Training in progress, step 46, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f182b81f638f8ef69ce66e93af01d395057cd24d2aab33b40325ca5c81f3d8
+oid sha256:f7c6f1084ed3700c3454a2448e5ed2b265c8884bf9fe07a9bc7ea28f5b7e9f11
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85324199877dfffb7607f7afa8d9b018a4116615c2246884a5654a617519a0c1
+oid sha256:14b7fc2a6d151125933a48bd6397cd8ad37fe4354457e9cf66b8a391ce3794cf
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30daa9a7592cfa20f51b94b4aa708a7dc5cf2aa1ae681035d89e0609a44222f0
+oid sha256:81741de6e898e1250e5cb590a0eb1c3e7bd6bd24806864d9b483fb4c30bbf825
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9739a5c84a65a183aaceb019fc9dc20dbfaebb0005316af3f80f4ee56607267
+oid sha256:19dddc0b6cb2d502dca9d4c1f1d4c7210ecd9950ff974605260df48030e6adc4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62fa0bd2b102f25022547f65a7a9db422bb2faff81778ad61c0ad62f909ebdf
+oid sha256:2b72b376989328d88f7204f8c2450c92ad968c5171aceb25802134dcad1bc175
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35af6438c2a92d9973acad6d80d8a4a33fdacd6d5b73017506a1248bcd26eb07
+oid sha256:9414d137ecdfe150cd36a229c2ee6d6c2d8e0dc3efcbc20a96e2225ff5299c68
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4e4728265849a5c8f503e18c55a53f2fb6db704986db6665c2db1ebdbba252
+oid sha256:9ae5239404ab97e0fcf1d64e94bd56d195792c49faa00afb9e436068b35b4aef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.19664782285690308,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.639344262295082,
+  "epoch": 3.0163934426229506,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 46,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,153 @@
       "eval_samples_per_second": 14.617,
       "eval_steps_per_second": 3.8,
       "step": 25
+    },
+    {
+      "epoch": 1.7049180327868854,
+      "grad_norm": 0.16763406991958618,
+      "learning_rate": 4.859583227770218e-05,
+      "loss": 0.3129,
+      "step": 26
+    },
+    {
+      "epoch": 1.7704918032786885,
+      "grad_norm": 0.10168012976646423,
+      "learning_rate": 4.543456197011605e-05,
+      "loss": 0.1769,
+      "step": 27
+    },
+    {
+      "epoch": 1.8360655737704918,
+      "grad_norm": 0.0870274230837822,
+      "learning_rate": 4.232203494213567e-05,
+      "loss": 0.1408,
+      "step": 28
+    },
+    {
+      "epoch": 1.901639344262295,
+      "grad_norm": 0.12161073088645935,
+      "learning_rate": 3.927411191804058e-05,
+      "loss": 0.206,
+      "step": 29
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 0.18406201899051666,
+      "learning_rate": 3.630632441491512e-05,
+      "loss": 0.3345,
+      "step": 30
+    },
+    {
+      "epoch": 2.0327868852459017,
+      "grad_norm": 0.2242753803730011,
+      "learning_rate": 3.343379559759746e-05,
+      "loss": 0.3352,
+      "step": 31
+    },
+    {
+      "epoch": 2.098360655737705,
+      "grad_norm": 0.07899916917085648,
+      "learning_rate": 3.067116321449813e-05,
+      "loss": 0.122,
+      "step": 32
+    },
+    {
+      "epoch": 2.1639344262295084,
+      "grad_norm": 0.12275606393814087,
+      "learning_rate": 2.803250500698939e-05,
+      "loss": 0.194,
+      "step": 33
+    },
+    {
+      "epoch": 2.2295081967213113,
+      "grad_norm": 0.13614587485790253,
+      "learning_rate": 2.5531266972462177e-05,
+      "loss": 0.2503,
+      "step": 34
+    },
+    {
+      "epoch": 2.2950819672131146,
+      "grad_norm": 0.11481458693742752,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1806,
+      "step": 35
+    },
+    {
+      "epoch": 2.360655737704918,
+      "grad_norm": 0.09330334514379501,
+      "learning_rate": 2.0991269154058385e-05,
+      "loss": 0.1425,
+      "step": 36
+    },
+    {
+      "epoch": 2.4262295081967213,
+      "grad_norm": 0.1448790580034256,
+      "learning_rate": 1.897564415840379e-05,
+      "loss": 0.2288,
+      "step": 37
+    },
+    {
+      "epoch": 2.4918032786885247,
+      "grad_norm": 0.12863922119140625,
+      "learning_rate": 1.7143591022596845e-05,
+      "loss": 0.181,
+      "step": 38
+    },
+    {
+      "epoch": 2.557377049180328,
+      "grad_norm": 0.10539160668849945,
+      "learning_rate": 1.5504445469473496e-05,
+      "loss": 0.1764,
+      "step": 39
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 0.1047457829117775,
+      "learning_rate": 1.4066560209046673e-05,
+      "loss": 0.1523,
+      "step": 40
+    },
+    {
+      "epoch": 2.6885245901639343,
+      "grad_norm": 0.15245206654071808,
+      "learning_rate": 1.2837262375010731e-05,
+      "loss": 0.2268,
+      "step": 41
+    },
+    {
+      "epoch": 2.7540983606557377,
+      "grad_norm": 0.12327948957681656,
+      "learning_rate": 1.1822816187347623e-05,
+      "loss": 0.1537,
+      "step": 42
+    },
+    {
+      "epoch": 2.819672131147541,
+      "grad_norm": 0.08937690407037735,
+      "learning_rate": 1.1028391031297826e-05,
+      "loss": 0.1227,
+      "step": 43
+    },
+    {
+      "epoch": 2.8852459016393444,
+      "grad_norm": 0.11844687163829803,
+      "learning_rate": 1.0458035115358032e-05,
+      "loss": 0.1708,
+      "step": 44
+    },
+    {
+      "epoch": 2.9508196721311473,
+      "grad_norm": 0.18891659379005432,
+      "learning_rate": 1.0114654842538593e-05,
+      "loss": 0.2713,
+      "step": 45
+    },
+    {
+      "epoch": 3.0163934426229506,
+      "grad_norm": 0.2762884795665741,
+      "learning_rate": 1e-05,
+      "loss": 0.3081,
+      "step": 46
     }
   ],
   "logging_steps": 1,
@@ -221,12 +368,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.315690861756416e+17,
+  "total_flos": 6.100871185631805e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null