Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c92c058ba2f5f4bda5e5218b0e10228f00884f4f10e38e2269260a9b6eca92
+oid sha256:f326ac01244b57f2627eceb74534449b8afc28d6ceb3f3a4b071c7339a01db93
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c7a63589f00ab31c6ba07c23790ccbdf188b766c126236f16016269cfc23cf
+oid sha256:c4a1bc35bfbc537273ae41dc8f102f36799e0c2eecd3a3102187969a17765b85
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619d8a91381c8f893e6203a86f380ced90d180a08d12fae876d7ea0c06ab2b00
+oid sha256:eada63ad6f28ef830f8cf583dec1aaea366d154a2c7696a7606d488addaa43d7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2913fccdef36919bb2f011279eea5e19b38a3c08385de54504f3f5d8e8a624d8
+oid sha256:edafd4df5aad1d3b7061a37014328ea51e0a0c77df291f00db54f164ccd35ff2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c8fe3ac6db7d9195bac33c58b9fc88ecec8187bf55d51f187c9be783b9f93d
+oid sha256:0490adea23f6aab198992cab1d8d3df27c47eab8a053dc9f22e966a66ca21228
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24fa0f146e95e969ae981049759503c019b8e33139203dbd1c607d6618650f0
+oid sha256:20cd461889bd059b6c6f341b6948ade6e0272b80d1c31ef08ca99d29a78747f8
 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": 1.1252893209457397,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.6106870229007634,
+  "epoch": 0.7735368956743003,
   "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": 15.399,
       "eval_steps_per_second": 4.004,
       "step": 75
+    },
+    {
+      "epoch": 0.6188295165394402,
+      "grad_norm": 0.2565176784992218,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 1.331,
+      "step": 76
+    },
+    {
+      "epoch": 0.6269720101781171,
+      "grad_norm": 0.2451658397912979,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 1.2461,
+      "step": 77
+    },
+    {
+      "epoch": 0.6351145038167939,
+      "grad_norm": 0.2756778597831726,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 1.2637,
+      "step": 78
+    },
+    {
+      "epoch": 0.6432569974554707,
+      "grad_norm": 0.2695421874523163,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 1.2262,
+      "step": 79
+    },
+    {
+      "epoch": 0.6513994910941476,
+      "grad_norm": 0.288644403219223,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 1.1969,
+      "step": 80
+    },
+    {
+      "epoch": 0.6595419847328244,
+      "grad_norm": 0.29181233048439026,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.163,
+      "step": 81
+    },
+    {
+      "epoch": 0.6676844783715012,
+      "grad_norm": 0.2998856008052826,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 1.0569,
+      "step": 82
+    },
+    {
+      "epoch": 0.6758269720101782,
+      "grad_norm": 0.3256518244743347,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 1.0537,
+      "step": 83
+    },
+    {
+      "epoch": 0.683969465648855,
+      "grad_norm": 0.29111307859420776,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 1.0298,
+      "step": 84
+    },
+    {
+      "epoch": 0.6921119592875318,
+      "grad_norm": 0.32174497842788696,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.9976,
+      "step": 85
+    },
+    {
+      "epoch": 0.7002544529262087,
+      "grad_norm": 0.36173349618911743,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.9361,
+      "step": 86
+    },
+    {
+      "epoch": 0.7083969465648855,
+      "grad_norm": 0.3511975407600403,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.8343,
+      "step": 87
+    },
+    {
+      "epoch": 0.7165394402035623,
+      "grad_norm": 0.2947863042354584,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 1.3039,
+      "step": 88
+    },
+    {
+      "epoch": 0.7246819338422392,
+      "grad_norm": 0.2641090154647827,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 1.2791,
+      "step": 89
+    },
+    {
+      "epoch": 0.732824427480916,
+      "grad_norm": 0.2599228024482727,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 1.2946,
+      "step": 90
+    },
+    {
+      "epoch": 0.7409669211195928,
+      "grad_norm": 0.2754274308681488,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 1.2478,
+      "step": 91
+    },
+    {
+      "epoch": 0.7491094147582698,
+      "grad_norm": 0.2846546173095703,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 1.2817,
+      "step": 92
+    },
+    {
+      "epoch": 0.7572519083969466,
+      "grad_norm": 0.29695919156074524,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 1.2161,
+      "step": 93
+    },
+    {
+      "epoch": 0.7653944020356234,
+      "grad_norm": 0.29593130946159363,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 1.1682,
+      "step": 94
+    },
+    {
+      "epoch": 0.7735368956743003,
+      "grad_norm": 0.2888301908969879,
+      "learning_rate": 1e-05,
+      "loss": 1.0711,
+      "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": 8.436086715973632e+17,
+  "total_flos": 1.0685709840233267e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null