Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80cd8d83bd004e45dd008bf00caff46c7583952f1f363f06098533ac8722c95e
+oid sha256:85cc40fd8deb083488991b99c75f53cdc39c77da2b7e297309a74b3bdc696399
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952caec92e413d367801fff10639fb8d7003d985be722bc8ff5d6ff20b761a8f
+oid sha256:9423be85e99a01f450116fc61c385cc4c78cfeab95a1f99b770ba835dd65f00c
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f707ae75c6760c97e0a46b6d2488eb7c38906f7fef8848da52bbec29a510681a
+oid sha256:fae5c7fef2289859eefd352ccbfe3b19ec447f59743687e23723354f0a8639de
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e696d0579180f92c2a603b2ad03a6af012cba45dfb83b730c4c6c63c02b38cc1
+oid sha256:e9ab67e4065735cffce79cc754ff6dc60f5cf4f560d341228ce30ac112f861da
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95340ab7cc64911b465141f2a0fc90a48a4fcc351235bb3e465634516704199e
+oid sha256:5f463e6a7cdbf39b86b6116b76bb44e1c8ed4534f133ea558d94a1589f8c6674
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5653c3709df0e3676c77b214174c250bbbc63350f65175c4760127742c6efbb
+oid sha256:2e7ff4b7e17d4a8ce30e499dcf88f161bc82c62bdc1eb243952daa021b7af302
 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": 0.6583801507949829,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031039031582214636,
+  "best_metric": 0.6460928320884705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06207806316442927,
   "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": 63.135,
       "eval_steps_per_second": 7.901,
       "step": 25
+    },
+    {
+      "epoch": 0.03228059284550322,
+      "grad_norm": 0.2256009429693222,
+      "learning_rate": 5e-05,
+      "loss": 0.7063,
+      "step": 26
+    },
+    {
+      "epoch": 0.03352215410879181,
+      "grad_norm": 0.15308834612369537,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6823,
+      "step": 27
+    },
+    {
+      "epoch": 0.03476371537208039,
+      "grad_norm": 0.14822077751159668,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6787,
+      "step": 28
+    },
+    {
+      "epoch": 0.036005276635368975,
+      "grad_norm": 0.15348833799362183,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7401,
+      "step": 29
+    },
+    {
+      "epoch": 0.03724683789865756,
+      "grad_norm": 0.15910352766513824,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7295,
+      "step": 30
+    },
+    {
+      "epoch": 0.03848839916194615,
+      "grad_norm": 0.14045007526874542,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6509,
+      "step": 31
+    },
+    {
+      "epoch": 0.03972996042523473,
+      "grad_norm": 0.14484994113445282,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6792,
+      "step": 32
+    },
+    {
+      "epoch": 0.04097152168852332,
+      "grad_norm": 0.14491479098796844,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6661,
+      "step": 33
+    },
+    {
+      "epoch": 0.042213082951811906,
+      "grad_norm": 0.13978998363018036,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6713,
+      "step": 34
+    },
+    {
+      "epoch": 0.04345464421510049,
+      "grad_norm": 0.15529781579971313,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6076,
+      "step": 35
+    },
+    {
+      "epoch": 0.044696205478389074,
+      "grad_norm": 0.15842097997665405,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5237,
+      "step": 36
+    },
+    {
+      "epoch": 0.04593776674167766,
+      "grad_norm": 0.1823544204235077,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4294,
+      "step": 37
+    },
+    {
+      "epoch": 0.04717932800496624,
+      "grad_norm": 0.45187708735466003,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7899,
+      "step": 38
+    },
+    {
+      "epoch": 0.04842088926825483,
+      "grad_norm": 0.1284649819135666,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6492,
+      "step": 39
+    },
+    {
+      "epoch": 0.04966245053154342,
+      "grad_norm": 0.13667044043540955,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7075,
+      "step": 40
+    },
+    {
+      "epoch": 0.050904011794832,
+      "grad_norm": 0.1311858743429184,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7165,
+      "step": 41
+    },
+    {
+      "epoch": 0.052145573058120585,
+      "grad_norm": 0.13079705834388733,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7097,
+      "step": 42
+    },
+    {
+      "epoch": 0.05338713432140917,
+      "grad_norm": 0.13603699207305908,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6489,
+      "step": 43
+    },
+    {
+      "epoch": 0.05462869558469776,
+      "grad_norm": 0.1422751545906067,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6811,
+      "step": 44
+    },
+    {
+      "epoch": 0.05587025684798634,
+      "grad_norm": 0.13295882940292358,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6908,
+      "step": 45
+    },
+    {
+      "epoch": 0.05711181811127493,
+      "grad_norm": 0.1368282288312912,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6654,
+      "step": 46
+    },
+    {
+      "epoch": 0.058353379374563516,
+      "grad_norm": 0.14943842589855194,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6069,
+      "step": 47
+    },
+    {
+      "epoch": 0.0595949406378521,
+      "grad_norm": 0.1544649749994278,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5667,
+      "step": 48
+    },
+    {
+      "epoch": 0.060836501901140684,
+      "grad_norm": 0.16153788566589355,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4583,
+      "step": 49
+    },
+    {
+      "epoch": 0.06207806316442927,
+      "grad_norm": 0.22390557825565338,
+      "learning_rate": 0.0,
+      "loss": 0.3561,
+      "step": 50
+    },
+    {
+      "epoch": 0.06207806316442927,
+      "eval_loss": 0.6460928320884705,
+      "eval_runtime": 86.0243,
+      "eval_samples_per_second": 63.075,
+      "eval_steps_per_second": 7.893,
+      "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": 4.216566050298266e+16,
+  "total_flos": 8.42792324479058e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null