Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47fd3b91457ae00c7a5c48c82ef50f0b570159280fd94f9e68c21a7155f4ca5e
+oid sha256:12cc8b66c1ac32ce6d497da3d1cd8d7543ba42d6c16d75c647ecdb14d3ccd800
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc6e3a9f41007899ee0674cc7b2213c3da0706f3bb3e474d6f5d5619933ce02
+oid sha256:566415624a2d02f8b78020d6fde21106444587670267ed72defeec83b573693c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d451fde37d6ebafadbf4c8ce9643dd4d01f57b5f1e3e59a56a4ec3e1a4a987d5
+oid sha256:44d09f587874641c076340fb98ed9d7f1717642b753304a27da10332efa83643
 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": 1.4482349157333374,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01886080724254998,
+  "best_metric": 1.4297280311584473,
+  "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": 23.17,
       "eval_steps_per_second": 2.905,
       "step": 25
+    },
+    {
+      "epoch": 0.01961523953225198,
+      "grad_norm": 9.728554725646973,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 5.9021,
+      "step": 26
+    },
+    {
+      "epoch": 0.02036967182195398,
+      "grad_norm": 9.531564712524414,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 6.1361,
+      "step": 27
+    },
+    {
+      "epoch": 0.021124104111655977,
+      "grad_norm": 9.711946487426758,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 6.3346,
+      "step": 28
+    },
+    {
+      "epoch": 0.02187853640135798,
+      "grad_norm": 9.515450477600098,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 6.0532,
+      "step": 29
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 9.936227798461914,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 5.9982,
+      "step": 30
+    },
+    {
+      "epoch": 0.023387400980761978,
+      "grad_norm": 8.55258560180664,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 5.5908,
+      "step": 31
+    },
+    {
+      "epoch": 0.024141833270463976,
+      "grad_norm": 9.07544994354248,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.5474,
+      "step": 32
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 9.403757095336914,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 6.2867,
+      "step": 33
+    },
+    {
+      "epoch": 0.025650697849867975,
+      "grad_norm": 9.350611686706543,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 5.4034,
+      "step": 34
+    },
+    {
+      "epoch": 0.026405130139569973,
+      "grad_norm": 8.95248031616211,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.6257,
+      "step": 35
+    },
+    {
+      "epoch": 0.027159562429271974,
+      "grad_norm": 9.22550106048584,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 5.3196,
+      "step": 36
+    },
+    {
+      "epoch": 0.02791399471897397,
+      "grad_norm": 8.956597328186035,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 5.1994,
+      "step": 37
+    },
+    {
+      "epoch": 0.028668427008675973,
+      "grad_norm": 10.275802612304688,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 5.0571,
+      "step": 38
+    },
+    {
+      "epoch": 0.02942285929837797,
+      "grad_norm": 10.483893394470215,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 6.1669,
+      "step": 39
+    },
+    {
+      "epoch": 0.03017729158807997,
+      "grad_norm": 12.084696769714355,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 5.6073,
+      "step": 40
+    },
+    {
+      "epoch": 0.03093172387778197,
+      "grad_norm": 11.926918029785156,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.2402,
+      "step": 41
+    },
+    {
+      "epoch": 0.03168615616748397,
+      "grad_norm": 10.83489990234375,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 5.0209,
+      "step": 42
+    },
+    {
+      "epoch": 0.03244058845718597,
+      "grad_norm": 10.564678192138672,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.8881,
+      "step": 43
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 11.461434364318848,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 5.0764,
+      "step": 44
+    },
+    {
+      "epoch": 0.033949453036589965,
+      "grad_norm": 11.702616691589355,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.5362,
+      "step": 45
+    },
+    {
+      "epoch": 0.03470388532629196,
+      "grad_norm": 13.87243366241455,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.3309,
+      "step": 46
+    },
+    {
+      "epoch": 0.03545831761599397,
+      "grad_norm": 14.594076156616211,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.9878,
+      "step": 47
+    },
+    {
+      "epoch": 0.036212749905695965,
+      "grad_norm": 16.554208755493164,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.7582,
+      "step": 48
+    },
+    {
+      "epoch": 0.03696718219539796,
+      "grad_norm": 21.001949310302734,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.6674,
+      "step": 49
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "grad_norm": 30.336759567260742,
+      "learning_rate": 0.0,
+      "loss": 3.3565,
+      "step": 50
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "eval_loss": 1.4297280311584473,
+      "eval_runtime": 96.4399,
+      "eval_samples_per_second": 23.154,
+      "eval_steps_per_second": 2.903,
+      "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": 1.824522461459251e+16,
+  "total_flos": 3.613269972693811e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null