Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ed2cf42aff71a90836bd7d70a644552d0441f07fe6e5bf5a29603d84ac56dc
+oid sha256:6ebfaec12a0bbd9025bc38a8a3dd89545001cf9bc0be2f6894946418a35e6b57
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be1ef5968c7a00b0a2e063f3abe16f836bd4ac13684eb407972a7f350970e5ac
+oid sha256:bfb93abbbd01f1a0fd1adc10d8368e94c0e9071c12be80645069cc37203abf8b
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb1fc1ef5366887d8bca7c9bb165980a5eb542993ef00905e920e083dc03112
+oid sha256:de774e93ee501b17eb81b112a023ed15ed30998ad6af8c361aa5ac3fbe9e75f7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f64f4e3e4968a3b4499fb4e6e17964aeca07554719f43324cc379c264389b6
+oid sha256:f8360cb91753a164d912aee60e815f87f78f8a96535578e085d430a2020ce4c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf7f530cb01d48aa85eafb9bf063d4d2fa00ccce7abe6fad96495f92fa192c0
+oid sha256:4dcfb30caf9a210623055c883f1640c1d64b1b2ed5df481d0e1d722f576ef7ab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a349c896105dd8e36f4ead1e81f911389e16cd2f8680c1ba8165546f82b76a9
+oid sha256:0738a35e3df6a8cc21015a1ef954efe222b314aa29831e50087dfa728521b8d5
 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": 0.8425735235214233,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5340453938584779,
+  "best_metric": 0.7348595261573792,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.081441922563418,
   "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": 80.451,
       "eval_steps_per_second": 10.184,
       "step": 25
+    },
+    {
+      "epoch": 0.5554072096128171,
+      "grad_norm": 2.1120316982269287,
+      "learning_rate": 5e-05,
+      "loss": 0.7252,
+      "step": 26
+    },
+    {
+      "epoch": 0.5767690253671562,
+      "grad_norm": 1.448875069618225,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6728,
+      "step": 27
+    },
+    {
+      "epoch": 0.5981308411214953,
+      "grad_norm": 0.9731662273406982,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5703,
+      "step": 28
+    },
+    {
+      "epoch": 0.6194926568758344,
+      "grad_norm": 1.6093170642852783,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6493,
+      "step": 29
+    },
+    {
+      "epoch": 0.6408544726301736,
+      "grad_norm": 1.569778323173523,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6615,
+      "step": 30
+    },
+    {
+      "epoch": 0.6622162883845126,
+      "grad_norm": 1.0836259126663208,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6269,
+      "step": 31
+    },
+    {
+      "epoch": 0.6835781041388518,
+      "grad_norm": 0.8956681489944458,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5857,
+      "step": 32
+    },
+    {
+      "epoch": 0.7049399198931909,
+      "grad_norm": 1.2497748136520386,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4974,
+      "step": 33
+    },
+    {
+      "epoch": 0.7263017356475301,
+      "grad_norm": 1.2253942489624023,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5433,
+      "step": 34
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 0.5431591272354126,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2895,
+      "step": 35
+    },
+    {
+      "epoch": 0.7690253671562083,
+      "grad_norm": 1.2693477869033813,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6153,
+      "step": 36
+    },
+    {
+      "epoch": 0.7903871829105474,
+      "grad_norm": 1.342617392539978,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7099,
+      "step": 37
+    },
+    {
+      "epoch": 0.8117489986648865,
+      "grad_norm": 0.7940839529037476,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5316,
+      "step": 38
+    },
+    {
+      "epoch": 0.8331108144192256,
+      "grad_norm": 1.0928740501403809,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6798,
+      "step": 39
+    },
+    {
+      "epoch": 0.8544726301735648,
+      "grad_norm": 1.2615504264831543,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5477,
+      "step": 40
+    },
+    {
+      "epoch": 0.8758344459279038,
+      "grad_norm": 0.9154185056686401,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6583,
+      "step": 41
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": 0.8197636008262634,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.549,
+      "step": 42
+    },
+    {
+      "epoch": 0.9185580774365821,
+      "grad_norm": 0.6741806268692017,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5017,
+      "step": 43
+    },
+    {
+      "epoch": 0.9399198931909212,
+      "grad_norm": 0.8679367899894714,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5409,
+      "step": 44
+    },
+    {
+      "epoch": 0.9612817089452603,
+      "grad_norm": 0.7181217670440674,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4768,
+      "step": 45
+    },
+    {
+      "epoch": 0.9826435246995995,
+      "grad_norm": 1.0969020128250122,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.49,
+      "step": 46
+    },
+    {
+      "epoch": 1.0173564753004005,
+      "grad_norm": 2.3091795444488525,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2256,
+      "step": 47
+    },
+    {
+      "epoch": 1.0387182910547397,
+      "grad_norm": 1.3182036876678467,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5804,
+      "step": 48
+    },
+    {
+      "epoch": 1.0600801068090788,
+      "grad_norm": 1.2283663749694824,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5296,
+      "step": 49
+    },
+    {
+      "epoch": 1.081441922563418,
+      "grad_norm": 1.7760813236236572,
+      "learning_rate": 0.0,
+      "loss": 0.5364,
+      "step": 50
+    },
+    {
+      "epoch": 1.081441922563418,
+      "eval_loss": 0.7348595261573792,
+      "eval_runtime": 3.9346,
+      "eval_samples_per_second": 80.314,
+      "eval_steps_per_second": 10.166,
+      "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": 5.327481232320102e+16,
+  "total_flos": 1.0648340363267277e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null