Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a6321f7f79c210b4589e52b5355110d62212c4ff01b3b98146919a816eb9b0
+oid sha256:c5513d61dbc469f75737731fe557c2a034c60758d21d4aa47304187b1de8cafc
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05605c7498b722b8db1c6995631e9cedfaf798fa855eb99009b3cb744c5be15d
+oid sha256:37d12bdd04809f555d1424ae5a074148da7eb813e5d7c34f05c6c77edcd68859
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15486fd7168c80d12f19a469255c8e3d292d65632b403d1c846c636b4d3bd597
+oid sha256:a759c30f60fc722413fc2980251fd59e9ce372d1ed1fd8e4a810ef3952d8b1f1
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a04e728991100b53f9feb6ac13b030ec558a32122cf933a55e2bcc1308eb560
+oid sha256:a6718c9f121e9406bd26c926f32d12784e790d6a230a6d71f2ca579c5433a997
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd402d520d6e36fa67b9590012250fbcd6b908613e775cb9d6c4ecfc7f461c2
+oid sha256:39c90e735caa0948a577bbe81083cf4b2e7348ddd67ce9f0249ce11992f3aba7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a236795b1b2aa2f21a4ee69748c4193a9ac88664f55fbf82a787e7b952efba91
+oid sha256:843d7885ee00fe9bcc151b8cd2d9ebbc2295adfd8d8491c91245e4f24b41faf4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3860068619251251,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.021443122118580467,
+  "best_metric": 0.2157745063304901,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.042886244237160934,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 70.903,
       "eval_steps_per_second": 8.864,
       "step": 25
+    },
+    {
+      "epoch": 0.022300847003323684,
+      "grad_norm": 2.8950188159942627,
+      "learning_rate": 5e-05,
+      "loss": 0.73,
+      "step": 26
+    },
+    {
+      "epoch": 0.023158571888066904,
+      "grad_norm": 3.2829320430755615,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5514,
+      "step": 27
+    },
+    {
+      "epoch": 0.02401629677281012,
+      "grad_norm": 2.5224287509918213,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3176,
+      "step": 28
+    },
+    {
+      "epoch": 0.02487402165755334,
+      "grad_norm": 4.160872936248779,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2866,
+      "step": 29
+    },
+    {
+      "epoch": 0.025731746542296558,
+      "grad_norm": 2.872546672821045,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3233,
+      "step": 30
+    },
+    {
+      "epoch": 0.02658947142703978,
+      "grad_norm": 2.607795476913452,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2424,
+      "step": 31
+    },
+    {
+      "epoch": 0.027447196311782995,
+      "grad_norm": 1.1529837846755981,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2562,
+      "step": 32
+    },
+    {
+      "epoch": 0.028304921196526216,
+      "grad_norm": 1.0159945487976074,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1601,
+      "step": 33
+    },
+    {
+      "epoch": 0.029162646081269433,
+      "grad_norm": 1.7587469816207886,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2515,
+      "step": 34
+    },
+    {
+      "epoch": 0.030020370966012653,
+      "grad_norm": 3.4404122829437256,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3353,
+      "step": 35
+    },
+    {
+      "epoch": 0.03087809585075587,
+      "grad_norm": 2.699526786804199,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.306,
+      "step": 36
+    },
+    {
+      "epoch": 0.03173582073549909,
+      "grad_norm": 2.4039580821990967,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3528,
+      "step": 37
+    },
+    {
+      "epoch": 0.03259354562024231,
+      "grad_norm": 1.31723153591156,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2554,
+      "step": 38
+    },
+    {
+      "epoch": 0.033451270504985524,
+      "grad_norm": 2.59911847114563,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3681,
+      "step": 39
+    },
+    {
+      "epoch": 0.034308995389728744,
+      "grad_norm": 1.1396697759628296,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1878,
+      "step": 40
+    },
+    {
+      "epoch": 0.035166720274471965,
+      "grad_norm": 1.5017955303192139,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.231,
+      "step": 41
+    },
+    {
+      "epoch": 0.036024445159215185,
+      "grad_norm": 1.122409462928772,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2008,
+      "step": 42
+    },
+    {
+      "epoch": 0.0368821700439584,
+      "grad_norm": 1.102306604385376,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1537,
+      "step": 43
+    },
+    {
+      "epoch": 0.03773989492870162,
+      "grad_norm": 0.766008734703064,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1989,
+      "step": 44
+    },
+    {
+      "epoch": 0.03859761981344484,
+      "grad_norm": 0.9516524076461792,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1724,
+      "step": 45
+    },
+    {
+      "epoch": 0.03945534469818806,
+      "grad_norm": 1.9921557903289795,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1597,
+      "step": 46
+    },
+    {
+      "epoch": 0.04031306958293127,
+      "grad_norm": 1.784018635749817,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2322,
+      "step": 47
+    },
+    {
+      "epoch": 0.04117079446767449,
+      "grad_norm": 3.5011606216430664,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.256,
+      "step": 48
+    },
+    {
+      "epoch": 0.04202851935241771,
+      "grad_norm": 1.876481533050537,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.224,
+      "step": 49
+    },
+    {
+      "epoch": 0.042886244237160934,
+      "grad_norm": 2.9017508029937744,
+      "learning_rate": 0.0,
+      "loss": 0.2913,
+      "step": 50
+    },
+    {
+      "epoch": 0.042886244237160934,
+      "eval_loss": 0.2157745063304901,
+      "eval_runtime": 111.122,
+      "eval_samples_per_second": 70.688,
+      "eval_steps_per_second": 8.837,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.367151308931072e+16,
+  "total_flos": 1.2634971083846451e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null