Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919629236b0b83a90acad1df064e9abda0b90a14854a453c0b8f7f0ec1f19ec3
+oid sha256:7ece964991d7ad0e579e8f6380c5f049b16cb4c7e2fb059c8220f7363c793e39
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3491b10cdbea7ce9f9fbfaf144537ea620cace5d55ef7e77933c5622310758
+oid sha256:7cc8f235e39faba8eef38b02394597de5b7e8cfbc8dcc85080dc0900e5d80ef0
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6856f97bd953c68e1e9e328fc15b4e7b2f9aa7922de5401a7af72d0cca64f7ae
+oid sha256:0ac1a143051d0e6be2b7672f573918ede55fbce8313de515ffc3ad04f719a183
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9aac30fd87aa2f7f0e8a6d79b3a366c6efd17bba24eaa7fa2e6b4bab2720244
+oid sha256:e9939b188a82aa9cc735897dc3acad13c5479b3b28b4e5289c4f0ceac6292bdb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df4a6a251e6cb8c5e39ae02a7dbf5ee77069fd8913c6dec177f41f3ffc3a69b
+oid sha256:f77dda86f427cc2c8528ac8b631ddeb0c02eb894798373b08a6505ddf0767747
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b160a30aea136979272a166d068da015321a3fc14b51236afad67861db5068e8
+oid sha256:1f74032e0366a77f6945a554d3f7c8a73ca227426fab31f03716b55e40aa9bae
 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": 1.5409281253814697,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010366722819748608,
+  "best_metric": 1.4669657945632935,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020733445639497215,
   "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": 16.066,
       "eval_steps_per_second": 2.008,
       "step": 25
+    },
+    {
+      "epoch": 0.010781391732538552,
+      "grad_norm": 0.7177833318710327,
+      "learning_rate": 5e-05,
+      "loss": 1.6508,
+      "step": 26
+    },
+    {
+      "epoch": 0.011196060645328496,
+      "grad_norm": 0.9440976977348328,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6868,
+      "step": 27
+    },
+    {
+      "epoch": 0.01161072955811844,
+      "grad_norm": 0.9967230558395386,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6338,
+      "step": 28
+    },
+    {
+      "epoch": 0.012025398470908385,
+      "grad_norm": 0.966355562210083,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.5745,
+      "step": 29
+    },
+    {
+      "epoch": 0.01244006738369833,
+      "grad_norm": 0.8293948173522949,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5831,
+      "step": 30
+    },
+    {
+      "epoch": 0.012854736296488273,
+      "grad_norm": 0.7298887968063354,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.5556,
+      "step": 31
+    },
+    {
+      "epoch": 0.013269405209278218,
+      "grad_norm": 0.5840082168579102,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.517,
+      "step": 32
+    },
+    {
+      "epoch": 0.013684074122068162,
+      "grad_norm": 0.4378565847873688,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.4803,
+      "step": 33
+    },
+    {
+      "epoch": 0.014098743034858105,
+      "grad_norm": 0.2756096124649048,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4003,
+      "step": 34
+    },
+    {
+      "epoch": 0.014513411947648049,
+      "grad_norm": 0.5180824398994446,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4261,
+      "step": 35
+    },
+    {
+      "epoch": 0.014928080860437993,
+      "grad_norm": 1.0332447290420532,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4312,
+      "step": 36
+    },
+    {
+      "epoch": 0.015342749773227938,
+      "grad_norm": 1.712068796157837,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3713,
+      "step": 37
+    },
+    {
+      "epoch": 0.015757418686017884,
+      "grad_norm": 0.2424265742301941,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5584,
+      "step": 38
+    },
+    {
+      "epoch": 0.016172087598807828,
+      "grad_norm": 0.40940093994140625,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5647,
+      "step": 39
+    },
+    {
+      "epoch": 0.016586756511597772,
+      "grad_norm": 0.4156504273414612,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5799,
+      "step": 40
+    },
+    {
+      "epoch": 0.017001425424387717,
+      "grad_norm": 0.3541248142719269,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5562,
+      "step": 41
+    },
+    {
+      "epoch": 0.01741609433717766,
+      "grad_norm": 0.3113373816013336,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5103,
+      "step": 42
+    },
+    {
+      "epoch": 0.017830763249967605,
+      "grad_norm": 0.24495618045330048,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.4807,
+      "step": 43
+    },
+    {
+      "epoch": 0.01824543216275755,
+      "grad_norm": 0.22791069746017456,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.474,
+      "step": 44
+    },
+    {
+      "epoch": 0.018660101075547494,
+      "grad_norm": 0.3220486342906952,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4798,
+      "step": 45
+    },
+    {
+      "epoch": 0.019074769988337438,
+      "grad_norm": 0.621979832649231,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.431,
+      "step": 46
+    },
+    {
+      "epoch": 0.019489438901127382,
+      "grad_norm": 0.7313467860221863,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3923,
+      "step": 47
+    },
+    {
+      "epoch": 0.019904107813917327,
+      "grad_norm": 1.0231751203536987,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4261,
+      "step": 48
+    },
+    {
+      "epoch": 0.02031877672670727,
+      "grad_norm": 1.4127227067947388,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.4077,
+      "step": 49
+    },
+    {
+      "epoch": 0.020733445639497215,
+      "grad_norm": 2.6152594089508057,
+      "learning_rate": 0.0,
+      "loss": 1.2716,
+      "step": 50
+    },
+    {
+      "epoch": 0.020733445639497215,
+      "eval_loss": 1.4669657945632935,
+      "eval_runtime": 848.7671,
+      "eval_samples_per_second": 19.142,
+      "eval_steps_per_second": 2.393,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null