Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0374e09677a8d86a7a2a48fbec0fb6af05464060dace58b0aa68277463b3fe94
+oid sha256:d6b71294dad63415fae2f5338f07bd36c7f1aa90a9c441e0f313aa0af2634db1
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681c9f685e588483367b87b486010f4fe6d9ec46b4812e1df476853e7cb7ca77
+oid sha256:8b275011acba662806ca51cc151acfef22bbaabd69958c542e88792983d4aadf
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccd438b16dfb23abd476fe1239a0dfae25da9efd6ef99fa1427161e85a6293b
+oid sha256:166aceadce1affcbb99008463a30113040d5754800857fccd13f04a77e5b2614
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4314c9969b4f008fb1e76b934c051e7538392452a16960c1b2bd2465ade119c1
+oid sha256:e40fc5397ff7b78c379c52f1df581cf4dc93e9c1ac2d9863dd0611e4a6bb38b8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf962592d459b2392a5ba49ddd233db14b83baa60015e967932546c8bc64a91
+oid sha256:d9604dbaa8c871ed51cf5f1b0feee44235c820ec360762a0d19e7644b5e4cc59
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f77da63529c8eeda4af0fc212292dc237a51d7ad107c8da531054a2e2ae7869
+oid sha256:16b1ceb13d8683ec52c5fcd610c4463cd458a30335edcc7d72a851fccc2e4920
 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": 1.3804173469543457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1316655694535879,
+  "best_metric": 1.3594727516174316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2633311389071758,
   "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": 93.219,
       "eval_steps_per_second": 5.831,
       "step": 25
+    },
+    {
+      "epoch": 0.1369321922317314,
+      "grad_norm": 0.10845153033733368,
+      "learning_rate": 5e-05,
+      "loss": 1.0823,
+      "step": 26
+    },
+    {
+      "epoch": 0.1421988150098749,
+      "grad_norm": 0.12122660130262375,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.068,
+      "step": 27
+    },
+    {
+      "epoch": 0.14746543778801843,
+      "grad_norm": 0.13943496346473694,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1514,
+      "step": 28
+    },
+    {
+      "epoch": 0.15273206056616195,
+      "grad_norm": 0.16596482694149017,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1358,
+      "step": 29
+    },
+    {
+      "epoch": 0.15799868334430547,
+      "grad_norm": 0.28701385855674744,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2192,
+      "step": 30
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.5179040431976318,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3186,
+      "step": 31
+    },
+    {
+      "epoch": 0.1685319289005925,
+      "grad_norm": 0.6661813855171204,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3722,
+      "step": 32
+    },
+    {
+      "epoch": 0.173798551678736,
+      "grad_norm": 0.8054024577140808,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3638,
+      "step": 33
+    },
+    {
+      "epoch": 0.17906517445687953,
+      "grad_norm": 0.8425301313400269,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.452,
+      "step": 34
+    },
+    {
+      "epoch": 0.18433179723502305,
+      "grad_norm": 0.8511418104171753,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4588,
+      "step": 35
+    },
+    {
+      "epoch": 0.18959842001316657,
+      "grad_norm": 0.693630039691925,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.571,
+      "step": 36
+    },
+    {
+      "epoch": 0.19486504279131006,
+      "grad_norm": 0.9213873147964478,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8619,
+      "step": 37
+    },
+    {
+      "epoch": 0.20013166556945358,
+      "grad_norm": 0.1158779114484787,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0672,
+      "step": 38
+    },
+    {
+      "epoch": 0.2053982883475971,
+      "grad_norm": 0.10753665119409561,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.107,
+      "step": 39
+    },
+    {
+      "epoch": 0.21066491112574062,
+      "grad_norm": 0.11137895286083221,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1033,
+      "step": 40
+    },
+    {
+      "epoch": 0.21593153390388414,
+      "grad_norm": 0.12284540385007858,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1007,
+      "step": 41
+    },
+    {
+      "epoch": 0.22119815668202766,
+      "grad_norm": 0.12770262360572815,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1736,
+      "step": 42
+    },
+    {
+      "epoch": 0.22646477946017116,
+      "grad_norm": 0.13465799391269684,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1704,
+      "step": 43
+    },
+    {
+      "epoch": 0.23173140223831468,
+      "grad_norm": 0.1592033952474594,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2186,
+      "step": 44
+    },
+    {
+      "epoch": 0.2369980250164582,
+      "grad_norm": 0.25981563329696655,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3009,
+      "step": 45
+    },
+    {
+      "epoch": 0.24226464779460172,
+      "grad_norm": 0.3332749009132385,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3673,
+      "step": 46
+    },
+    {
+      "epoch": 0.24753127057274524,
+      "grad_norm": 0.4068727195262909,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5235,
+      "step": 47
+    },
+    {
+      "epoch": 0.25279789335088876,
+      "grad_norm": 0.48335689306259155,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.557,
+      "step": 48
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.6301862001419067,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7907,
+      "step": 49
+    },
+    {
+      "epoch": 0.2633311389071758,
+      "grad_norm": 1.721063256263733,
+      "learning_rate": 0.0,
+      "loss": 2.1814,
+      "step": 50
+    },
+    {
+      "epoch": 0.2633311389071758,
+      "eval_loss": 1.3594727516174316,
+      "eval_runtime": 27.9639,
+      "eval_samples_per_second": 91.475,
+      "eval_steps_per_second": 5.722,
+      "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": 1.059536353886208e+17,
+  "total_flos": 2.119072707772416e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null