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:ae9af1173ad4aaab31d86d5c217e3a7b067a9982f4ce6deaf934832d2c00b4da
+oid sha256:044d37547202c8f3af0007219578a3936f0a4bf9a591e54513e5f03f8d6c08a7
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd7b93f241e7e4c347181ce1daad77323af370fe3f05b2a5ff92f23b7d1b125
+oid sha256:03f3581af99c8068647fb6d4b09475850c72f7eddba8026c1a1aac57da070516
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d6a5140c3d310ab8cd80e23bb0c49c0a02c8a17f2cbf4a8c007e4cde240bd2
+oid sha256:0f4d2b02d87c902ca441a86c6fc15b24eb8a6974f4b7f1d3469eb217237efc15
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdeeb4144832a1b3dc19b07696e36c1abb522393a31b30c2ff24138d5899e83a
+oid sha256:adcbed02b1e3293e937623c3b46dd578cd7021d27ae4de4aff406faad586ab06
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03f1bf15ba0cfce3e6ae7a5dbf4adf9fd1b4a4f59a834d38baf972258b9be9d
+oid sha256:7d947124b4356cf44cf395ff75ede8a581733355431e54a401fd7bf4a8bbd94e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5323ce153e43e05e439a6388a56ea2b7074da740b3d736506d811e440aa1ee1b
+oid sha256:6dbd638288f0f874d71d90d54901314288597c1cf0f954fbfdd53bdbd380ac89
 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": 2.268191337585449,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.41025641025641024,
+  "best_metric": 2.253286123275757,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8205128205128205,
   "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": 75.895,
       "eval_steps_per_second": 9.602,
       "step": 25
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0765756294131279,
+      "learning_rate": 5e-05,
+      "loss": 2.3111,
+      "step": 26
+    },
+    {
+      "epoch": 0.4430769230769231,
+      "grad_norm": 0.08956744521856308,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3291,
+      "step": 27
+    },
+    {
+      "epoch": 0.4594871794871795,
+      "grad_norm": 0.10433879494667053,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.321,
+      "step": 28
+    },
+    {
+      "epoch": 0.4758974358974359,
+      "grad_norm": 0.12222084403038025,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3884,
+      "step": 29
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.13194355368614197,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.3473,
+      "step": 30
+    },
+    {
+      "epoch": 0.5087179487179487,
+      "grad_norm": 0.14553877711296082,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.3531,
+      "step": 31
+    },
+    {
+      "epoch": 0.5251282051282051,
+      "grad_norm": 0.1670655906200409,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3598,
+      "step": 32
+    },
+    {
+      "epoch": 0.5415384615384615,
+      "grad_norm": 0.18873582780361176,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.3712,
+      "step": 33
+    },
+    {
+      "epoch": 0.5579487179487179,
+      "grad_norm": 0.19720564782619476,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3851,
+      "step": 34
+    },
+    {
+      "epoch": 0.5743589743589743,
+      "grad_norm": 0.22771696746349335,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2665,
+      "step": 35
+    },
+    {
+      "epoch": 0.5907692307692308,
+      "grad_norm": 0.23396721482276917,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.302,
+      "step": 36
+    },
+    {
+      "epoch": 0.6071794871794872,
+      "grad_norm": 0.2983793616294861,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2401,
+      "step": 37
+    },
+    {
+      "epoch": 0.6235897435897436,
+      "grad_norm": 0.08449523895978928,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3447,
+      "step": 38
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.07961072027683258,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.3006,
+      "step": 39
+    },
+    {
+      "epoch": 0.6564102564102564,
+      "grad_norm": 0.0954764187335968,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.354,
+      "step": 40
+    },
+    {
+      "epoch": 0.6728205128205128,
+      "grad_norm": 0.11071515828371048,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.3124,
+      "step": 41
+    },
+    {
+      "epoch": 0.6892307692307692,
+      "grad_norm": 0.12081477046012878,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3707,
+      "step": 42
+    },
+    {
+      "epoch": 0.7056410256410256,
+      "grad_norm": 0.1372407227754593,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3573,
+      "step": 43
+    },
+    {
+      "epoch": 0.7220512820512821,
+      "grad_norm": 0.14904159307479858,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.303,
+      "step": 44
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.16220468282699585,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.3307,
+      "step": 45
+    },
+    {
+      "epoch": 0.7548717948717949,
+      "grad_norm": 0.18126922845840454,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3042,
+      "step": 46
+    },
+    {
+      "epoch": 0.7712820512820513,
+      "grad_norm": 0.1950266808271408,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2016,
+      "step": 47
+    },
+    {
+      "epoch": 0.7876923076923077,
+      "grad_norm": 0.2183115929365158,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.243,
+      "step": 48
+    },
+    {
+      "epoch": 0.8041025641025641,
+      "grad_norm": 0.2518211305141449,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1715,
+      "step": 49
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 0.36862725019454956,
+      "learning_rate": 0.0,
+      "loss": 2.2768,
+      "step": 50
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "eval_loss": 2.253286123275757,
+      "eval_runtime": 5.4183,
+      "eval_samples_per_second": 75.854,
+      "eval_steps_per_second": 9.597,
+      "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": 5.522833269797683e+16,
+  "total_flos": 1.1005933877670707e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null