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:b8043c981f48b2c803e1c9da184d2dbe9baa85b1e370ceaa65467ef4fd359eb1
+oid sha256:076f5e16e5ea45d412cfe38634be97068b6a241ed95b0ae3f03447feecb6fefe
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e43080d6b3e0bd5c547aafe512bf1b6cffa8f7564172590becb5037d907a5c
+oid sha256:7b3e8f7518b8e96e2dfa2da40be7ed44139fc47dfc7a73ae4fec878d834499c3
 size 147359892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e49d9dbe8d2652cfdd37880b83870f836a5d062b6df4debf28db8c7b2f7103e
+oid sha256:d742ac054e628c3472155bf73268ae6bdcbbbbca8cdb09a424c8ec52f4016863
 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": 1.246727466583252,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01585288522511097,
+  "best_metric": 1.1821939945220947,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03170577045022194,
   "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": 36.971,
       "eval_steps_per_second": 4.621,
       "step": 25
+    },
+    {
+      "epoch": 0.016487000634115408,
+      "grad_norm": 0.1652495563030243,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.2518,
+      "step": 26
+    },
+    {
+      "epoch": 0.017121116043119847,
+      "grad_norm": 0.14872929453849792,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.2467,
+      "step": 27
+    },
+    {
+      "epoch": 0.017755231452124286,
+      "grad_norm": 0.15020141005516052,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.1887,
+      "step": 28
+    },
+    {
+      "epoch": 0.018389346861128725,
+      "grad_norm": 0.1462440937757492,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.256,
+      "step": 29
+    },
+    {
+      "epoch": 0.019023462270133164,
+      "grad_norm": 0.14527584612369537,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.2337,
+      "step": 30
+    },
+    {
+      "epoch": 0.019657577679137603,
+      "grad_norm": 0.1435730755329132,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.2035,
+      "step": 31
+    },
+    {
+      "epoch": 0.020291693088142042,
+      "grad_norm": 0.13261650502681732,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.2267,
+      "step": 32
+    },
+    {
+      "epoch": 0.02092580849714648,
+      "grad_norm": 0.13555127382278442,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.1804,
+      "step": 33
+    },
+    {
+      "epoch": 0.02155992390615092,
+      "grad_norm": 0.13484609127044678,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.223,
+      "step": 34
+    },
+    {
+      "epoch": 0.02219403931515536,
+      "grad_norm": 0.13975246250629425,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.214,
+      "step": 35
+    },
+    {
+      "epoch": 0.022828154724159798,
+      "grad_norm": 0.1460408866405487,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.2044,
+      "step": 36
+    },
+    {
+      "epoch": 0.023462270133164237,
+      "grad_norm": 0.12898333370685577,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2115,
+      "step": 37
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 0.1304863840341568,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1808,
+      "step": 38
+    },
+    {
+      "epoch": 0.024730500951173115,
+      "grad_norm": 0.1284722238779068,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.1606,
+      "step": 39
+    },
+    {
+      "epoch": 0.025364616360177554,
+      "grad_norm": 0.14207273721694946,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1678,
+      "step": 40
+    },
+    {
+      "epoch": 0.02599873176918199,
+      "grad_norm": 0.1767612099647522,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2159,
+      "step": 41
+    },
+    {
+      "epoch": 0.02663284717818643,
+      "grad_norm": 0.28571370244026184,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.1637,
+      "step": 42
+    },
+    {
+      "epoch": 0.027266962587190868,
+      "grad_norm": 0.29650741815567017,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.1653,
+      "step": 43
+    },
+    {
+      "epoch": 0.027901077996195307,
+      "grad_norm": 0.3082343637943268,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.167,
+      "step": 44
+    },
+    {
+      "epoch": 0.028535193405199746,
+      "grad_norm": 0.3386911153793335,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.1402,
+      "step": 45
+    },
+    {
+      "epoch": 0.029169308814204185,
+      "grad_norm": 0.33259084820747375,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.1347,
+      "step": 46
+    },
+    {
+      "epoch": 0.029803424223208624,
+      "grad_norm": 0.3457428216934204,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.1041,
+      "step": 47
+    },
+    {
+      "epoch": 0.030437539632213063,
+      "grad_norm": 0.3795575201511383,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.0849,
+      "step": 48
+    },
+    {
+      "epoch": 0.031071655041217502,
+      "grad_norm": 0.3850218653678894,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1325,
+      "step": 49
+    },
+    {
+      "epoch": 0.03170577045022194,
+      "grad_norm": 0.41590115427970886,
+      "learning_rate": 0.0,
+      "loss": 1.1493,
+      "step": 50
+    },
+    {
+      "epoch": 0.03170577045022194,
+      "eval_loss": 1.1821939945220947,
+      "eval_runtime": 71.9855,
+      "eval_samples_per_second": 36.896,
+      "eval_steps_per_second": 4.612,
+      "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": 8272600262246400.0,
+  "total_flos": 1.5138858479910912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null