Training in progress, step 84, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ada79dd370e83a047b0b6657b584cffec3951c9f2c738b336b7d3cf3e37cdf
+oid sha256:abaca53eb5827a8040ea6ba138386b60d148485e56e0ac3216537d45bee43af4
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bc0a8ed47d0c9b841760485f83b64aad5f5d88a17c8c5e4c6e52f7d89f014f
+oid sha256:1efad5db01bfe0b61f0122c42351eaf97cb57df7f8902dc30462f14c0494c932
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e358da91580cd66b2e37389c47d953a5c80737daa6eaf90c2b7451657a8d9d3c
+oid sha256:0e831928e96095aec0d5ce7aa160da3ad5fb823ddcd34e216fe120fc7c0379dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70ae2ccb443145dd03605557356bbb8336e340a70ea79ce07109ae066b2e8f7
+oid sha256:9a523cba751bf5de6a14df0525da0bc637eac82db4a6caf44eef419cda99e26f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0678768157958984,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.7857142857142856,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,244 @@
       "eval_samples_per_second": 11.976,
       "eval_steps_per_second": 3.058,
       "step": 50
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.9605938792228699,
+      "learning_rate": 4.1549958983907555e-05,
+      "loss": 0.8505,
+      "step": 51
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.9948092103004456,
+      "learning_rate": 3.94660365002137e-05,
+      "loss": 0.8254,
+      "step": 52
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.5172920823097229,
+      "learning_rate": 3.740109693074375e-05,
+      "loss": 0.997,
+      "step": 53
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.618449866771698,
+      "learning_rate": 3.5358861436172485e-05,
+      "loss": 0.8848,
+      "step": 54
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 0.7257911562919617,
+      "learning_rate": 3.334301026289712e-05,
+      "loss": 0.8151,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9913805723190308,
+      "learning_rate": 3.135717611098458e-05,
+      "loss": 0.6593,
+      "step": 56
+    },
+    {
+      "epoch": 2.0357142857142856,
+      "grad_norm": 0.509917140007019,
+      "learning_rate": 2.9404937587800375e-05,
+      "loss": 0.9468,
+      "step": 57
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.5384827852249146,
+      "learning_rate": 2.748981275911633e-05,
+      "loss": 0.8333,
+      "step": 58
+    },
+    {
+      "epoch": 2.107142857142857,
+      "grad_norm": 0.6404847502708435,
+      "learning_rate": 2.5615252809318284e-05,
+      "loss": 0.7695,
+      "step": 59
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.7586694359779358,
+      "learning_rate": 2.3784635822138424e-05,
+      "loss": 0.7043,
+      "step": 60
+    },
+    {
+      "epoch": 2.1785714285714284,
+      "grad_norm": 0.886222779750824,
+      "learning_rate": 2.2001260693120233e-05,
+      "loss": 0.5816,
+      "step": 61
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.9940441846847534,
+      "learning_rate": 2.026834118478567e-05,
+      "loss": 0.5794,
+      "step": 62
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.5342968702316284,
+      "learning_rate": 1.858900013521788e-05,
+      "loss": 0.8532,
+      "step": 63
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.6643630266189575,
+      "learning_rate": 1.6966263830495936e-05,
+      "loss": 0.8265,
+      "step": 64
+    },
+    {
+      "epoch": 2.3214285714285716,
+      "grad_norm": 0.6381016373634338,
+      "learning_rate": 1.5403056551122697e-05,
+      "loss": 0.7252,
+      "step": 65
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.6933656334877014,
+      "learning_rate": 1.3902195302273779e-05,
+      "loss": 0.6327,
+      "step": 66
+    },
+    {
+      "epoch": 2.392857142857143,
+      "grad_norm": 0.8817493915557861,
+      "learning_rate": 1.246638473736378e-05,
+      "loss": 0.5871,
+      "step": 67
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 1.0448442697525024,
+      "learning_rate": 1.1098212284078036e-05,
+      "loss": 0.6083,
+      "step": 68
+    },
+    {
+      "epoch": 2.4642857142857144,
+      "grad_norm": 0.6664843559265137,
+      "learning_rate": 9.800143481652979e-06,
+      "loss": 0.8117,
+      "step": 69
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.8378458023071289,
+      "learning_rate": 8.574517537807897e-06,
+      "loss": 0.8003,
+      "step": 70
+    },
+    {
+      "epoch": 2.5357142857142856,
+      "grad_norm": 0.7771973013877869,
+      "learning_rate": 7.423543113334436e-06,
+      "loss": 0.7034,
+      "step": 71
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.8301295638084412,
+      "learning_rate": 6.349294341940593e-06,
+      "loss": 0.6515,
+      "step": 72
+    },
+    {
+      "epoch": 2.607142857142857,
+      "grad_norm": 0.9299514293670654,
+      "learning_rate": 5.353707092521582e-06,
+      "loss": 0.4939,
+      "step": 73
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 1.0564358234405518,
+      "learning_rate": 4.43857548059321e-06,
+      "loss": 0.4689,
+      "step": 74
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 0.6848633885383606,
+      "learning_rate": 3.605548635174533e-06,
+      "loss": 0.83,
+      "step": 75
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.7416503429412842,
+      "learning_rate": 2.85612772694579e-06,
+      "loss": 0.7841,
+      "step": 76
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.7347410917282104,
+      "learning_rate": 2.191663263037458e-06,
+      "loss": 0.741,
+      "step": 77
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.7589361667633057,
+      "learning_rate": 1.6133526533250565e-06,
+      "loss": 0.5824,
+      "step": 78
+    },
+    {
+      "epoch": 2.821428571428571,
+      "grad_norm": 0.964680016040802,
+      "learning_rate": 1.1222380526156928e-06,
+      "loss": 0.6366,
+      "step": 79
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.945676863193512,
+      "learning_rate": 7.192044826145771e-07,
+      "loss": 0.4343,
+      "step": 80
+    },
+    {
+      "epoch": 2.892857142857143,
+      "grad_norm": 0.6502677202224731,
+      "learning_rate": 4.049782370561583e-07,
+      "loss": 0.8532,
+      "step": 81
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.7305717468261719,
+      "learning_rate": 1.8012557287367392e-07,
+      "loss": 0.7416,
+      "step": 82
+    },
+    {
+      "epoch": 2.9642857142857144,
+      "grad_norm": 0.7641732692718506,
+      "learning_rate": 4.5051689765929214e-08,
+      "loss": 0.5735,
+      "step": 83
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0511471033096313,
+      "learning_rate": 0.0,
+      "loss": 0.5306,
+      "step": 84
     }
   ],
   "logging_steps": 1,
@@ -396,12 +634,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.853698819345613e+16,
+  "total_flos": 1.3114639925221786e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null