Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f583834bbce9dff3c4190e4b544b32cc3e6b8aad0c2cc4db78f90c32b494c6d5
+oid sha256:da52cab24327ae193d83cd890f42da8f46d5ef5a74e64c363f0f5627717e2555
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f703d7b3e3b461cee90be78974a3149b62f1634412ab8d20eb71e6af8041e7b
+oid sha256:5296f35a3466fde202ee0f9c6c4fbe75c357d2e84fb57b0387b1cedbd229e913
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348423016cd468e87bf1055688f8279d584df3402114224ced597d402741a6c2
+oid sha256:d6b67260b146c1a31729eceea98f9db54edb2f6b2f931604888ffca08fe405bb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e423371f7241bbc318ffebfbb1762f075f08a1dfc821d8377483824ee44ae67
+oid sha256:39dc9fed967bb61de87aa65ff797df987c2d6d9842740e4743bd4bee060df731
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225aef233c53e245d3147cba77ccbcd1c9ff6db4d8ad774acf8f7604b5685443
+oid sha256:3a3349eeb4ef9e1b42a121e9128220222370d5875e3675793788cdd47a6eb584
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c55d4b9e6b75c072d7f3861825bd82916294198d7211847ee3bf7eacf37cec4
+oid sha256:53edf81a0414687c89e9f22fc2b14da8140dfdea6492428fdff134b827f3ac0b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 8.485151290893555,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.05333451854485655,
+  "epoch": 0.06755705682348496,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 103.437,
       "eval_steps_per_second": 26.894,
       "step": 75
+    },
+    {
+      "epoch": 0.054045645458787976,
+      "grad_norm": 1.2563050985336304,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 8.1814,
+      "step": 76
+    },
+    {
+      "epoch": 0.05475677237271939,
+      "grad_norm": 1.031311273574829,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 8.4385,
+      "step": 77
+    },
+    {
+      "epoch": 0.055467899286650815,
+      "grad_norm": 1.0750837326049805,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 8.5048,
+      "step": 78
+    },
+    {
+      "epoch": 0.05617902620058224,
+      "grad_norm": 1.2149912118911743,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 8.2128,
+      "step": 79
+    },
+    {
+      "epoch": 0.056890153114513654,
+      "grad_norm": 0.8455520272254944,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 8.585,
+      "step": 80
+    },
+    {
+      "epoch": 0.05760128002844508,
+      "grad_norm": 0.9065818190574646,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 8.8332,
+      "step": 81
+    },
+    {
+      "epoch": 0.0583124069423765,
+      "grad_norm": 0.9263755083084106,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 8.7434,
+      "step": 82
+    },
+    {
+      "epoch": 0.059023533856307916,
+      "grad_norm": 0.953991174697876,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 8.4833,
+      "step": 83
+    },
+    {
+      "epoch": 0.05973466077023934,
+      "grad_norm": 0.9421951174736023,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 8.9237,
+      "step": 84
+    },
+    {
+      "epoch": 0.06044578768417076,
+      "grad_norm": 0.9801391959190369,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 8.7981,
+      "step": 85
+    },
+    {
+      "epoch": 0.06115691459810218,
+      "grad_norm": 1.2952722311019897,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 8.8525,
+      "step": 86
+    },
+    {
+      "epoch": 0.0618680415120336,
+      "grad_norm": 1.563397765159607,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 8.9335,
+      "step": 87
+    },
+    {
+      "epoch": 0.06257916842596502,
+      "grad_norm": 1.1210330724716187,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 8.1383,
+      "step": 88
+    },
+    {
+      "epoch": 0.06329029533989644,
+      "grad_norm": 1.132744312286377,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 8.304,
+      "step": 89
+    },
+    {
+      "epoch": 0.06400142225382786,
+      "grad_norm": 1.082865595817566,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 8.348,
+      "step": 90
+    },
+    {
+      "epoch": 0.06471254916775929,
+      "grad_norm": 0.9174438118934631,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 8.3503,
+      "step": 91
+    },
+    {
+      "epoch": 0.06542367608169071,
+      "grad_norm": 0.9113219380378723,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 8.5919,
+      "step": 92
+    },
+    {
+      "epoch": 0.06613480299562212,
+      "grad_norm": 0.8231514096260071,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 8.509,
+      "step": 93
+    },
+    {
+      "epoch": 0.06684592990955354,
+      "grad_norm": 0.9372797012329102,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 8.7682,
+      "step": 94
+    },
+    {
+      "epoch": 0.06755705682348496,
+      "grad_norm": 0.9878532290458679,
+      "learning_rate": 1e-05,
+      "loss": 8.678,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 348020696678400.0,
+  "total_flos": 440826215792640.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null