Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d10ba30ce374c430675cb83fa95ad09fd03dfddace7321ff355b81e6e71cee
+oid sha256:e4f2e06f7b039976fc75df11142a1eceb6cd2f24db71c183879c42ac8f75e50d
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3e3ccc0c27f5466791cc8422887783022d4453591521600a7cb2f843dc83cc
+oid sha256:52c9bdf55e4ab322f074855d7832562a3dea7bf8a975330f34c34ce5ede432bb
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90a8c87e4d78f90bbb605cdc81f1896a30b0e0b4c81693e9d203d81cf6fdcd4
+oid sha256:29b60a19ed07327340e89c4cb2549ca22cbe049e758c4f1dbca79b88554e6dab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366d72b8f97ee5ad1868d341501b8e368b56d2f1958fd78791ea2ff8a533914d
+oid sha256:d7ce98f853005751c467c733cd6172bca52c1651e435d66348ed7743cfb3f18b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3387ab4dbfc2519e7b09f26b99a54876bceb4d8efd3cb0e27871765b805d7a2a
+oid sha256:cd9145236fb8777a05d0c70f7e959af256e266b6622a198fb59384cb946e1eb6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc6f04b5d113fda331f990d93b1f41be1dbeab94483cb3b90376bc0e1c27e68
+oid sha256:1a033f311926773e95431c59bc355ee81ee35a2f05e05339a21febec83f14e50
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.929224967956543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014155283459551277,
+  "best_metric": 11.927395820617676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028310566919102553,
   "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": 277.538,
       "eval_steps_per_second": 72.16,
       "step": 25
+    },
+    {
+      "epoch": 0.014721494797933329,
+      "grad_norm": 0.012647237628698349,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 11.9297,
+      "step": 26
+    },
+    {
+      "epoch": 0.015287706136315379,
+      "grad_norm": 0.015734661370515823,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 11.9291,
+      "step": 27
+    },
+    {
+      "epoch": 0.01585391747469743,
+      "grad_norm": 0.017150381579995155,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 11.9295,
+      "step": 28
+    },
+    {
+      "epoch": 0.01642012881307948,
+      "grad_norm": 0.020637271925807,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 11.9292,
+      "step": 29
+    },
+    {
+      "epoch": 0.016986340151461533,
+      "grad_norm": 0.018464168533682823,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 11.9282,
+      "step": 30
+    },
+    {
+      "epoch": 0.017552551489843585,
+      "grad_norm": 0.020926039665937424,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 11.9294,
+      "step": 31
+    },
+    {
+      "epoch": 0.018118762828225634,
+      "grad_norm": 0.02240375615656376,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 11.9286,
+      "step": 32
+    },
+    {
+      "epoch": 0.018684974166607686,
+      "grad_norm": 0.02602965198457241,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 11.9302,
+      "step": 33
+    },
+    {
+      "epoch": 0.019251185504989738,
+      "grad_norm": 0.024349767714738846,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 11.9309,
+      "step": 34
+    },
+    {
+      "epoch": 0.01981739684337179,
+      "grad_norm": 0.028244735673069954,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 11.9283,
+      "step": 35
+    },
+    {
+      "epoch": 0.02038360818175384,
+      "grad_norm": 0.030170924961566925,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 11.9298,
+      "step": 36
+    },
+    {
+      "epoch": 0.02094981952013589,
+      "grad_norm": 0.03267698734998703,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 11.9284,
+      "step": 37
+    },
+    {
+      "epoch": 0.021516030858517943,
+      "grad_norm": 0.020892078056931496,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 11.9295,
+      "step": 38
+    },
+    {
+      "epoch": 0.02208224219689999,
+      "grad_norm": 0.021916329860687256,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 11.9294,
+      "step": 39
+    },
+    {
+      "epoch": 0.022648453535282043,
+      "grad_norm": 0.020233944058418274,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 11.9292,
+      "step": 40
+    },
+    {
+      "epoch": 0.023214664873664095,
+      "grad_norm": 0.019477376714348793,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 11.9283,
+      "step": 41
+    },
+    {
+      "epoch": 0.023780876212046147,
+      "grad_norm": 0.02245022915303707,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 11.9279,
+      "step": 42
+    },
+    {
+      "epoch": 0.024347087550428196,
+      "grad_norm": 0.025973478332161903,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 11.9285,
+      "step": 43
+    },
+    {
+      "epoch": 0.024913298888810248,
+      "grad_norm": 0.027722090482711792,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 11.9288,
+      "step": 44
+    },
+    {
+      "epoch": 0.0254795102271923,
+      "grad_norm": 0.028943056240677834,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 11.9274,
+      "step": 45
+    },
+    {
+      "epoch": 0.026045721565574352,
+      "grad_norm": 0.025688176974654198,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 11.9279,
+      "step": 46
+    },
+    {
+      "epoch": 0.0266119329039564,
+      "grad_norm": 0.03459373489022255,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 11.9283,
+      "step": 47
+    },
+    {
+      "epoch": 0.027178144242338453,
+      "grad_norm": 0.034123897552490234,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 11.9279,
+      "step": 48
+    },
+    {
+      "epoch": 0.027744355580720505,
+      "grad_norm": 0.03610537573695183,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9265,
+      "step": 49
+    },
+    {
+      "epoch": 0.028310566919102553,
+      "grad_norm": 0.043514493852853775,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 11.9264,
+      "step": 50
+    },
+    {
+      "epoch": 0.028310566919102553,
+      "eval_loss": 11.927395820617676,
+      "eval_runtime": 0.1723,
+      "eval_samples_per_second": 290.181,
+      "eval_steps_per_second": 75.447,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null