Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b48d861f0b8251e75c28b77ac836ab52fada76655a5823a0aa75b42e2abadfc
+oid sha256:e68d44be9c285fb71dc1b703a6277ce68d91cfb5f33b09fbd4406ac6b905f170
 size 498804568

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d0ae15a4f2c0ef8a01bba3b001600e4bc911240bf7231aef579300b8a54f59
+oid sha256:5ebe475ff56fcc1a71a1266d1d925d74fd540e871a91c8283d9adf8a2a67424b
 size 997931362

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f27d02e88a7cd525d0bcba3b1fab975417bc68459b8a5ea3c9e3740b7dda44
+oid sha256:cfc3181b9b0a3cf353d39dc1b3cd79363987574cce9cb8a6d4675eedd41a8e65
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8f64f6555c220fff99a66668f97dcefc752cba5f8276dff3d3203ffb494624
+oid sha256:ad19df10e9ddc082a60de4fbd9a1c14f2f4b0443a4a75bc6ba2d653dfd15ec93
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0856d45485fb50567419b2ccce1dffb1636d7b003cb3c902d08b4aff805dbfdc
+oid sha256:246039295e3e44141a7203c84874cca0e24b74c196e7f8bf8995130a5225db4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97422e674366147420ae817995a50a96de7ec3ab3c87ef53dd341a3f4c4a1d4
+oid sha256:79840ebd984a9961d0b81d51dda6f4f18201a7f2ad603099d1898d81fe90234b
 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": 1.0806931257247925,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.075268817204301,
+  "best_metric": 0.7887606024742126,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.150537634408602,
   "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": 19.736,
       "eval_steps_per_second": 2.514,
       "step": 25
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 4.576476097106934,
+      "learning_rate": 5e-05,
+      "loss": 1.2379,
+      "step": 26
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 3.7548060417175293,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0289,
+      "step": 27
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 3.2624807357788086,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9353,
+      "step": 28
+    },
+    {
+      "epoch": 1.2473118279569892,
+      "grad_norm": 5.262892246246338,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3024,
+      "step": 29
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 3.8155572414398193,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9858,
+      "step": 30
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 4.295482158660889,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0545,
+      "step": 31
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 2.9629807472229004,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1583,
+      "step": 32
+    },
+    {
+      "epoch": 1.4193548387096775,
+      "grad_norm": 3.3191750049591064,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9557,
+      "step": 33
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 2.754456043243408,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8508,
+      "step": 34
+    },
+    {
+      "epoch": 1.5053763440860215,
+      "grad_norm": 2.761148691177368,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0884,
+      "step": 35
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 2.2412075996398926,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.702,
+      "step": 36
+    },
+    {
+      "epoch": 1.5913978494623655,
+      "grad_norm": 3.087839365005493,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8207,
+      "step": 37
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 2.7227118015289307,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.909,
+      "step": 38
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": 2.712979555130005,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8866,
+      "step": 39
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 2.3975188732147217,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7952,
+      "step": 40
+    },
+    {
+      "epoch": 1.7634408602150538,
+      "grad_norm": 2.380941152572632,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8558,
+      "step": 41
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 1.8597089052200317,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6109,
+      "step": 42
+    },
+    {
+      "epoch": 1.849462365591398,
+      "grad_norm": 3.6962974071502686,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7898,
+      "step": 43
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 3.9587137699127197,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.906,
+      "step": 44
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.634704351425171,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7133,
+      "step": 45
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 2.543936014175415,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8129,
+      "step": 46
+    },
+    {
+      "epoch": 2.021505376344086,
+      "grad_norm": 5.290590286254883,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3649,
+      "step": 47
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 1.4306670427322388,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6567,
+      "step": 48
+    },
+    {
+      "epoch": 2.10752688172043,
+      "grad_norm": 2.4674768447875977,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8203,
+      "step": 49
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 1.742997407913208,
+      "learning_rate": 0.0,
+      "loss": 0.8144,
+      "step": 50
+    },
+    {
+      "epoch": 2.150537634408602,
+      "eval_loss": 0.7887606024742126,
+      "eval_runtime": 7.9519,
+      "eval_samples_per_second": 19.744,
+      "eval_steps_per_second": 2.515,
+      "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": 5.313687367712768e+17,
+  "total_flos": 1.0627374735425536e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null