,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.2444,
+      "step": 33
+    },
+    {
+      "epoch": 0.13856342333163527,
+      "grad_norm": 7.486405849456787,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.2902,
+      "step": 34
+    },
+    {
+      "epoch": 0.14263881813550688,
+      "grad_norm": 7.402297019958496,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.2322,
+      "step": 35
+    },
+    {
+      "epoch": 0.1467142129393785,
+      "grad_norm": 8.339662551879883,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.2498,
+      "step": 36
+    },
+    {
+      "epoch": 0.15078960774325012,
+      "grad_norm": 6.3191704750061035,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.8306,
+      "step": 37
+    },
+    {
+      "epoch": 0.15486500254712177,
+      "grad_norm": 16.101682662963867,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.3577,
+      "step": 38
+    },
+    {
+      "epoch": 0.15894039735099338,
+      "grad_norm": 3.658964157104492,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.0985,
+      "step": 39
+    },
+    {
+      "epoch": 0.163015792154865,
+      "grad_norm": 3.7097461223602295,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.4058,
+      "step": 40
+    },
+    {
+      "epoch": 0.16709118695873662,
+      "grad_norm": 3.5799686908721924,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.4198,
+      "step": 41
+    },
+    {
+      "epoch": 0.17116658176260827,
+      "grad_norm": 5.910707950592041,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2987,
+      "step": 42
+    },
+    {
+      "epoch": 0.17524197656647988,
+      "grad_norm": 7.766164302825928,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3937,
+      "step": 43
+    },
+    {
+      "epoch": 0.1793173713703515,
+      "grad_norm": 12.289716720581055,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.527,
+      "step": 44
+    },
+    {
+      "epoch": 0.18339276617422312,
+      "grad_norm": 26.6347713470459,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.4737,
+      "step": 45
+    },
+    {
+      "epoch": 0.18746816097809477,
+      "grad_norm": 8.661320686340332,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.6673,
+      "step": 46
+    },
+    {
+      "epoch": 0.19154355578196638,
+      "grad_norm": 5.6989240646362305,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.6876,
+      "step": 47
+    },
+    {
+      "epoch": 0.195618950585838,
+      "grad_norm": 6.910922527313232,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6955,
+      "step": 48
+    },
+    {
+      "epoch": 0.19969434538970962,
+      "grad_norm": 9.750502586364746,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.8129,
+      "step": 49
+    },
+    {
+      "epoch": 0.20376974019358127,
+      "grad_norm": 8.881779670715332,
+      "learning_rate": 1e-05,
+      "loss": 1.5954,
+      "step": 50
+    },
+    {
+      "epoch": 0.20376974019358127,
+      "eval_loss": 0.1133032962679863,
+      "eval_runtime": 4.8522,
+      "eval_samples_per_second": 10.305,
+      "eval_steps_per_second": 2.679,
+      "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