Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1442ad3fd9341d08500712b240f6e66385443e438497a278d2fc591efe6da52b
+oid sha256:1a93b485d9f57d1b07fefd905fc14c0a7f15109c7ae74d882b2367b6b3d8e719
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543c53536b4c1b16284420ba9ab7364f315d13271a6c8649be24a91127d9c891
+oid sha256:c177b76257602b13b0f3c1f6c22791bd7b4014a9262aec1e868395eb2bddc98e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c4d8fc23197ea1aad6eeb66193dca6900fd38b167672ab7a849cca3f318249
+oid sha256:80176c0fad6fcfe8e4ae37a6c40fce76dc0639d9a3f1d25e372765f2573dc4ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c385c2367cee9050da33bd1b747366bb4ae0f3eec3f2365bd8705d70b415e8
+oid sha256:72d4218c914ae87a27e06828bf0297cc254e636755939bf22bbc7d16adb16269
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c85b0ee00390d074383ae8ccb3140309b05505bf389b14875f08b94c5cf6a4
+oid sha256:6d937d0df8149f7edb26ac82c757890602869c5da77b81d7544ae381588602ae
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407dd0cab4f5409a36630fee399679a694f6d3c4e30db4813ae6fefdb0508b57
+oid sha256:213a7ffe0f34afa1bdb4794d03616c531d85a89b33c398887989ecca82250f77
 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": 0.0022325909230858088,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06363347120585428,
+  "best_metric": 0.0015694969333708286,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12726694241170855,
   "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": 20.132,
       "eval_steps_per_second": 2.517,
       "step": 25
+    },
+    {
+      "epoch": 0.06617881005408845,
+      "grad_norm": 0.02771487459540367,
+      "learning_rate": 5e-05,
+      "loss": 0.0006,
+      "step": 26
+    },
+    {
+      "epoch": 0.06872414890232262,
+      "grad_norm": 0.3581013083457947,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0026,
+      "step": 27
+    },
+    {
+      "epoch": 0.07126948775055679,
+      "grad_norm": 0.17332956194877625,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0013,
+      "step": 28
+    },
+    {
+      "epoch": 0.07381482659879096,
+      "grad_norm": 0.04999712109565735,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0006,
+      "step": 29
+    },
+    {
+      "epoch": 0.07636016544702513,
+      "grad_norm": 0.01677992381155491,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0003,
+      "step": 30
+    },
+    {
+      "epoch": 0.0789055042952593,
+      "grad_norm": 0.008356700651347637,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0003,
+      "step": 31
+    },
+    {
+      "epoch": 0.08145084314349348,
+      "grad_norm": 0.011792369186878204,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.08399618199172765,
+      "grad_norm": 0.03631852939724922,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.08654152083996182,
+      "grad_norm": 0.004105123691260815,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0002,
+      "step": 34
+    },
+    {
+      "epoch": 0.08908685968819599,
+      "grad_norm": 0.007662076968699694,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0003,
+      "step": 35
+    },
+    {
+      "epoch": 0.09163219853643016,
+      "grad_norm": 0.005889294669032097,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0002,
+      "step": 36
+    },
+    {
+      "epoch": 0.09417753738466433,
+      "grad_norm": 1.1749862432479858,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0066,
+      "step": 37
+    },
+    {
+      "epoch": 0.0967228762328985,
+      "grad_norm": 0.03878513351082802,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0003,
+      "step": 38
+    },
+    {
+      "epoch": 0.09926821508113268,
+      "grad_norm": 0.00471383985131979,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 0.10181355392936685,
+      "grad_norm": 0.004265178926289082,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.10435889277760102,
+      "grad_norm": 0.004452875815331936,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0002,
+      "step": 41
+    },
+    {
+      "epoch": 0.10690423162583519,
+      "grad_norm": 0.0047661480493843555,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.10944957047406936,
+      "grad_norm": 0.004124505445361137,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0002,
+      "step": 43
+    },
+    {
+      "epoch": 0.11199490932230353,
+      "grad_norm": 0.0037059446331113577,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.1145402481705377,
+      "grad_norm": 0.003210233524441719,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.11708558701877188,
+      "grad_norm": 0.003240456571802497,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.11963092586700605,
+      "grad_norm": 0.004116287920624018,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.12217626471524022,
+      "grad_norm": 0.006474327761679888,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 0.12472160356347439,
+      "grad_norm": 0.007355257868766785,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.12726694241170855,
+      "grad_norm": 10.613334655761719,
+      "learning_rate": 0.0,
+      "loss": 1.0866,
+      "step": 50
+    },
+    {
+      "epoch": 0.12726694241170855,
+      "eval_loss": 0.0015694969333708286,
+      "eval_runtime": 133.4738,
+      "eval_samples_per_second": 19.832,
+      "eval_steps_per_second": 2.48,
+      "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": 2.631221648430203e+17,
+  "total_flos": 5.260799806149755e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null