Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61cbe330c1020fd480930f2ce15d9934c4347f200f856053db5ddffa75a84e66
+oid sha256:03b81c94eeb28df8637ef81d2460ce8647519d00e59301d91fa27a6e9b290cfb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24272c439d6dc228d4f803b0e05fd2802dbbc99fe8ace3ce871c5dedddf2d4c4
+oid sha256:b5e89cb0828344cbde8593d77e79cfcccfb37426b8e2a41da76a143348951bda
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732eb742d3e875f1fb84796d36b10d7e6d706a7749b3f38bc6a8ef284a1beb99
+oid sha256:87c8a91fbdef91178944ebb72cdb44178b8172a107fcb2dc960c9c19e9cd1daa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855f981654da2756c230c45b8596dfdfdc0e36c822fe2d0e20291d481752f327
+oid sha256:f528e0e70ee7410483b2d0eb5d3cb6fd74298ca4f42d8938db0b664028dc4336
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b8f2ba99da064e03dad17e472d01b3c5081ef0f8dd5d687a783fdfd9912db4
+oid sha256:70661cf4f2e8ae8655866d4cd8ca4264a6dad47c95cfc21ed1675a008744df87
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f81c8b14aa5d1bfedc2e3264844ebf1ecb4d21f5b106abdd07c6ce0e664d4e
+oid sha256:81352e128a762fbcdec0f447c4cdcca445834d0b29c47efa76ca9c4728287f27
 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": 0.3290276825428009,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.42328042328042326,
+  "best_metric": 0.26727595925331116,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8465608465608465,
   "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": 32.847,
       "eval_steps_per_second": 4.127,
       "step": 25
+    },
+    {
+      "epoch": 0.4402116402116402,
+      "grad_norm": 2.553032398223877,
+      "learning_rate": 5e-05,
+      "loss": 0.2123,
+      "step": 26
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 2.527278184890747,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2425,
+      "step": 27
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 1.3259862661361694,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2149,
+      "step": 28
+    },
+    {
+      "epoch": 0.491005291005291,
+      "grad_norm": 0.9057004451751709,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1846,
+      "step": 29
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 2.1379523277282715,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2631,
+      "step": 30
+    },
+    {
+      "epoch": 0.5248677248677248,
+      "grad_norm": 1.7521412372589111,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2363,
+      "step": 31
+    },
+    {
+      "epoch": 0.5417989417989418,
+      "grad_norm": 1.938287615776062,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2474,
+      "step": 32
+    },
+    {
+      "epoch": 0.5587301587301587,
+      "grad_norm": 1.5582822561264038,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2299,
+      "step": 33
+    },
+    {
+      "epoch": 0.5756613756613757,
+      "grad_norm": 1.065468668937683,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2233,
+      "step": 34
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.8618595600128174,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1876,
+      "step": 35
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 1.1647229194641113,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1651,
+      "step": 36
+    },
+    {
+      "epoch": 0.6264550264550265,
+      "grad_norm": 1.375846266746521,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.243,
+      "step": 37
+    },
+    {
+      "epoch": 0.6433862433862434,
+      "grad_norm": 1.3024173974990845,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.145,
+      "step": 38
+    },
+    {
+      "epoch": 0.6603174603174603,
+      "grad_norm": 1.9372594356536865,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2139,
+      "step": 39
+    },
+    {
+      "epoch": 0.6772486772486772,
+      "grad_norm": 1.7783533334732056,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1954,
+      "step": 40
+    },
+    {
+      "epoch": 0.6941798941798942,
+      "grad_norm": 1.3502763509750366,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1917,
+      "step": 41
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.9650064706802368,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.175,
+      "step": 42
+    },
+    {
+      "epoch": 0.728042328042328,
+      "grad_norm": 0.9830562472343445,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2051,
+      "step": 43
+    },
+    {
+      "epoch": 0.744973544973545,
+      "grad_norm": 1.0555146932601929,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1936,
+      "step": 44
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.937089204788208,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1957,
+      "step": 45
+    },
+    {
+      "epoch": 0.7788359788359789,
+      "grad_norm": 1.1521154642105103,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2199,
+      "step": 46
+    },
+    {
+      "epoch": 0.7957671957671958,
+      "grad_norm": 1.1540207862854004,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2073,
+      "step": 47
+    },
+    {
+      "epoch": 0.8126984126984127,
+      "grad_norm": 1.0548319816589355,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1964,
+      "step": 48
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 1.3886256217956543,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2309,
+      "step": 49
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 2.104114055633545,
+      "learning_rate": 0.0,
+      "loss": 0.2309,
+      "step": 50
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "eval_loss": 0.26727595925331116,
+      "eval_runtime": 12.1192,
+      "eval_samples_per_second": 32.84,
+      "eval_steps_per_second": 4.126,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null