Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c55b4eed0b746ae45b7295b4f9be65583711db82b7c2f7707948bae4f170f9
+oid sha256:275ed51fe3652165fa6692329401cd7912f6a718372eddc9309b9221534ce2bc
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d90d257c3aff25669f4e7550cc14d66c1c6c0d43e3d48ac669293f2c0c917b4
+oid sha256:860a8f63c5d5db7c2b48ca2a53809405c30ed2458d18996434295a852e9f6169
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a26eb597e8aa1b86749fcc341508259c6fab8882b734c9d37dae325ac2541d4
+oid sha256:da7e15a46bda6c26da792524d97edad3de03cc7210544c6c214ea315d14f5b97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db9ad58b857bad82cd5e6a12dccc1f534b063b17c7aa654a17de080df09ebd0
+oid sha256:62b300f7450315b944956528c96746ea0a0cc63a230d4875313db926c1935f34
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b1d438d2969689559dfd67c633889a9795583ac455446164269ca2b1b353bc
+oid sha256:856391f8406b04329e436043853869f7157d22cd2f54855ca3886a3b485746d1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75a268a221ac9f6a5d5d88dfebbac5e82a6c2031da10aa2fee719cc4c36d6de
+oid sha256:cc4dd2b968bbed974eb791267f04e25b8b180b16ea2e478f0d591f2842ddfa34
 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": 6.408796787261963,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08298755186721991,
+  "best_metric": 5.886590957641602,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16597510373443983,
   "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": 89.102,
       "eval_steps_per_second": 11.149,
       "step": 25
+    },
+    {
+      "epoch": 0.08630705394190871,
+      "grad_norm": 6.193380355834961,
+      "learning_rate": 5e-05,
+      "loss": 6.3512,
+      "step": 26
+    },
+    {
+      "epoch": 0.08962655601659751,
+      "grad_norm": 6.526251792907715,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.3189,
+      "step": 27
+    },
+    {
+      "epoch": 0.09294605809128631,
+      "grad_norm": 5.399415493011475,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 6.2825,
+      "step": 28
+    },
+    {
+      "epoch": 0.09626556016597511,
+      "grad_norm": 3.2363271713256836,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 6.1822,
+      "step": 29
+    },
+    {
+      "epoch": 0.0995850622406639,
+      "grad_norm": 1.8278745412826538,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.0853,
+      "step": 30
+    },
+    {
+      "epoch": 0.10290456431535269,
+      "grad_norm": 1.6847590208053589,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.0437,
+      "step": 31
+    },
+    {
+      "epoch": 0.10622406639004149,
+      "grad_norm": 2.0661935806274414,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.9981,
+      "step": 32
+    },
+    {
+      "epoch": 0.10954356846473029,
+      "grad_norm": 2.292564868927002,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 6.1408,
+      "step": 33
+    },
+    {
+      "epoch": 0.11286307053941909,
+      "grad_norm": 2.2145509719848633,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.1147,
+      "step": 34
+    },
+    {
+      "epoch": 0.11618257261410789,
+      "grad_norm": 2.2277729511260986,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.1476,
+      "step": 35
+    },
+    {
+      "epoch": 0.11950207468879669,
+      "grad_norm": 2.4843192100524902,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.2465,
+      "step": 36
+    },
+    {
+      "epoch": 0.12282157676348547,
+      "grad_norm": 2.5991244316101074,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.3102,
+      "step": 37
+    },
+    {
+      "epoch": 0.12614107883817427,
+      "grad_norm": 1.514162540435791,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.0682,
+      "step": 38
+    },
+    {
+      "epoch": 0.12946058091286308,
+      "grad_norm": 1.709502935409546,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 5.7858,
+      "step": 39
+    },
+    {
+      "epoch": 0.13278008298755187,
+      "grad_norm": 1.5972634553909302,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 5.7559,
+      "step": 40
+    },
+    {
+      "epoch": 0.13609958506224065,
+      "grad_norm": 1.3997278213500977,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 5.8057,
+      "step": 41
+    },
+    {
+      "epoch": 0.13941908713692946,
+      "grad_norm": 1.292576789855957,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.8228,
+      "step": 42
+    },
+    {
+      "epoch": 0.14273858921161825,
+      "grad_norm": 1.3085607290267944,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.8759,
+      "step": 43
+    },
+    {
+      "epoch": 0.14605809128630706,
+      "grad_norm": 1.286241888999939,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.8659,
+      "step": 44
+    },
+    {
+      "epoch": 0.14937759336099585,
+      "grad_norm": 1.2643060684204102,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 5.8861,
+      "step": 45
+    },
+    {
+      "epoch": 0.15269709543568466,
+      "grad_norm": 1.270158052444458,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5.8817,
+      "step": 46
+    },
+    {
+      "epoch": 0.15601659751037344,
+      "grad_norm": 1.4481507539749146,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.9544,
+      "step": 47
+    },
+    {
+      "epoch": 0.15933609958506223,
+      "grad_norm": 1.435001254081726,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.9207,
+      "step": 48
+    },
+    {
+      "epoch": 0.16265560165975104,
+      "grad_norm": 1.6827739477157593,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.085,
+      "step": 49
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "grad_norm": 2.8101089000701904,
+      "learning_rate": 0.0,
+      "loss": 6.3224,
+      "step": 50
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "eval_loss": 5.886590957641602,
+      "eval_runtime": 22.7757,
+      "eval_samples_per_second": 89.13,
+      "eval_steps_per_second": 11.152,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null