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:c92c5abe6adfe9fa76fab4c302b19825843d41f206f657441b2d30d1bcd6a9d8
+oid sha256:a45ccf3a453d6a9a556f2abd9028bd62a5a935537e239e020f620bff548d4006
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1568d384f51e0c0a6e4ceddb28dcfb60eeb7199ea335259606278f81ad11fe50
+oid sha256:852f120e4ef1108aaf3a8fb0b642fc6a8ada2ffab6e8b98bc7635ac76d13aff2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:008d23f95d472be06b6f105efc2ad34e76643ecc77697de914fbe14df365ced6
+oid sha256:9be115b3fb300169dc4d1bf37b33dc8bc71afdd9ab912345de2170aec0b921a0
 size 15024

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": 0.22793392837047577,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18709073900841908,
+  "best_metric": 0.10144082456827164,
+  "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": 34.192,
       "eval_steps_per_second": 4.288,
       "step": 25
+    },
+    {
+      "epoch": 0.19457436856875585,
+      "grad_norm": 88.36663818359375,
+      "learning_rate": 5e-05,
+      "loss": 0.4986,
+      "step": 26
+    },
+    {
+      "epoch": 0.20205799812909261,
+      "grad_norm": 71.94731903076172,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4428,
+      "step": 27
+    },
+    {
+      "epoch": 0.20954162768942938,
+      "grad_norm": 38.94894027709961,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3858,
+      "step": 28
+    },
+    {
+      "epoch": 0.21702525724976612,
+      "grad_norm": 46.135990142822266,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3197,
+      "step": 29
+    },
+    {
+      "epoch": 0.2245088868101029,
+      "grad_norm": 178.49417114257812,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1487,
+      "step": 30
+    },
+    {
+      "epoch": 0.23199251637043966,
+      "grad_norm": 62.31162643432617,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0742,
+      "step": 31
+    },
+    {
+      "epoch": 0.23947614593077643,
+      "grad_norm": 33.370609283447266,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0345,
+      "step": 32
+    },
+    {
+      "epoch": 0.2469597754911132,
+      "grad_norm": 17.26993751525879,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0258,
+      "step": 33
+    },
+    {
+      "epoch": 0.25444340505144997,
+      "grad_norm": 14.258871078491211,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.027,
+      "step": 34
+    },
+    {
+      "epoch": 0.26192703461178674,
+      "grad_norm": 11.711955070495605,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0188,
+      "step": 35
+    },
+    {
+      "epoch": 0.2694106641721235,
+      "grad_norm": 14.561089515686035,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0255,
+      "step": 36
+    },
+    {
+      "epoch": 0.2768942937324602,
+      "grad_norm": 8.522704124450684,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0103,
+      "step": 37
+    },
+    {
+      "epoch": 0.284377923292797,
+      "grad_norm": 665.8914794921875,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8397,
+      "step": 38
+    },
+    {
+      "epoch": 0.29186155285313375,
+      "grad_norm": 717.4110717773438,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8972,
+      "step": 39
+    },
+    {
+      "epoch": 0.2993451824134705,
+      "grad_norm": 291.5386047363281,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5768,
+      "step": 40
+    },
+    {
+      "epoch": 0.3068288119738073,
+      "grad_norm": 176.5371551513672,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4695,
+      "step": 41
+    },
+    {
+      "epoch": 0.31431244153414406,
+      "grad_norm": 60.231441497802734,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2442,
+      "step": 42
+    },
+    {
+      "epoch": 0.32179607109448083,
+      "grad_norm": 14.835460662841797,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0233,
+      "step": 43
+    },
+    {
+      "epoch": 0.3292797006548176,
+      "grad_norm": 6.386807918548584,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.011,
+      "step": 44
+    },
+    {
+      "epoch": 0.33676333021515437,
+      "grad_norm": 10.121891975402832,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0239,
+      "step": 45
+    },
+    {
+      "epoch": 0.34424695977549113,
+      "grad_norm": 11.264687538146973,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0104,
+      "step": 46
+    },
+    {
+      "epoch": 0.3517305893358279,
+      "grad_norm": 7.20819091796875,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0104,
+      "step": 47
+    },
+    {
+      "epoch": 0.3592142188961646,
+      "grad_norm": 9.249587059020996,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0109,
+      "step": 48
+    },
+    {
+      "epoch": 0.3666978484565014,
+      "grad_norm": 19.556489944458008,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0141,
+      "step": 49
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "grad_norm": 106.16588592529297,
+      "learning_rate": 0.0,
+      "loss": 0.016,
+      "step": 50
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "eval_loss": 0.10144082456827164,
+      "eval_runtime": 26.358,
+      "eval_samples_per_second": 34.183,
+      "eval_steps_per_second": 4.287,
+      "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