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:e5f1d0970acc7c9a88e7f6cc3ef0332918d431bd3dcd54431aa97b8827e69c23
+oid sha256:dacc4bfa4c652224e3f5ade9519c924871bf39e5de8d71835a4fcae7ff20fe71
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01641c33bbe2657676eaac06834c8ab1175b72c13b50756e95861913e66cf3e7
+oid sha256:1425e8d24fdfc29cbb55a13266efc975c2bb08ea2b90844c01e4623584638cfe
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26a1c518064c5bfab06c0f9e91ef1ea222b80ef230f7c036afc5a22a8035a32
+oid sha256:ae1a1f4e2fc92eb324d3b893fc49674fa4cbcdf0b9ae81831da817cbb61753e1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa757e87b086873609e3d41dd370af3b70e58721e81ce5232122aab3c84128a
+oid sha256:cde0e80397e7f1483d40297f5091b222389e1391b28bd449445dbfae451ee544
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a61af90559abe41003fe5359aba86cd74c501f1fafce164fd95cd8cffb2202e
+oid sha256:c65c6f6b1391bb8610a8581ef385fff93490d45bc5aa3aa3c56db4948b91b163
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1689f6e80ab757d4c0cfc6be3fc4c5e1f8cfc4f892fb4fe4a459b6f076a910
+oid sha256:b0238d981d4eae3945741a458487693989f055229b5ee83702fcc2d5fcbbcc9b
 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": 1.8950231075286865,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8298755186721992,
+  "best_metric": 1.736671805381775,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.6597510373443982,
   "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": 15.175,
       "eval_steps_per_second": 1.944,
       "step": 25
+    },
+    {
+      "epoch": 0.8630705394190872,
+      "grad_norm": 0.8051521182060242,
+      "learning_rate": 5e-05,
+      "loss": 1.949,
+      "step": 26
+    },
+    {
+      "epoch": 0.8962655601659751,
+      "grad_norm": 0.9853439927101135,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8323,
+      "step": 27
+    },
+    {
+      "epoch": 0.9294605809128631,
+      "grad_norm": 1.0945851802825928,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7493,
+      "step": 28
+    },
+    {
+      "epoch": 0.9626556016597511,
+      "grad_norm": 1.676234483718872,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7922,
+      "step": 29
+    },
+    {
+      "epoch": 0.995850622406639,
+      "grad_norm": 3.2048423290252686,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6883,
+      "step": 30
+    },
+    {
+      "epoch": 1.0290456431535269,
+      "grad_norm": 1.70829439163208,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.6119,
+      "step": 31
+    },
+    {
+      "epoch": 1.062240663900415,
+      "grad_norm": 1.1503565311431885,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9121,
+      "step": 32
+    },
+    {
+      "epoch": 1.095435684647303,
+      "grad_norm": 1.1516892910003662,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8036,
+      "step": 33
+    },
+    {
+      "epoch": 1.1286307053941909,
+      "grad_norm": 1.125571370124817,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8119,
+      "step": 34
+    },
+    {
+      "epoch": 1.161825726141079,
+      "grad_norm": 1.2525907754898071,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.7454,
+      "step": 35
+    },
+    {
+      "epoch": 1.1950207468879668,
+      "grad_norm": 1.5668110847473145,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.6739,
+      "step": 36
+    },
+    {
+      "epoch": 1.2282157676348548,
+      "grad_norm": 1.3762764930725098,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6281,
+      "step": 37
+    },
+    {
+      "epoch": 1.2614107883817427,
+      "grad_norm": 0.9111345410346985,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7097,
+      "step": 38
+    },
+    {
+      "epoch": 1.2946058091286308,
+      "grad_norm": 0.942206084728241,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0938,
+      "step": 39
+    },
+    {
+      "epoch": 1.3278008298755186,
+      "grad_norm": 0.9035945534706116,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.8342,
+      "step": 40
+    },
+    {
+      "epoch": 1.3609958506224067,
+      "grad_norm": 1.1322251558303833,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.7725,
+      "step": 41
+    },
+    {
+      "epoch": 1.3941908713692945,
+      "grad_norm": 1.2130287885665894,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6429,
+      "step": 42
+    },
+    {
+      "epoch": 1.4273858921161826,
+      "grad_norm": 1.4975661039352417,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6027,
+      "step": 43
+    },
+    {
+      "epoch": 1.4605809128630705,
+      "grad_norm": 1.4150943756103516,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5654,
+      "step": 44
+    },
+    {
+      "epoch": 1.4937759336099585,
+      "grad_norm": 2.0287270545959473,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6134,
+      "step": 45
+    },
+    {
+      "epoch": 1.5269709543568464,
+      "grad_norm": 0.7386268377304077,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9227,
+      "step": 46
+    },
+    {
+      "epoch": 1.5601659751037344,
+      "grad_norm": 0.951142430305481,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8699,
+      "step": 47
+    },
+    {
+      "epoch": 1.5933609958506225,
+      "grad_norm": 1.1127924919128418,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8144,
+      "step": 48
+    },
+    {
+      "epoch": 1.6265560165975104,
+      "grad_norm": 1.1469711065292358,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7043,
+      "step": 49
+    },
+    {
+      "epoch": 1.6597510373443982,
+      "grad_norm": 1.2899292707443237,
+      "learning_rate": 0.0,
+      "loss": 1.6653,
+      "step": 50
+    },
+    {
+      "epoch": 1.6597510373443982,
+      "eval_loss": 1.736671805381775,
+      "eval_runtime": 13.3627,
+      "eval_samples_per_second": 15.192,
+      "eval_steps_per_second": 1.946,
+      "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": 2.652642132099072e+17,
+  "total_flos": 5.305284264198144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null