Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79291d7d9515b33715266281f996cb0acf08e244926451d4595e6c68ea69ddfe
+oid sha256:f22496712fc5efb0a400a83d4c23ed289b3555ef1f8e8c69c8a9cff79f3cf658
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0684527733e0117d140ea340d29f402f047e960836040e9b290533536604a0
+oid sha256:005371babdabb9018bea3fe11e98c0b3c83641a65e16a91405a4569608982d6d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b4387aafdc649fd4e1bba44635c70ea79bc0e0571b22dc9d644928ce1b7535
+oid sha256:83dcff0a16765769a48a7747da189d563c55af010b7a78d9bcb5b0e5ff2cfef8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa753333ebae38375fcf4181a7ad4f96ce302a722a3a87f0417d13bd72d9af7d
+oid sha256:776fd5cb7ccdc8f9f8192eb3b96c529049ae49b8a7dcf9d127b5de47954ef5fb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500c212ad0afb415532c8629fbb474ce5c2adb7033c78fe223f28a35a5e6666f
+oid sha256:78de5a81f027f75bc277d68d3e9125ef909afdb1951bb0ceab4adbe2ecd7a878
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a6fe599c714e6d93726f89079c01dcb72fa0af8f33ce51c86eb0e6991a77e48
+oid sha256:7238e77cfb3adb05bd2aa4ecf9e15dd956e20f7c57a862cebf274e47b32e5856
 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": 0.7983564734458923,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.030798845043310877,
+  "best_metric": 0.6646984219551086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.061597690086621755,
   "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": 14.214,
       "eval_steps_per_second": 3.696,
       "step": 25
+    },
+    {
+      "epoch": 0.03203079884504331,
+      "grad_norm": 1.529720425605774,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.8309,
+      "step": 26
+    },
+    {
+      "epoch": 0.033262752646775744,
+      "grad_norm": 1.6183327436447144,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.7803,
+      "step": 27
+    },
+    {
+      "epoch": 0.03449470644850818,
+      "grad_norm": 1.110182285308838,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.7443,
+      "step": 28
+    },
+    {
+      "epoch": 0.03572666025024061,
+      "grad_norm": 0.8818290829658508,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.7466,
+      "step": 29
+    },
+    {
+      "epoch": 0.03695861405197305,
+      "grad_norm": 0.9471279978752136,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.7426,
+      "step": 30
+    },
+    {
+      "epoch": 0.03819056785370548,
+      "grad_norm": 1.0536586046218872,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.7339,
+      "step": 31
+    },
+    {
+      "epoch": 0.03942252165543792,
+      "grad_norm": 0.8326343894004822,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.6976,
+      "step": 32
+    },
+    {
+      "epoch": 0.04065447545717036,
+      "grad_norm": 0.823235273361206,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.7378,
+      "step": 33
+    },
+    {
+      "epoch": 0.04188642925890279,
+      "grad_norm": 0.8146088719367981,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.7537,
+      "step": 34
+    },
+    {
+      "epoch": 0.04311838306063523,
+      "grad_norm": 0.852783739566803,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.7191,
+      "step": 35
+    },
+    {
+      "epoch": 0.04435033686236766,
+      "grad_norm": 0.9801528453826904,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.774,
+      "step": 36
+    },
+    {
+      "epoch": 0.0455822906641001,
+      "grad_norm": 1.0414175987243652,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.8229,
+      "step": 37
+    },
+    {
+      "epoch": 0.04681424446583253,
+      "grad_norm": 0.8394467234611511,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.7731,
+      "step": 38
+    },
+    {
+      "epoch": 0.04804619826756497,
+      "grad_norm": 0.8109716773033142,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.6696,
+      "step": 39
+    },
+    {
+      "epoch": 0.0492781520692974,
+      "grad_norm": 0.7383696436882019,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.6555,
+      "step": 40
+    },
+    {
+      "epoch": 0.05051010587102984,
+      "grad_norm": 0.7810937166213989,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.6789,
+      "step": 41
+    },
+    {
+      "epoch": 0.05174205967276227,
+      "grad_norm": 0.7691031694412231,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.6582,
+      "step": 42
+    },
+    {
+      "epoch": 0.05297401347449471,
+      "grad_norm": 0.9100735783576965,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.7069,
+      "step": 43
+    },
+    {
+      "epoch": 0.05420596727622714,
+      "grad_norm": 0.931399405002594,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.7135,
+      "step": 44
+    },
+    {
+      "epoch": 0.05543792107795958,
+      "grad_norm": 0.8463882803916931,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.6697,
+      "step": 45
+    },
+    {
+      "epoch": 0.05666987487969201,
+      "grad_norm": 0.85605788230896,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.6989,
+      "step": 46
+    },
+    {
+      "epoch": 0.05790182868142445,
+      "grad_norm": 0.8102529048919678,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.6696,
+      "step": 47
+    },
+    {
+      "epoch": 0.05913378248315688,
+      "grad_norm": 0.8773670196533203,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.7289,
+      "step": 48
+    },
+    {
+      "epoch": 0.06036573628488932,
+      "grad_norm": 0.856377363204956,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7178,
+      "step": 49
+    },
+    {
+      "epoch": 0.061597690086621755,
+      "grad_norm": 0.9929988384246826,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.7789,
+      "step": 50
+    },
+    {
+      "epoch": 0.061597690086621755,
+      "eval_loss": 0.6646984219551086,
+      "eval_runtime": 3.5125,
+      "eval_samples_per_second": 14.235,
+      "eval_steps_per_second": 3.701,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null