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:c3a6fdabdbe8e6b42bf16f54d493ef92a05e3e00d90806fbc43b4901dd715fd1
+oid sha256:8ca5a2be3cc4898b51fcb982402f85e0b177f846a88c140f3bb56171c9a204e8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c95e3755066453acb04bdb1966751c51af6c3f54c66cb94fa0ccf064638b5c
+oid sha256:e6308c863920527b8ca7356ff8b4243bb5b46e11b858d095e0dd8f67949c7278
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1502e091651346156815ad6974bf7edaf065ee796c7a805386c8aa841bdac2fa
+oid sha256:3d3999b1afc5f3c2a49d91271909824ee16eab64e8a3d1d3dd33a20620f8035c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85507e0291216950681eedb7d9f902c0b0dee52d54fea08630cd2e7d39862948
+oid sha256:9ec7f0ffd7f4401420823044a41b76c719e594eb5198296759866a5411b775a9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0335f2f56ae586484368147e98b78cb52a2dc0a6ac723c661162a73e72ab4b
+oid sha256:ca9319caac8a7ed4817691020c5754d8407b39815c7a083f436d3cec9a413bfd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0441b71f4ac48b391155619e65f4a68e2b20a86b9259e13dbda6a2001b9e1026
+oid sha256:fa702b6bd42f135f3773f39f95a92d3fa3100968155763e7d3830f93241955aa
 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": 0.07755980640649796,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07969715082685794,
+  "best_metric": 0.07640355080366135,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15939430165371588,
   "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": 14.746,
       "eval_steps_per_second": 1.849,
       "step": 25
+    },
+    {
+      "epoch": 0.08288503685993226,
+      "grad_norm": 0.0372718870639801,
+      "learning_rate": 5e-05,
+      "loss": 0.0005,
+      "step": 26
+    },
+    {
+      "epoch": 0.08607292289300658,
+      "grad_norm": 0.0864085778594017,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0087,
+      "step": 27
+    },
+    {
+      "epoch": 0.08926080892608089,
+      "grad_norm": 0.07040909677743912,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.001,
+      "step": 28
+    },
+    {
+      "epoch": 0.09244869495915521,
+      "grad_norm": 0.08171924203634262,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0013,
+      "step": 29
+    },
+    {
+      "epoch": 0.09563658099222953,
+      "grad_norm": 0.04170752316713333,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0006,
+      "step": 30
+    },
+    {
+      "epoch": 0.09882446702530384,
+      "grad_norm": 0.04046756774187088,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0006,
+      "step": 31
+    },
+    {
+      "epoch": 0.10201235305837816,
+      "grad_norm": 0.10425488650798798,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0097,
+      "step": 32
+    },
+    {
+      "epoch": 0.10520023909145249,
+      "grad_norm": 0.13888247311115265,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0111,
+      "step": 33
+    },
+    {
+      "epoch": 0.1083881251245268,
+      "grad_norm": 0.42929139733314514,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0647,
+      "step": 34
+    },
+    {
+      "epoch": 0.11157601115760112,
+      "grad_norm": 0.5731561779975891,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0943,
+      "step": 35
+    },
+    {
+      "epoch": 0.11476389719067544,
+      "grad_norm": 0.602446973323822,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2037,
+      "step": 36
+    },
+    {
+      "epoch": 0.11795178322374975,
+      "grad_norm": 1.7377841472625732,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5449,
+      "step": 37
+    },
+    {
+      "epoch": 0.12113966925682407,
+      "grad_norm": 1.0830893516540527,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3696,
+      "step": 38
+    },
+    {
+      "epoch": 0.12432755528989839,
+      "grad_norm": 0.007708725985139608,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.1275154413229727,
+      "grad_norm": 0.008319525048136711,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.13070332735604703,
+      "grad_norm": 0.006531168706715107,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.13389121338912133,
+      "grad_norm": 0.005489464849233627,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.13707909942219565,
+      "grad_norm": 0.005156314000487328,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0001,
+      "step": 43
+    },
+    {
+      "epoch": 0.14026698545526997,
+      "grad_norm": 0.005498033948242664,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.1434548714883443,
+      "grad_norm": 0.005461568012833595,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.14664275752141862,
+      "grad_norm": 0.0800841674208641,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0069,
+      "step": 46
+    },
+    {
+      "epoch": 0.14983064355449294,
+      "grad_norm": 0.22930651903152466,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0571,
+      "step": 47
+    },
+    {
+      "epoch": 0.15301852958756723,
+      "grad_norm": 0.622684121131897,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.201,
+      "step": 48
+    },
+    {
+      "epoch": 0.15620641562064155,
+      "grad_norm": 0.3593548834323883,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2477,
+      "step": 49
+    },
+    {
+      "epoch": 0.15939430165371588,
+      "grad_norm": 0.9446438550949097,
+      "learning_rate": 0.0,
+      "loss": 0.593,
+      "step": 50
+    },
+    {
+      "epoch": 0.15939430165371588,
+      "eval_loss": 0.07640355080366135,
+      "eval_runtime": 143.3385,
+      "eval_samples_per_second": 14.748,
+      "eval_steps_per_second": 1.849,
+      "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