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:f0fbf280e31e1bb3c3d86d6e286ea4b19869029a76773d1105aba548b388f177
+oid sha256:2663a32f73dfa280bcd59863b877b527f2e7e842fc58264f29808462d4fc03d9
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e6e2ef2675f85be93aa3706eeb438c4f34c7bbf21b60a72cf5961941054244d
+oid sha256:b0990e562cc54898cc0cff293718e20860b290b9ad423bde3f30d05e5e9a40c2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01e79fdf3153a9adb667d159df4732752b3d098e8fd8409bfe0ba32414a13a
+oid sha256:36493a5d7acfb47da9a4be27b5e2d688bb24f20b27b1f9b16a17628a5aa3f7b8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f141b2f1ac0d1ae1ee0a08e36966ecc914f6493c2cc4489245bfdd4b2848e283
+oid sha256:96cc1563bde5330b3e000c9a04d69997f6afc7be1fda96383fc631ca6f4961ce
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e439393da96622b24543b06b6f4a815f7ed790f55ff8c6624e65a866c326f24
+oid sha256:87df3303b07e1f288db3dcae94523681276b529276891a15aa256f93df0b05a0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b5e225b595a5d0ecebe54733d04b09a193b70667a3cb2487430fa0d3b9c4c8
+oid sha256:f3a10b955998ccc7b833dc5e5b42f5c991aa0ac5f2d2ea80d8467db7728ba354
 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": 1.047793984413147,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.1841332027424094,
+  "epoch": 1.4975514201762978,
   "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": 12.351,
       "eval_steps_per_second": 3.211,
       "step": 75
+    },
+    {
+      "epoch": 1.1998041136141038,
+      "grad_norm": 0.20321336388587952,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.6967,
+      "step": 76
+    },
+    {
+      "epoch": 1.2154750244857984,
+      "grad_norm": 0.29565516114234924,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 1.0459,
+      "step": 77
+    },
+    {
+      "epoch": 1.2311459353574927,
+      "grad_norm": 0.21626198291778564,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.8837,
+      "step": 78
+    },
+    {
+      "epoch": 1.246816846229187,
+      "grad_norm": 0.21457991003990173,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.9977,
+      "step": 79
+    },
+    {
+      "epoch": 1.2624877571008815,
+      "grad_norm": 0.23749592900276184,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 1.0405,
+      "step": 80
+    },
+    {
+      "epoch": 1.2781586679725758,
+      "grad_norm": 0.2553286850452423,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.0177,
+      "step": 81
+    },
+    {
+      "epoch": 1.2938295788442704,
+      "grad_norm": 0.25675755739212036,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 1.0387,
+      "step": 82
+    },
+    {
+      "epoch": 1.3095004897159648,
+      "grad_norm": 0.3346741795539856,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 1.0614,
+      "step": 83
+    },
+    {
+      "epoch": 1.3251714005876591,
+      "grad_norm": 0.29241129755973816,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 1.1101,
+      "step": 84
+    },
+    {
+      "epoch": 1.3408423114593535,
+      "grad_norm": 0.30398261547088623,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 1.0412,
+      "step": 85
+    },
+    {
+      "epoch": 1.3565132223310479,
+      "grad_norm": 0.35737118124961853,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 1.0841,
+      "step": 86
+    },
+    {
+      "epoch": 1.3721841332027425,
+      "grad_norm": 0.3579014241695404,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 1.0572,
+      "step": 87
+    },
+    {
+      "epoch": 1.3878550440744368,
+      "grad_norm": 0.45231765508651733,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 1.171,
+      "step": 88
+    },
+    {
+      "epoch": 1.4035259549461312,
+      "grad_norm": 0.21733441948890686,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.8669,
+      "step": 89
+    },
+    {
+      "epoch": 1.4191968658178258,
+      "grad_norm": 0.2003743052482605,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.8578,
+      "step": 90
+    },
+    {
+      "epoch": 1.4348677766895201,
+      "grad_norm": 0.21388119459152222,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 1.0007,
+      "step": 91
+    },
+    {
+      "epoch": 1.4505386875612145,
+      "grad_norm": 0.23207959532737732,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.9724,
+      "step": 92
+    },
+    {
+      "epoch": 1.4662095984329089,
+      "grad_norm": 0.22219336032867432,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 1.0635,
+      "step": 93
+    },
+    {
+      "epoch": 1.4818805093046032,
+      "grad_norm": 0.2789229452610016,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 1.0651,
+      "step": 94
+    },
+    {
+      "epoch": 1.4975514201762978,
+      "grad_norm": 0.2932514548301697,
+      "learning_rate": 1e-05,
+      "loss": 1.0618,
+      "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": 8.975438240022528e+17,
+  "total_flos": 1.1368266762320609e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null