Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2189b5a4893b96774c6d7666e7d04eb27f101aca15dbb34685c840f74bc7cd23
+oid sha256:fd47974216cc03421d647d6d00ce1f3da6e2432747858c7bbcc9ce8bf80414fb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfa0f0fab6a8cf6c52a333d2be93cec4ef3bd37d59b5de82955148cbf42fc02
+oid sha256:3ccb5cd874ad31ee955f80ca5d053de57408037a963d5e9605366d966d9d38bb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bff9b3b799d91b5cd41ac87242c9f0a05e46a494063ebbd52c4409ac61fe547
+oid sha256:7c6017c402e9dc7cf6359f8161fdd50cd25c42c0914cb2b16e4ffb50bfd129e6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6a472a3525db046b690012ee04cda4fc60ae0a4038d59f50373c897e897b14
+oid sha256:23cec556d53b75d46031bb087cd9e08410569e24387fc2cf7522ad24967de378
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1ebd5956b13b7509e61f8cb84d36cea3eb1f933e0c646bbdba0c0f0749da03
+oid sha256:d92dac097c4d14c28f76c37c8aa96ba2da127b8d2a05cc3f889a5e42e29e4adc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120682cbea57f6b3c32ea8188f4da6a6e32a8898bdc0de6826bc0be2bdd131b5
+oid sha256:1db311a351fbf3a54dd561ecb041e9ed714f60d2fc61b79be6adec0baf88848a
 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": 3.822291851043701,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13745704467353953,
+  "best_metric": 3.0637059211730957,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.27491408934707906,
   "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": 37.663,
       "eval_steps_per_second": 4.735,
       "step": 25
+    },
+    {
+      "epoch": 0.1429553264604811,
+      "grad_norm": 5.419510364532471,
+      "learning_rate": 5e-05,
+      "loss": 3.8078,
+      "step": 26
+    },
+    {
+      "epoch": 0.14845360824742268,
+      "grad_norm": 4.982654571533203,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.3511,
+      "step": 27
+    },
+    {
+      "epoch": 0.15395189003436427,
+      "grad_norm": 6.311149597167969,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.5434,
+      "step": 28
+    },
+    {
+      "epoch": 0.15945017182130583,
+      "grad_norm": 5.579045295715332,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.3358,
+      "step": 29
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 5.663218021392822,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.3071,
+      "step": 30
+    },
+    {
+      "epoch": 0.170446735395189,
+      "grad_norm": 4.017464637756348,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.5254,
+      "step": 31
+    },
+    {
+      "epoch": 0.1759450171821306,
+      "grad_norm": 5.227976322174072,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.3985,
+      "step": 32
+    },
+    {
+      "epoch": 0.18144329896907216,
+      "grad_norm": 4.223237991333008,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.485,
+      "step": 33
+    },
+    {
+      "epoch": 0.18694158075601375,
+      "grad_norm": 4.4165802001953125,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.1429,
+      "step": 34
+    },
+    {
+      "epoch": 0.19243986254295534,
+      "grad_norm": 5.69273567199707,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.0846,
+      "step": 35
+    },
+    {
+      "epoch": 0.1979381443298969,
+      "grad_norm": 3.754176378250122,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.0226,
+      "step": 36
+    },
+    {
+      "epoch": 0.2034364261168385,
+      "grad_norm": 3.810027837753296,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.144,
+      "step": 37
+    },
+    {
+      "epoch": 0.20893470790378008,
+      "grad_norm": 4.153249263763428,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.7011,
+      "step": 38
+    },
+    {
+      "epoch": 0.21443298969072164,
+      "grad_norm": 7.607944011688232,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2281,
+      "step": 39
+    },
+    {
+      "epoch": 0.21993127147766323,
+      "grad_norm": 5.7672271728515625,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.4422,
+      "step": 40
+    },
+    {
+      "epoch": 0.22542955326460482,
+      "grad_norm": 5.408945560455322,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.7773,
+      "step": 41
+    },
+    {
+      "epoch": 0.2309278350515464,
+      "grad_norm": 4.62959098815918,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.0449,
+      "step": 42
+    },
+    {
+      "epoch": 0.23642611683848797,
+      "grad_norm": 4.441442489624023,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.7026,
+      "step": 43
+    },
+    {
+      "epoch": 0.24192439862542955,
+      "grad_norm": 3.5565311908721924,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1796,
+      "step": 44
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 4.673423767089844,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.906,
+      "step": 45
+    },
+    {
+      "epoch": 0.2529209621993127,
+      "grad_norm": 5.534946918487549,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.6066,
+      "step": 46
+    },
+    {
+      "epoch": 0.2584192439862543,
+      "grad_norm": 5.209371089935303,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.7243,
+      "step": 47
+    },
+    {
+      "epoch": 0.2639175257731959,
+      "grad_norm": 4.706009387969971,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.7562,
+      "step": 48
+    },
+    {
+      "epoch": 0.26941580756013744,
+      "grad_norm": 4.775091648101807,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.9579,
+      "step": 49
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "grad_norm": 7.205026149749756,
+      "learning_rate": 0.0,
+      "loss": 4.3403,
+      "step": 50
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "eval_loss": 3.0637059211730957,
+      "eval_runtime": 32.5531,
+      "eval_samples_per_second": 37.631,
+      "eval_steps_per_second": 4.731,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null