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:f1ee4718df7a6bc921993cc4171fee6566196720a2267219c6f5eabcbf8d761a
+oid sha256:1acc18072064540eeb0654c4ecea88681d1f82d2431ee9d629ee71c5018e9307
 size 4525640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c120b80c1d8aedeff9fd6c968e021ade58747ac05b8d2247ac9b85527a6a923f
+oid sha256:3cec3a594cb5785a82b37ca011f9d8ad82b5aee2e8e2b952a5939bcf494579d6
 size 9067978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9245c4e652c3e5d6ddde083c2e6c37d13f06c92c18226f74c2aacd12316d2592
+oid sha256:0216a32c6eef3e2f9c7449db9565689339e1409596b215915cc1bb98f1eb56e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8eb6d9a12d25f7c51a251ec4efb86bb45df859e21751f0e093271a3f5f5e34a
+oid sha256:55a324d7c244c99337725c7eb72f97494ab86349453674f951bf00a5c28e7b8a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2c5c77a5a3faba1c1284c0a057baef70eba279c0132b6a4ad3f24eabc9da8a
+oid sha256:3c8321ff4c3f427859b461353d55fad2997e21574658206006373a0bd3a7cf29
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2d9c93594838a58a29a4a55b40d30669e820c77600b466d3c26351f92fb253
+oid sha256:63f3b7fc31ec278f5b3722cd91d05f6623f5b248a2e0c63d6a657882805573c2
 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": 2.1244988441467285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.023449407902450464,
+  "best_metric": 2.0720748901367188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04689881580490093,
   "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": 411.605,
       "eval_steps_per_second": 51.465,
       "step": 25
+    },
+    {
+      "epoch": 0.024387384218548483,
+      "grad_norm": 0.8481528759002686,
+      "learning_rate": 5e-05,
+      "loss": 2.1097,
+      "step": 26
+    },
+    {
+      "epoch": 0.0253253605346465,
+      "grad_norm": 0.852368175983429,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0837,
+      "step": 27
+    },
+    {
+      "epoch": 0.026263336850744518,
+      "grad_norm": 0.7314043045043945,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1093,
+      "step": 28
+    },
+    {
+      "epoch": 0.027201313166842538,
+      "grad_norm": 0.6793732643127441,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0646,
+      "step": 29
+    },
+    {
+      "epoch": 0.028139289482940557,
+      "grad_norm": 0.6859661340713501,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.1209,
+      "step": 30
+    },
+    {
+      "epoch": 0.029077265799038573,
+      "grad_norm": 0.7069147825241089,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1315,
+      "step": 31
+    },
+    {
+      "epoch": 0.030015242115136592,
+      "grad_norm": 0.6345369815826416,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0951,
+      "step": 32
+    },
+    {
+      "epoch": 0.03095321843123461,
+      "grad_norm": 0.6450087428092957,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0838,
+      "step": 33
+    },
+    {
+      "epoch": 0.03189119474733263,
+      "grad_norm": 0.7155236601829529,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0965,
+      "step": 34
+    },
+    {
+      "epoch": 0.03282917106343065,
+      "grad_norm": 0.7774618864059448,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.0836,
+      "step": 35
+    },
+    {
+      "epoch": 0.03376714737952867,
+      "grad_norm": 0.9112603068351746,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0658,
+      "step": 36
+    },
+    {
+      "epoch": 0.034705123695626686,
+      "grad_norm": 0.9569104909896851,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0882,
+      "step": 37
+    },
+    {
+      "epoch": 0.0356431000117247,
+      "grad_norm": 0.5913195013999939,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0908,
+      "step": 38
+    },
+    {
+      "epoch": 0.036581076327822724,
+      "grad_norm": 0.5460679531097412,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0435,
+      "step": 39
+    },
+    {
+      "epoch": 0.03751905264392074,
+      "grad_norm": 0.5165838599205017,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0967,
+      "step": 40
+    },
+    {
+      "epoch": 0.038457028960018756,
+      "grad_norm": 0.553436815738678,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.061,
+      "step": 41
+    },
+    {
+      "epoch": 0.03939500527611678,
+      "grad_norm": 0.5237096548080444,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.0698,
+      "step": 42
+    },
+    {
+      "epoch": 0.040332981592214795,
+      "grad_norm": 0.5039860010147095,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0596,
+      "step": 43
+    },
+    {
+      "epoch": 0.04127095790831282,
+      "grad_norm": 0.5638653635978699,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1267,
+      "step": 44
+    },
+    {
+      "epoch": 0.042208934224410834,
+      "grad_norm": 0.5625221729278564,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0721,
+      "step": 45
+    },
+    {
+      "epoch": 0.04314691054050885,
+      "grad_norm": 0.564399242401123,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0598,
+      "step": 46
+    },
+    {
+      "epoch": 0.04408488685660687,
+      "grad_norm": 0.5962613821029663,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.0765,
+      "step": 47
+    },
+    {
+      "epoch": 0.04502286317270489,
+      "grad_norm": 0.6754391193389893,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.0752,
+      "step": 48
+    },
+    {
+      "epoch": 0.045960839488802904,
+      "grad_norm": 0.6958993077278137,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0509,
+      "step": 49
+    },
+    {
+      "epoch": 0.04689881580490093,
+      "grad_norm": 0.9654695987701416,
+      "learning_rate": 0.0,
+      "loss": 2.0207,
+      "step": 50
+    },
+    {
+      "epoch": 0.04689881580490093,
+      "eval_loss": 2.0720748901367188,
+      "eval_runtime": 17.5741,
+      "eval_samples_per_second": 408.67,
+      "eval_steps_per_second": 51.098,
+      "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": 1753141896806400.0,
+  "total_flos": 3506283793612800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null