Training in progress, step 82, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c824ebdfc578f7ada46763335d719d2ee5de8604889825ddc60f736b962f372c
+oid sha256:6eec4e255dc2c237418995da20f97830b4db96eba6df2723e135b818d9f80ada
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2d403b1bcea18961184d1cab7f088ea4e916e171225f66f38771fe0cee673b
+oid sha256:9492c6ef77a4881b144764073b48f5aab32509ad0010534dd34adfaf6139a0d4
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f115dd00401ad09a019a79057eef9805cd37d1dee586fb50518d785474dca9ed
+oid sha256:07c34260a314a1151e761369646bee8d7c1d2f43246d6d1db828d43799d50770
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22c4128b93322f91dfe46e838107695ac428a6ebd522442cb1b93f0b3af5c23
+oid sha256:2913c743d432c63154cc874349ee4f205805b2a7c45ea65b19238384071e5c70
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.794490337371826,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.834862385321101,
+  "epoch": 3.0091743119266057,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 82,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,230 @@
       "eval_samples_per_second": 55.497,
       "eval_steps_per_second": 14.478,
       "step": 50
+    },
+    {
+      "epoch": 1.8715596330275228,
+      "grad_norm": 2.4646809101104736,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 3.1713,
+      "step": 51
+    },
+    {
+      "epoch": 1.908256880733945,
+      "grad_norm": 1.8905830383300781,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8779,
+      "step": 52
+    },
+    {
+      "epoch": 1.9449541284403669,
+      "grad_norm": 1.9871137142181396,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 2.301,
+      "step": 53
+    },
+    {
+      "epoch": 1.981651376146789,
+      "grad_norm": 2.354430675506592,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.8783,
+      "step": 54
+    },
+    {
+      "epoch": 2.018348623853211,
+      "grad_norm": 18.58392906188965,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4221,
+      "step": 55
+    },
+    {
+      "epoch": 2.055045871559633,
+      "grad_norm": 1.5382347106933594,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 1.709,
+      "step": 56
+    },
+    {
+      "epoch": 2.091743119266055,
+      "grad_norm": 2.0155248641967773,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 2.0317,
+      "step": 57
+    },
+    {
+      "epoch": 2.128440366972477,
+      "grad_norm": 2.010490894317627,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1576,
+      "step": 58
+    },
+    {
+      "epoch": 2.165137614678899,
+      "grad_norm": 2.338270664215088,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 2.6313,
+      "step": 59
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 2.1534883975982666,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 2.4052,
+      "step": 60
+    },
+    {
+      "epoch": 2.238532110091743,
+      "grad_norm": 1.8989624977111816,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5759,
+      "step": 61
+    },
+    {
+      "epoch": 2.2752293577981653,
+      "grad_norm": 1.8402177095413208,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.8791,
+      "step": 62
+    },
+    {
+      "epoch": 2.311926605504587,
+      "grad_norm": 1.8744562864303589,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 1.8791,
+      "step": 63
+    },
+    {
+      "epoch": 2.3486238532110093,
+      "grad_norm": 2.0032284259796143,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0758,
+      "step": 64
+    },
+    {
+      "epoch": 2.385321100917431,
+      "grad_norm": 2.3931808471679688,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 2.5836,
+      "step": 65
+    },
+    {
+      "epoch": 2.4220183486238533,
+      "grad_norm": 2.3359298706054688,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.2854,
+      "step": 66
+    },
+    {
+      "epoch": 2.458715596330275,
+      "grad_norm": 2.2190897464752197,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.4988,
+      "step": 67
+    },
+    {
+      "epoch": 2.4954128440366974,
+      "grad_norm": 1.7014034986495972,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.7235,
+      "step": 68
+    },
+    {
+      "epoch": 2.532110091743119,
+      "grad_norm": 1.9192044734954834,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 1.853,
+      "step": 69
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 2.194664716720581,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2183,
+      "step": 70
+    },
+    {
+      "epoch": 2.6055045871559632,
+      "grad_norm": 2.3629367351531982,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 2.433,
+      "step": 71
+    },
+    {
+      "epoch": 2.6422018348623855,
+      "grad_norm": 2.4009580612182617,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 2.6095,
+      "step": 72
+    },
+    {
+      "epoch": 2.6788990825688073,
+      "grad_norm": 2.021143674850464,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0666,
+      "step": 73
+    },
+    {
+      "epoch": 2.7155963302752295,
+      "grad_norm": 1.8128962516784668,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.619,
+      "step": 74
+    },
+    {
+      "epoch": 2.7522935779816513,
+      "grad_norm": 2.0448718070983887,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.9748,
+      "step": 75
+    },
+    {
+      "epoch": 2.7889908256880735,
+      "grad_norm": 2.2684381008148193,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3428,
+      "step": 76
+    },
+    {
+      "epoch": 2.8256880733944953,
+      "grad_norm": 2.097766160964966,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 2.1287,
+      "step": 77
+    },
+    {
+      "epoch": 2.8623853211009176,
+      "grad_norm": 2.689925193786621,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.5555,
+      "step": 78
+    },
+    {
+      "epoch": 2.8990825688073394,
+      "grad_norm": 2.0559446811676025,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8365,
+      "step": 79
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 1.871863603591919,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.7793,
+      "step": 80
+    },
+    {
+      "epoch": 2.9724770642201834,
+      "grad_norm": 2.4684290885925293,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 2.483,
+      "step": 81
+    },
+    {
+      "epoch": 3.0091743119266057,
+      "grad_norm": 21.217084884643555,
+      "learning_rate": 0.0,
+      "loss": 2.2827,
+      "step": 82
     }
   ],
   "logging_steps": 1,
@@ -396,12 +620,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3847335160578048.0,
+  "total_flos": 6286637428113408.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null