Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db84b01ed5cc73e324c0eafb8beda3cf8c5fbbef8ada6f459e22b3c9395b69a0
+oid sha256:34ca463bbf7e4cfbb80933541a1a9940e7d45fc728c3b4ee90eb03209a37de64
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc6d66f743b8cb41366d9a4276cd6a3dcfe9414daae246132c2eb38b552eb26
+oid sha256:ca5b4b523dacb9b3df9b59a05e5abef9b6c193ffcecb3b335f466e020eb2dcab
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ad85418c126fdeb377fd9de8d3ac567da48fe7c9bcc3e518597457527160e9
+oid sha256:78f9a3484f58e7dfed81e76a7f50059b1853d5679c09ba3d9678f6bb748f249a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405f7b532d333ab7fb02890cf58d2bc50f7e2cda7c9769f728bbdd7f58e4069a
+oid sha256:34bebae8dbb4044169aedad702183ea2a5f7688635af093bea630f24dc71f1ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3121320009231567,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.837696335078534,
+  "epoch": 1.0052356020942408,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,146 @@
       "eval_samples_per_second": 7.376,
       "eval_steps_per_second": 1.849,
       "step": 100
+    },
+    {
+      "epoch": 0.8460732984293193,
+      "grad_norm": 0.24377289414405823,
+      "learning_rate": 1.4365096974841108e-05,
+      "loss": 1.2426,
+      "step": 101
+    },
+    {
+      "epoch": 0.8544502617801047,
+      "grad_norm": 0.27847498655319214,
+      "learning_rate": 1.2925392288022298e-05,
+      "loss": 1.2593,
+      "step": 102
+    },
+    {
+      "epoch": 0.86282722513089,
+      "grad_norm": 0.2640259563922882,
+      "learning_rate": 1.1556706900218572e-05,
+      "loss": 1.2703,
+      "step": 103
+    },
+    {
+      "epoch": 0.8712041884816754,
+      "grad_norm": 0.2538398504257202,
+      "learning_rate": 1.026015713086418e-05,
+      "loss": 1.2544,
+      "step": 104
+    },
+    {
+      "epoch": 0.8795811518324608,
+      "grad_norm": 0.244331493973732,
+      "learning_rate": 9.036800464548157e-06,
+      "loss": 1.3047,
+      "step": 105
+    },
+    {
+      "epoch": 0.8879581151832461,
+      "grad_norm": 0.26120704412460327,
+      "learning_rate": 7.887634688515e-06,
+      "loss": 1.2688,
+      "step": 106
+    },
+    {
+      "epoch": 0.8963350785340314,
+      "grad_norm": 0.2646150290966034,
+      "learning_rate": 6.813597078854772e-06,
+      "loss": 1.3536,
+      "step": 107
+    },
+    {
+      "epoch": 0.9047120418848168,
+      "grad_norm": 0.2558758854866028,
+      "learning_rate": 5.8155636360475385e-06,
+      "loss": 1.2918,
+      "step": 108
+    },
+    {
+      "epoch": 0.9130890052356021,
+      "grad_norm": 0.25811469554901123,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.2869,
+      "step": 109
+    },
+    {
+      "epoch": 0.9214659685863874,
+      "grad_norm": 0.25502899289131165,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 1.2949,
+      "step": 110
+    },
+    {
+      "epoch": 0.9298429319371728,
+      "grad_norm": 0.25524598360061646,
+      "learning_rate": 3.2853145298042953e-06,
+      "loss": 1.27,
+      "step": 111
+    },
+    {
+      "epoch": 0.9382198952879581,
+      "grad_norm": 0.2520923614501953,
+      "learning_rate": 2.5988083057666533e-06,
+      "loss": 1.3135,
+      "step": 112
+    },
+    {
+      "epoch": 0.9465968586387434,
+      "grad_norm": 0.2525266110897064,
+      "learning_rate": 1.9917438907606556e-06,
+      "loss": 1.2766,
+      "step": 113
+    },
+    {
+      "epoch": 0.9549738219895288,
+      "grad_norm": 0.25608813762664795,
+      "learning_rate": 1.4646164152307018e-06,
+      "loss": 1.3429,
+      "step": 114
+    },
+    {
+      "epoch": 0.9633507853403142,
+      "grad_norm": 0.26775017380714417,
+      "learning_rate": 1.0178558119067315e-06,
+      "loss": 1.3198,
+      "step": 115
+    },
+    {
+      "epoch": 0.9717277486910995,
+      "grad_norm": 0.25307947397232056,
+      "learning_rate": 6.518264651449779e-07,
+      "loss": 1.2831,
+      "step": 116
+    },
+    {
+      "epoch": 0.9801047120418848,
+      "grad_norm": 0.26626452803611755,
+      "learning_rate": 3.6682691373086665e-07,
+      "loss": 1.2701,
+      "step": 117
+    },
+    {
+      "epoch": 0.9884816753926702,
+      "grad_norm": 0.22642602026462555,
+      "learning_rate": 1.630896073864352e-07,
+      "loss": 1.3243,
+      "step": 118
+    },
+    {
+      "epoch": 0.9968586387434555,
+      "grad_norm": 0.28676363825798035,
+      "learning_rate": 4.078071718107701e-08,
+      "loss": 1.3269,
+      "step": 119
+    },
+    {
+      "epoch": 1.0052356020942408,
+      "grad_norm": 0.5024040937423706,
+      "learning_rate": 0.0,
+      "loss": 2.1063,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -754,12 +894,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.273845103591424e+17,
+  "total_flos": 6.327790086012273e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null