Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a89539890bc03101e8a119648f29be892781b4805078bcbd381c55583513e5d
+oid sha256:f0fab38c4a9ab673e4003edbe714c9bb1ffe8234c84d5b4a30965cdd23a700e2
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4061378af4794f34e774ff688dcf828f4fad6b332aca5055fa635daa8fc62a5
+oid sha256:c80d281fc4a6a1d5814ea5444b9373c8396e4fca9c786c1d9a07f0182d62aea1
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf0711432c7b446a12b08e6785fd8461abc932dce231d3ed990a5d3234075e8
+oid sha256:a219b893db4d19edaf81a951903faf96796b19862c0588a36fc8f8f10228b476
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe8c1fc8f4fe89535a76c37ef7e08e7ea325ea39214867b9e3595ed85c4678d
+oid sha256:176db279320aa30e1f17c7fcc7682012f415003d155db0b9d22d60a8748fa216
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e82b05a22f2f469842f0e22e263e88a414fa23dcd931ffbaaa5a59ecf44c6a3
+oid sha256:a886aa09131f3d46dfc4a5f160a5a6719695283f71cf35e68c834fb9471850ca
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d936cfe64857172bf20a6d7ea58255532213f12d7700a3647273fa9f71c692a6
+oid sha256:d1537d6b5279090b392cda6e147fa2e100f424737a3f69e41773f1d25f39a52a
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.43383947939262474,
+  "epoch": 0.8676789587852495,
   "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": 112.347,
       "eval_steps_per_second": 14.188,
       "step": 25
+    },
+    {
+      "epoch": 0.4511930585683297,
+      "grad_norm": 3.592841863632202,
+      "learning_rate": 5e-05,
+      "loss": 1.6595,
+      "step": 26
+    },
+    {
+      "epoch": 0.4685466377440347,
+      "grad_norm": 3.3573250770568848,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9147,
+      "step": 27
+    },
+    {
+      "epoch": 0.48590021691973967,
+      "grad_norm": 4.765448570251465,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7692,
+      "step": 28
+    },
+    {
+      "epoch": 0.5032537960954447,
+      "grad_norm": 3.249962091445923,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8794,
+      "step": 29
+    },
+    {
+      "epoch": 0.5206073752711496,
+      "grad_norm": 2.330742597579956,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6543,
+      "step": 30
+    },
+    {
+      "epoch": 0.5379609544468547,
+      "grad_norm": 2.1469850540161133,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9566,
+      "step": 31
+    },
+    {
+      "epoch": 0.5553145336225597,
+      "grad_norm": 1.5431785583496094,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6821,
+      "step": 32
+    },
+    {
+      "epoch": 0.5726681127982647,
+      "grad_norm": 1.3677806854248047,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5056,
+      "step": 33
+    },
+    {
+      "epoch": 0.5900216919739696,
+      "grad_norm": 2.1696317195892334,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7864,
+      "step": 34
+    },
+    {
+      "epoch": 0.6073752711496746,
+      "grad_norm": 2.6742897033691406,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5466,
+      "step": 35
+    },
+    {
+      "epoch": 0.6247288503253796,
+      "grad_norm": 2.6641054153442383,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3242,
+      "step": 36
+    },
+    {
+      "epoch": 0.6420824295010846,
+      "grad_norm": 2.7193713188171387,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5333,
+      "step": 37
+    },
+    {
+      "epoch": 0.6594360086767896,
+      "grad_norm": 2.1605968475341797,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4433,
+      "step": 38
+    },
+    {
+      "epoch": 0.6767895878524945,
+      "grad_norm": 2.5785412788391113,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0248,
+      "step": 39
+    },
+    {
+      "epoch": 0.6941431670281996,
+      "grad_norm": 3.018906354904175,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8749,
+      "step": 40
+    },
+    {
+      "epoch": 0.7114967462039046,
+      "grad_norm": 2.0637898445129395,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7313,
+      "step": 41
+    },
+    {
+      "epoch": 0.7288503253796096,
+      "grad_norm": 1.7586486339569092,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6862,
+      "step": 42
+    },
+    {
+      "epoch": 0.7462039045553145,
+      "grad_norm": 1.8308066129684448,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.705,
+      "step": 43
+    },
+    {
+      "epoch": 0.7635574837310195,
+      "grad_norm": 2.8740651607513428,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4843,
+      "step": 44
+    },
+    {
+      "epoch": 0.7809110629067245,
+      "grad_norm": 2.069096088409424,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5375,
+      "step": 45
+    },
+    {
+      "epoch": 0.7982646420824295,
+      "grad_norm": 2.0131049156188965,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6646,
+      "step": 46
+    },
+    {
+      "epoch": 0.8156182212581344,
+      "grad_norm": 2.2476651668548584,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4876,
+      "step": 47
+    },
+    {
+      "epoch": 0.8329718004338394,
+      "grad_norm": 1.6577153205871582,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3299,
+      "step": 48
+    },
+    {
+      "epoch": 0.8503253796095445,
+      "grad_norm": 1.759014368057251,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3173,
+      "step": 49
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "grad_norm": 1.747079849243164,
+      "learning_rate": 0.0,
+      "loss": 0.4631,
+      "step": 50
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "eval_loss": NaN,
+      "eval_runtime": 3.4625,
+      "eval_samples_per_second": 112.058,
+      "eval_steps_per_second": 14.152,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.93479042587689e+16,
+  "total_flos": 7.867133847823974e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null