Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea915ed350288b9e53847205d854744c45ba764d0ee49803cee94d7224ac91f
+oid sha256:d17878c8eea4c53e4eae77f7fe83d8a3c7304f765ca05fcd54874393d9ba4ad7
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b7da45bb413218290387766443db8f13c9b2ec48ecbbd99605abe178dbc30c
+oid sha256:c7dfa2bc2620b339f066aa10d66c5e94d2c4236399fbd2f5618abd18513bb9f1
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:394d79bd9ac663f1c19723ed1141821ced6d884b8927b99c91f1b2d204771ecd
+oid sha256:cc6d17f5d3e6977f4a967ef3207a5dc14265e37caf420f5cf5b8d578a4d7e7ca
 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": 0.3726862370967865,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01886080724254998,
+  "best_metric": 0.3445923328399658,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03772161448509996,
   "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": 109.666,
       "eval_steps_per_second": 13.751,
       "step": 25
+    },
+    {
+      "epoch": 0.01961523953225198,
+      "grad_norm": 0.7956138849258423,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.3527,
+      "step": 26
+    },
+    {
+      "epoch": 0.02036967182195398,
+      "grad_norm": 0.8124170899391174,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2873,
+      "step": 27
+    },
+    {
+      "epoch": 0.021124104111655977,
+      "grad_norm": 0.878582239151001,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3622,
+      "step": 28
+    },
+    {
+      "epoch": 0.02187853640135798,
+      "grad_norm": 0.9804088473320007,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.3978,
+      "step": 29
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 0.8588770031929016,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2956,
+      "step": 30
+    },
+    {
+      "epoch": 0.023387400980761978,
+      "grad_norm": 0.783898115158081,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.301,
+      "step": 31
+    },
+    {
+      "epoch": 0.024141833270463976,
+      "grad_norm": 0.6420652270317078,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2105,
+      "step": 32
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 1.0156136751174927,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.3051,
+      "step": 33
+    },
+    {
+      "epoch": 0.025650697849867975,
+      "grad_norm": 0.7897914052009583,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.3269,
+      "step": 34
+    },
+    {
+      "epoch": 0.026405130139569973,
+      "grad_norm": 0.7197304368019104,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2039,
+      "step": 35
+    },
+    {
+      "epoch": 0.027159562429271974,
+      "grad_norm": 0.8324704170227051,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.3202,
+      "step": 36
+    },
+    {
+      "epoch": 0.02791399471897397,
+      "grad_norm": 0.8574749231338501,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2887,
+      "step": 37
+    },
+    {
+      "epoch": 0.028668427008675973,
+      "grad_norm": 1.0728785991668701,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4163,
+      "step": 38
+    },
+    {
+      "epoch": 0.02942285929837797,
+      "grad_norm": 0.9155979156494141,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2978,
+      "step": 39
+    },
+    {
+      "epoch": 0.03017729158807997,
+      "grad_norm": 0.8738413453102112,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3142,
+      "step": 40
+    },
+    {
+      "epoch": 0.03093172387778197,
+      "grad_norm": 0.89309161901474,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2975,
+      "step": 41
+    },
+    {
+      "epoch": 0.03168615616748397,
+      "grad_norm": 1.0845947265625,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3054,
+      "step": 42
+    },
+    {
+      "epoch": 0.03244058845718597,
+      "grad_norm": 0.9354661107063293,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3257,
+      "step": 43
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 1.173690676689148,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3655,
+      "step": 44
+    },
+    {
+      "epoch": 0.033949453036589965,
+      "grad_norm": 0.984697699546814,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2914,
+      "step": 45
+    },
+    {
+      "epoch": 0.03470388532629196,
+      "grad_norm": 1.103393316268921,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3537,
+      "step": 46
+    },
+    {
+      "epoch": 0.03545831761599397,
+      "grad_norm": 1.3742722272872925,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4048,
+      "step": 47
+    },
+    {
+      "epoch": 0.036212749905695965,
+      "grad_norm": 1.5404117107391357,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4235,
+      "step": 48
+    },
+    {
+      "epoch": 0.03696718219539796,
+      "grad_norm": 1.8669302463531494,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3197,
+      "step": 49
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "grad_norm": 3.114102602005005,
+      "learning_rate": 0.0,
+      "loss": 0.5909,
+      "step": 50
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "eval_loss": 0.3445923328399658,
+      "eval_runtime": 20.3648,
+      "eval_samples_per_second": 109.65,
+      "eval_steps_per_second": 13.749,
+      "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": 1033684525252608.0,
+  "total_flos": 1999744829227008.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null