Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220d3df0155d4360d115f82b4c67571317a5592ba64cffe9a418968ae22c5811
+oid sha256:761b01606509a9fa33d9fca16b5dcacd70a269cf8ef2f0c634ab395c4309490e
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5533b0764001815b7df165a1d23a88b663009ddc67d0c370a3a0ec6e0e6879
+oid sha256:4b26cbd1cec4cabc527f5b0b4535a2212ad27ec84d6969a9abcdd9d8309a7cc2
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334d877cb53b63f40feaf798ed2d27d51fa607b0b40673b82657ea0addb7517c
+oid sha256:8a9dc045b9bc5a565e6dfde3fdb06b0d620422165417c90d17c180980214fd9c
 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": 0.37303784489631653,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01886080724254998,
+  "best_metric": 0.34442776441574097,
+  "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": 110.003,
       "eval_steps_per_second": 13.794,
       "step": 25
+    },
+    {
+      "epoch": 0.01961523953225198,
+      "grad_norm": 0.7916195392608643,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.3521,
+      "step": 26
+    },
+    {
+      "epoch": 0.02036967182195398,
+      "grad_norm": 0.8140760660171509,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2878,
+      "step": 27
+    },
+    {
+      "epoch": 0.021124104111655977,
+      "grad_norm": 0.8776665925979614,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3625,
+      "step": 28
+    },
+    {
+      "epoch": 0.02187853640135798,
+      "grad_norm": 0.9702516794204712,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.3975,
+      "step": 29
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 0.8504037261009216,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.299,
+      "step": 30
+    },
+    {
+      "epoch": 0.023387400980761978,
+      "grad_norm": 0.7773805260658264,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.3011,
+      "step": 31
+    },
+    {
+      "epoch": 0.024141833270463976,
+      "grad_norm": 0.67751145362854,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2111,
+      "step": 32
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 0.9894010424613953,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.3064,
+      "step": 33
+    },
+    {
+      "epoch": 0.025650697849867975,
+      "grad_norm": 0.7872379422187805,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.327,
+      "step": 34
+    },
+    {
+      "epoch": 0.026405130139569973,
+      "grad_norm": 0.714971125125885,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2041,
+      "step": 35
+    },
+    {
+      "epoch": 0.027159562429271974,
+      "grad_norm": 0.8356368541717529,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.3212,
+      "step": 36
+    },
+    {
+      "epoch": 0.02791399471897397,
+      "grad_norm": 0.8638647794723511,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2885,
+      "step": 37
+    },
+    {
+      "epoch": 0.028668427008675973,
+      "grad_norm": 1.0834510326385498,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4168,
+      "step": 38
+    },
+    {
+      "epoch": 0.02942285929837797,
+      "grad_norm": 0.9180977940559387,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2998,
+      "step": 39
+    },
+    {
+      "epoch": 0.03017729158807997,
+      "grad_norm": 0.8694742918014526,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3141,
+      "step": 40
+    },
+    {
+      "epoch": 0.03093172387778197,
+      "grad_norm": 0.8900282382965088,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2984,
+      "step": 41
+    },
+    {
+      "epoch": 0.03168615616748397,
+      "grad_norm": 1.0807785987854004,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3059,
+      "step": 42
+    },
+    {
+      "epoch": 0.03244058845718597,
+      "grad_norm": 0.9371557235717773,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3262,
+      "step": 43
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 1.1675786972045898,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3664,
+      "step": 44
+    },
+    {
+      "epoch": 0.033949453036589965,
+      "grad_norm": 0.9846644997596741,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.292,
+      "step": 45
+    },
+    {
+      "epoch": 0.03470388532629196,
+      "grad_norm": 1.1046561002731323,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3549,
+      "step": 46
+    },
+    {
+      "epoch": 0.03545831761599397,
+      "grad_norm": 1.3664727210998535,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4048,
+      "step": 47
+    },
+    {
+      "epoch": 0.036212749905695965,
+      "grad_norm": 1.5488460063934326,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4229,
+      "step": 48
+    },
+    {
+      "epoch": 0.03696718219539796,
+      "grad_norm": 1.8980265855789185,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3193,
+      "step": 49
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "grad_norm": 3.1977779865264893,
+      "learning_rate": 0.0,
+      "loss": 0.5885,
+      "step": 50
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "eval_loss": 0.34442776441574097,
+      "eval_runtime": 20.2984,
+      "eval_samples_per_second": 110.009,
+      "eval_steps_per_second": 13.794,
+      "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