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:c3bec104e5220b17b99b80e6c7fcb12bee70eef3a2b2d06b66773a27b12e24f5
+oid sha256:084f657a6410a41ee1a28e996aa901ba3e5b28627f97e3b2168bd2f866d6258c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d68ce9b88b761c30c9326363a0b19d44b0ebd127664666edd465966951a5c6
+oid sha256:e5facc060745567024d26cc5af5cb29c31745b518eb4859632a3e55aaf7e4231
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22a984101aad3d120e721c9d4ca276e9b369d337c5f5829d084f63352d40673
+oid sha256:1ffbf2f14f91f7cca1de9e69db11356084d6b4a2ed7894eedd141648cb0d9a79
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d505ce59b3ba14c7f78895a853337ae88a447612f99b5133ef7806b856bb5a9
+oid sha256:ab7897f0d4d5dcfd5be2d5d3564ac289d8ddb932ed435698cbb3c44c5c399916
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd333cb13bbbdb4c0b9e8814897d13b40b860564e46271095465fe2b6e91ecb4
+oid sha256:199a00579383281c722b724e2945b4c971ee1db0e381f26639c63850b9ea652a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:264d54565e9891add9915dadd1f2dda4df4e97eefed4cacff2aedcd526ba03d3
+oid sha256:39fd7d1c06a8536b112d6fb00f057dd5b289cdcdede786b7a861eb55d6eaef2b
 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": 0.20019382238388062,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18709073900841908,
+  "best_metric": 0.09737779200077057,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.37418147801683815,
   "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": 34.326,
       "eval_steps_per_second": 4.305,
       "step": 25
+    },
+    {
+      "epoch": 0.19457436856875585,
+      "grad_norm": 134.28933715820312,
+      "learning_rate": 5e-05,
+      "loss": 0.5206,
+      "step": 26
+    },
+    {
+      "epoch": 0.20205799812909261,
+      "grad_norm": 90.19445037841797,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4137,
+      "step": 27
+    },
+    {
+      "epoch": 0.20954162768942938,
+      "grad_norm": 30.906604766845703,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3565,
+      "step": 28
+    },
+    {
+      "epoch": 0.21702525724976612,
+      "grad_norm": 47.67278289794922,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3031,
+      "step": 29
+    },
+    {
+      "epoch": 0.2245088868101029,
+      "grad_norm": 38.380367279052734,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.119,
+      "step": 30
+    },
+    {
+      "epoch": 0.23199251637043966,
+      "grad_norm": 40.00833511352539,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0969,
+      "step": 31
+    },
+    {
+      "epoch": 0.23947614593077643,
+      "grad_norm": 125.88969421386719,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0652,
+      "step": 32
+    },
+    {
+      "epoch": 0.2469597754911132,
+      "grad_norm": 16.30948257446289,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0244,
+      "step": 33
+    },
+    {
+      "epoch": 0.25444340505144997,
+      "grad_norm": 7.882120132446289,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0111,
+      "step": 34
+    },
+    {
+      "epoch": 0.26192703461178674,
+      "grad_norm": 10.894170761108398,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0194,
+      "step": 35
+    },
+    {
+      "epoch": 0.2694106641721235,
+      "grad_norm": 17.481016159057617,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0125,
+      "step": 36
+    },
+    {
+      "epoch": 0.2768942937324602,
+      "grad_norm": 8.537217140197754,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0026,
+      "step": 37
+    },
+    {
+      "epoch": 0.284377923292797,
+      "grad_norm": 59.2493896484375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2544,
+      "step": 38
+    },
+    {
+      "epoch": 0.29186155285313375,
+      "grad_norm": 69.87789916992188,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3332,
+      "step": 39
+    },
+    {
+      "epoch": 0.2993451824134705,
+      "grad_norm": 62.049102783203125,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3479,
+      "step": 40
+    },
+    {
+      "epoch": 0.3068288119738073,
+      "grad_norm": 47.844940185546875,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3231,
+      "step": 41
+    },
+    {
+      "epoch": 0.31431244153414406,
+      "grad_norm": 32.43928146362305,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1896,
+      "step": 42
+    },
+    {
+      "epoch": 0.32179607109448083,
+      "grad_norm": 17.590641021728516,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0433,
+      "step": 43
+    },
+    {
+      "epoch": 0.3292797006548176,
+      "grad_norm": 16.18429946899414,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0399,
+      "step": 44
+    },
+    {
+      "epoch": 0.33676333021515437,
+      "grad_norm": 8.45818042755127,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0182,
+      "step": 45
+    },
+    {
+      "epoch": 0.34424695977549113,
+      "grad_norm": 13.13820743560791,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0156,
+      "step": 46
+    },
+    {
+      "epoch": 0.3517305893358279,
+      "grad_norm": 7.652195930480957,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0156,
+      "step": 47
+    },
+    {
+      "epoch": 0.3592142188961646,
+      "grad_norm": 12.8060884475708,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0252,
+      "step": 48
+    },
+    {
+      "epoch": 0.3666978484565014,
+      "grad_norm": 6.800826549530029,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0051,
+      "step": 49
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "grad_norm": 6.836678981781006,
+      "learning_rate": 0.0,
+      "loss": 0.0027,
+      "step": 50
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "eval_loss": 0.09737779200077057,
+      "eval_runtime": 26.2411,
+      "eval_samples_per_second": 34.335,
+      "eval_steps_per_second": 4.306,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null