Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f5cc248d97fe850356611a5099ccb51da60238bcd786e39cdbb6fa2a5384d1
+oid sha256:c7743c289f1b8086a918c3df5a1c2b8806809bfb4b8805e2e369ada3c792692e
 size 224224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8050ee37e85a9cb08a98871d075aee5f0163bc9536562475935a6ae04d5a76d3
+oid sha256:332501e7b286391141c125b28bb014f3a65dc6054aec01f3606dffbfed51e6b2
 size 458278

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e9f85a66e6fac5105027b1edad344f0154b57bd2a796c6438d16f90d42fab0
+oid sha256:56c9d102e7c59e99bf627a4a69a071908b93a94d73a3136dd88bbe2888ee9115
 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": 10.35084342956543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006898454746136865,
+  "best_metric": 10.337969779968262,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01379690949227373,
   "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": 605.461,
       "eval_steps_per_second": 75.683,
       "step": 25
+    },
+    {
+      "epoch": 0.00717439293598234,
+      "grad_norm": 1.611414909362793,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 41.407,
+      "step": 26
+    },
+    {
+      "epoch": 0.0074503311258278145,
+      "grad_norm": 1.6409019231796265,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 41.3963,
+      "step": 27
+    },
+    {
+      "epoch": 0.00772626931567329,
+      "grad_norm": 1.5699679851531982,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 41.3951,
+      "step": 28
+    },
+    {
+      "epoch": 0.008002207505518763,
+      "grad_norm": 1.6396316289901733,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 41.3885,
+      "step": 29
+    },
+    {
+      "epoch": 0.008278145695364239,
+      "grad_norm": 1.6167317628860474,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 41.3895,
+      "step": 30
+    },
+    {
+      "epoch": 0.008554083885209713,
+      "grad_norm": 1.7325376272201538,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 41.3668,
+      "step": 31
+    },
+    {
+      "epoch": 0.008830022075055188,
+      "grad_norm": 1.465965986251831,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 41.372,
+      "step": 32
+    },
+    {
+      "epoch": 0.009105960264900662,
+      "grad_norm": 1.48931884765625,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 41.3638,
+      "step": 33
+    },
+    {
+      "epoch": 0.009381898454746136,
+      "grad_norm": 1.526735782623291,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 41.3626,
+      "step": 34
+    },
+    {
+      "epoch": 0.009657836644591612,
+      "grad_norm": 1.6789668798446655,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 41.3546,
+      "step": 35
+    },
+    {
+      "epoch": 0.009933774834437087,
+      "grad_norm": 1.4913084506988525,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 41.347,
+      "step": 36
+    },
+    {
+      "epoch": 0.01020971302428256,
+      "grad_norm": 1.4911720752716064,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 41.3674,
+      "step": 37
+    },
+    {
+      "epoch": 0.010485651214128035,
+      "grad_norm": 1.5095301866531372,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 41.3685,
+      "step": 38
+    },
+    {
+      "epoch": 0.01076158940397351,
+      "grad_norm": 1.401106357574463,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 41.374,
+      "step": 39
+    },
+    {
+      "epoch": 0.011037527593818985,
+      "grad_norm": 1.4282902479171753,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 41.3633,
+      "step": 40
+    },
+    {
+      "epoch": 0.01131346578366446,
+      "grad_norm": 1.5233620405197144,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 41.3372,
+      "step": 41
+    },
+    {
+      "epoch": 0.011589403973509934,
+      "grad_norm": 1.521764874458313,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 41.3368,
+      "step": 42
+    },
+    {
+      "epoch": 0.011865342163355408,
+      "grad_norm": 1.5868169069290161,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 41.3614,
+      "step": 43
+    },
+    {
+      "epoch": 0.012141280353200883,
+      "grad_norm": 1.4296141862869263,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 41.3517,
+      "step": 44
+    },
+    {
+      "epoch": 0.012417218543046357,
+      "grad_norm": 1.431632161140442,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 41.3548,
+      "step": 45
+    },
+    {
+      "epoch": 0.012693156732891833,
+      "grad_norm": 1.5977118015289307,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 41.3662,
+      "step": 46
+    },
+    {
+      "epoch": 0.012969094922737307,
+      "grad_norm": 1.4877045154571533,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 41.3298,
+      "step": 47
+    },
+    {
+      "epoch": 0.013245033112582781,
+      "grad_norm": 1.7337113618850708,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 41.3669,
+      "step": 48
+    },
+    {
+      "epoch": 0.013520971302428256,
+      "grad_norm": 1.775262475013733,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 41.3547,
+      "step": 49
+    },
+    {
+      "epoch": 0.01379690949227373,
+      "grad_norm": 2.36063289642334,
+      "learning_rate": 0.0,
+      "loss": 41.3447,
+      "step": 50
+    },
+    {
+      "epoch": 0.01379690949227373,
+      "eval_loss": 10.337969779968262,
+      "eval_runtime": 10.0528,
+      "eval_samples_per_second": 607.196,
+      "eval_steps_per_second": 75.9,
+      "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": 5370229555200.0,
+  "total_flos": 8726623027200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null