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:b6e8a65c7d5cc151bacfbf583642df01845bfe82dfbe93052ccad16010ae916f
+oid sha256:b7782ec1a77b44cbf224c4e1b34119e2e3dc1926bde424e7e20d7ce17ce90ccf
 size 3152280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acea168fc62821108f9efcc27794a37de24bf55792fa08771e400bffda94c8b7
+oid sha256:8a4f751aebd838f25e5e0a008abda5ef489319f42a23a72cb4a93edc137b8efd
 size 1655994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0275bb38724621a13fc024988102341acdf93d64fab7fe318413474a54d8a9b2
+oid sha256:daaf75ae9600bcdd74114dbd260d462460d9649c1401a41b3bce0fb870d987a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.293178081512451,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014188422247446084,
+  "best_metric": 5.875912666320801,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028376844494892167,
   "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": 504.784,
       "eval_steps_per_second": 63.098,
       "step": 25
+    },
+    {
+      "epoch": 0.014755959137343927,
+      "grad_norm": 14289.7685546875,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 25.5509,
+      "step": 26
+    },
+    {
+      "epoch": 0.01532349602724177,
+      "grad_norm": 9686.123046875,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 24.924,
+      "step": 27
+    },
+    {
+      "epoch": 0.015891032917139614,
+      "grad_norm": 14150.8583984375,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 25.4809,
+      "step": 28
+    },
+    {
+      "epoch": 0.016458569807037457,
+      "grad_norm": 9053.201171875,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 25.4006,
+      "step": 29
+    },
+    {
+      "epoch": 0.0170261066969353,
+      "grad_norm": 9801.84765625,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 24.2856,
+      "step": 30
+    },
+    {
+      "epoch": 0.017593643586833144,
+      "grad_norm": 10064.693359375,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 23.7726,
+      "step": 31
+    },
+    {
+      "epoch": 0.018161180476730987,
+      "grad_norm": 8841.45703125,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 23.7834,
+      "step": 32
+    },
+    {
+      "epoch": 0.01872871736662883,
+      "grad_norm": 12932.470703125,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 24.4075,
+      "step": 33
+    },
+    {
+      "epoch": 0.019296254256526674,
+      "grad_norm": 14299.3837890625,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 24.5745,
+      "step": 34
+    },
+    {
+      "epoch": 0.019863791146424517,
+      "grad_norm": 10526.33984375,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 24.5074,
+      "step": 35
+    },
+    {
+      "epoch": 0.02043132803632236,
+      "grad_norm": 11805.779296875,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 23.6392,
+      "step": 36
+    },
+    {
+      "epoch": 0.020998864926220204,
+      "grad_norm": 10636.3212890625,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 24.116,
+      "step": 37
+    },
+    {
+      "epoch": 0.021566401816118047,
+      "grad_norm": 10777.1533203125,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 24.2741,
+      "step": 38
+    },
+    {
+      "epoch": 0.02213393870601589,
+      "grad_norm": 14647.6123046875,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 23.7515,
+      "step": 39
+    },
+    {
+      "epoch": 0.022701475595913734,
+      "grad_norm": 11201.9638671875,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 23.7649,
+      "step": 40
+    },
+    {
+      "epoch": 0.023269012485811577,
+      "grad_norm": 11670.091796875,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 23.0908,
+      "step": 41
+    },
+    {
+      "epoch": 0.02383654937570942,
+      "grad_norm": 11383.5146484375,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 23.4959,
+      "step": 42
+    },
+    {
+      "epoch": 0.024404086265607264,
+      "grad_norm": 13790.1787109375,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 22.942,
+      "step": 43
+    },
+    {
+      "epoch": 0.024971623155505107,
+      "grad_norm": 10936.7509765625,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 24.7202,
+      "step": 44
+    },
+    {
+      "epoch": 0.02553916004540295,
+      "grad_norm": 10467.732421875,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 23.336,
+      "step": 45
+    },
+    {
+      "epoch": 0.026106696935300794,
+      "grad_norm": 13301.62109375,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 23.3341,
+      "step": 46
+    },
+    {
+      "epoch": 0.026674233825198637,
+      "grad_norm": 12683.9287109375,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 23.277,
+      "step": 47
+    },
+    {
+      "epoch": 0.02724177071509648,
+      "grad_norm": 12008.130859375,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 23.0534,
+      "step": 48
+    },
+    {
+      "epoch": 0.027809307604994324,
+      "grad_norm": 13983.6748046875,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 24.6009,
+      "step": 49
+    },
+    {
+      "epoch": 0.028376844494892167,
+      "grad_norm": 13639.6083984375,
+      "learning_rate": 0.0,
+      "loss": 22.5073,
+      "step": 50
+    },
+    {
+      "epoch": 0.028376844494892167,
+      "eval_loss": 5.875912666320801,
+      "eval_runtime": 5.8904,
+      "eval_samples_per_second": 503.868,
+      "eval_steps_per_second": 62.984,
+      "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": 29781034795008.0,
+  "total_flos": 50462308958208.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null