Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1febb6b8c487f66d3eaacbf33db5487c9a3d229218323cdca685761e1aa63cb6
+oid sha256:ab20c364e42310ed437faf8460c3206ecba82fce9b1aeb3364f58c170d4c2049
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94bf98f926a1252fb8b14bad67b6453dc7beb9b390deed43e523d779e15269e
+oid sha256:8c372ddb5011b8a7d2405d81cc5d7e44d59303ae53d8f7f052c10cd44f30f56a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:910235954e3050ae5a481a55a523f9ae20c1c19fe123b30124a974ada5a456ee
+oid sha256:5a12635441debf73fea86223e7939f3057cc0ac942a12eb1b3c97fb835087ec1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3192059420211edc26748a07e2699e00ee3be65f92a2cf84ef56d22611d9eb5c
+oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0772173404693604,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.038662284941040015,
+  "best_metric": 1.0642553567886353,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.05799342741156002,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 1.549,
       "eval_steps_per_second": 0.776,
       "step": 50
+    },
+    {
+      "epoch": 0.039435530639860814,
+      "grad_norm": 10.129049301147461,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 4.7483,
+      "step": 51
+    },
+    {
+      "epoch": 0.04020877633868162,
+      "grad_norm": 8.601277351379395,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 4.5312,
+      "step": 52
+    },
+    {
+      "epoch": 0.04098202203750242,
+      "grad_norm": 11.301950454711914,
+      "learning_rate": 4.917330276168208e-05,
+      "loss": 4.7463,
+      "step": 53
+    },
+    {
+      "epoch": 0.041755267736323216,
+      "grad_norm": 8.8668851852417,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 5.0553,
+      "step": 54
+    },
+    {
+      "epoch": 0.042528513435144015,
+      "grad_norm": 9.888030052185059,
+      "learning_rate": 4.5871032726383386e-05,
+      "loss": 4.5142,
+      "step": 55
+    },
+    {
+      "epoch": 0.04330175913396482,
+      "grad_norm": 9.675687789916992,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 4.6986,
+      "step": 56
+    },
+    {
+      "epoch": 0.04407500483278562,
+      "grad_norm": 11.324494361877441,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 5.2414,
+      "step": 57
+    },
+    {
+      "epoch": 0.04484825053160642,
+      "grad_norm": 10.077937126159668,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 4.647,
+      "step": 58
+    },
+    {
+      "epoch": 0.045621496230427216,
+      "grad_norm": 9.43274211883545,
+      "learning_rate": 3.933501846281267e-05,
+      "loss": 4.5543,
+      "step": 59
+    },
+    {
+      "epoch": 0.046394741929248015,
+      "grad_norm": 10.41069221496582,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 4.8732,
+      "step": 60
+    },
+    {
+      "epoch": 0.04716798762806882,
+      "grad_norm": 9.759603500366211,
+      "learning_rate": 3.612985456190778e-05,
+      "loss": 4.7214,
+      "step": 61
+    },
+    {
+      "epoch": 0.04794123332688962,
+      "grad_norm": 11.823719024658203,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.5216,
+      "step": 62
+    },
+    {
+      "epoch": 0.04871447902571042,
+      "grad_norm": 9.14537239074707,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 3.9145,
+      "step": 63
+    },
+    {
+      "epoch": 0.04948772472453122,
+      "grad_norm": 10.29529094696045,
+      "learning_rate": 3.144013755408895e-05,
+      "loss": 5.2241,
+      "step": 64
+    },
+    {
+      "epoch": 0.05026097042335202,
+      "grad_norm": 8.020105361938477,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 4.4175,
+      "step": 65
+    },
+    {
+      "epoch": 0.05103421612217282,
+      "grad_norm": 7.962001323699951,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 3.8547,
+      "step": 66
+    },
+    {
+      "epoch": 0.05180746182099362,
+      "grad_norm": 7.753868579864502,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 3.7267,
+      "step": 67
+    },
+    {
+      "epoch": 0.05258070751981442,
+      "grad_norm": 8.525618553161621,
+      "learning_rate": 2.547882480847461e-05,
+      "loss": 4.6899,
+      "step": 68
+    },
+    {
+      "epoch": 0.053353953218635224,
+      "grad_norm": 8.045459747314453,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 4.1387,
+      "step": 69
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 7.087581634521484,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 4.1212,
+      "step": 70
+    },
+    {
+      "epoch": 0.05490044461627682,
+      "grad_norm": 7.834628582000732,
+      "learning_rate": 2.128356686585282e-05,
+      "loss": 3.7453,
+      "step": 71
+    },
+    {
+      "epoch": 0.05567369031509762,
+      "grad_norm": 8.538744926452637,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 4.6089,
+      "step": 72
+    },
+    {
+      "epoch": 0.056446936013918425,
+      "grad_norm": 7.815285682678223,
+      "learning_rate": 1.8641182076323148e-05,
+      "loss": 3.8365,
+      "step": 73
+    },
+    {
+      "epoch": 0.057220181712739224,
+      "grad_norm": 7.645932674407959,
+      "learning_rate": 1.7370711923791567e-05,
+      "loss": 2.5073,
+      "step": 74
+    },
+    {
+      "epoch": 0.05799342741156002,
+      "grad_norm": 8.115581512451172,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 4.0698,
+      "step": 75
+    },
+    {
+      "epoch": 0.05799342741156002,
+      "eval_loss": 1.0642553567886353,
+      "eval_runtime": 352.0611,
+      "eval_samples_per_second": 1.548,
+      "eval_steps_per_second": 0.775,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.03129498681344e+16,
+  "total_flos": 1.054694248022016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null