Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291214b969435121a62e3461d03aabd1cfd41b84bc7c9fb5141db351d94407bf
+oid sha256:68df9bc0d7c3fd7446aee3131f5519019f80b844c44b0eb7d57cd2f334119087
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a156e3b116157a78505e886ddea532f3a57f0f79d5b01551f3aa2e1537f62384
+oid sha256:cd730854612530fb95d9ad2b8a98e2b3450b0bd6be98b6a9f7480f096ae802be
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea5dd64b4d8616ac34fb3a581d5e92a9ed7987aff3fecf823c4114c082bcfe43
+oid sha256:6b917d9eafff7c1dfffb1df40eea06aef93b28a595bc74c5a0c461d97445938d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44d378579853882a0105739b82bd123631a7e5020a7d39951af6675c75532d1
+oid sha256:d27e319e315ecf215424486964035fbbaf4fe52c5b0ef7f972036c059f0dcf31
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a1793c5dff9996e3ac3e64dc6e3a51255a4a7301045b7ad42ea83a5deb9b88
+oid sha256:ffd31ce42e272e6ef2e23877da808684db8d6dc053764f506197db87db4ebaa2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c15a460c925470a7de090742206e2b41d8d4fea6bce460cbbc049627c6365104
+oid sha256:1bdbed8655d50128a464e4cd423db9e90b8a25f86c88f64bbd9acc95f7f7cda0
 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": 1.3074243068695068,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.7275985663082438,
+  "epoch": 2.193548387096774,
   "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": 10.469,
       "eval_steps_per_second": 2.722,
       "step": 75
+    },
+    {
+      "epoch": 1.750537634408602,
+      "grad_norm": 55.19490051269531,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 28.7145,
+      "step": 76
+    },
+    {
+      "epoch": 1.7734767025089606,
+      "grad_norm": 54.55601501464844,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 37.6403,
+      "step": 77
+    },
+    {
+      "epoch": 1.7964157706093191,
+      "grad_norm": 53.513118743896484,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 34.2424,
+      "step": 78
+    },
+    {
+      "epoch": 1.8193548387096774,
+      "grad_norm": 53.09416198730469,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 34.4384,
+      "step": 79
+    },
+    {
+      "epoch": 1.8422939068100357,
+      "grad_norm": 54.03006362915039,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 31.8524,
+      "step": 80
+    },
+    {
+      "epoch": 1.8652329749103944,
+      "grad_norm": 53.396759033203125,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 31.2347,
+      "step": 81
+    },
+    {
+      "epoch": 1.8881720430107527,
+      "grad_norm": 54.46861267089844,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 31.0389,
+      "step": 82
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 56.113277435302734,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 27.2539,
+      "step": 83
+    },
+    {
+      "epoch": 1.9340501792114695,
+      "grad_norm": 57.12498474121094,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 29.4038,
+      "step": 84
+    },
+    {
+      "epoch": 1.956989247311828,
+      "grad_norm": 61.591796875,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 29.9574,
+      "step": 85
+    },
+    {
+      "epoch": 1.9799283154121863,
+      "grad_norm": 65.86859893798828,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 27.3837,
+      "step": 86
+    },
+    {
+      "epoch": 2.010035842293907,
+      "grad_norm": 53.8763313293457,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 30.1786,
+      "step": 87
+    },
+    {
+      "epoch": 2.032974910394265,
+      "grad_norm": 46.642704010009766,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 32.0186,
+      "step": 88
+    },
+    {
+      "epoch": 2.055913978494624,
+      "grad_norm": 47.648860931396484,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 29.1689,
+      "step": 89
+    },
+    {
+      "epoch": 2.078853046594982,
+      "grad_norm": 51.06687927246094,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 27.9636,
+      "step": 90
+    },
+    {
+      "epoch": 2.1017921146953404,
+      "grad_norm": 59.35122299194336,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 26.5625,
+      "step": 91
+    },
+    {
+      "epoch": 2.1247311827956987,
+      "grad_norm": 51.24475860595703,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 26.1366,
+      "step": 92
+    },
+    {
+      "epoch": 2.1476702508960575,
+      "grad_norm": 53.65019607543945,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 24.5783,
+      "step": 93
+    },
+    {
+      "epoch": 2.1706093189964157,
+      "grad_norm": 53.362648010253906,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 22.3915,
+      "step": 94
+    },
+    {
+      "epoch": 2.193548387096774,
+      "grad_norm": 55.55318069458008,
+      "learning_rate": 1e-05,
+      "loss": 23.159,
+      "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": 8.487032007426048e+17,
+  "total_flos": 1.0750240542739661e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null