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:f27c2604d9e7337ab4542f90e0c89242a31d9836ee80ff314eb95bb23d00afed
+oid sha256:9a16782ad6003cc249729eaf787b2f12c4580a66df7a4ad911042842ad8b37f3
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5dda0192adbadad4c40944ec04ba46a02eb5ab7a87e940eab710ed6da89dcc1
+oid sha256:07b7bb7ee1bd78fc86f3b3d334c0f723efc54a0e89cee8a3e6addb29cdc51e70
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9cd01f9d98a12ab57d887418ef602665d4d593012a3b6e186e0462a0dae8477
+oid sha256:dc4ab12b951b506558e3646daa733529bdc43d20d10a4cbf4bfaaa2fdda79b66
 size 14244

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": 0.00532330758869648,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5228758169934641,
+  "best_metric": 4.127087231609039e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0496732026143791,
   "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": 3.106,
       "eval_steps_per_second": 1.572,
       "step": 25
+    },
+    {
+      "epoch": 0.5437908496732026,
+      "grad_norm": 8.163567543029785,
+      "learning_rate": 5e-05,
+      "loss": 0.172,
+      "step": 26
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 2.176654577255249,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0438,
+      "step": 27
+    },
+    {
+      "epoch": 0.5856209150326798,
+      "grad_norm": 0.09583692997694016,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0033,
+      "step": 28
+    },
+    {
+      "epoch": 0.6065359477124183,
+      "grad_norm": 2.4841692447662354,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0293,
+      "step": 29
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.9432563185691833,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0176,
+      "step": 30
+    },
+    {
+      "epoch": 0.6483660130718955,
+      "grad_norm": 0.29981163144111633,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0095,
+      "step": 31
+    },
+    {
+      "epoch": 0.6692810457516339,
+      "grad_norm": 0.13397172093391418,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0034,
+      "step": 32
+    },
+    {
+      "epoch": 0.6901960784313725,
+      "grad_norm": 0.26384004950523376,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0036,
+      "step": 33
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.017268378287553787,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0007,
+      "step": 34
+    },
+    {
+      "epoch": 0.7320261437908496,
+      "grad_norm": 0.0771813616156578,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0022,
+      "step": 35
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.06307241320610046,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0011,
+      "step": 36
+    },
+    {
+      "epoch": 0.7738562091503268,
+      "grad_norm": 0.009056968614459038,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0003,
+      "step": 37
+    },
+    {
+      "epoch": 0.7947712418300653,
+      "grad_norm": 0.02682294324040413,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0008,
+      "step": 38
+    },
+    {
+      "epoch": 0.8156862745098039,
+      "grad_norm": 0.03674069046974182,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0013,
+      "step": 39
+    },
+    {
+      "epoch": 0.8366013071895425,
+      "grad_norm": 0.011068358086049557,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0005,
+      "step": 40
+    },
+    {
+      "epoch": 0.857516339869281,
+      "grad_norm": 0.013999490067362785,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0007,
+      "step": 41
+    },
+    {
+      "epoch": 0.8784313725490196,
+      "grad_norm": 0.011875639669597149,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0006,
+      "step": 42
+    },
+    {
+      "epoch": 0.8993464052287582,
+      "grad_norm": 0.12404092401266098,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0015,
+      "step": 43
+    },
+    {
+      "epoch": 0.9202614379084967,
+      "grad_norm": 0.03556958585977554,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.001,
+      "step": 44
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 6.352353096008301,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0426,
+      "step": 45
+    },
+    {
+      "epoch": 0.9620915032679739,
+      "grad_norm": 0.0167868509888649,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 0.9830065359477124,
+      "grad_norm": 0.024576369673013687,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0005,
+      "step": 47
+    },
+    {
+      "epoch": 1.007843137254902,
+      "grad_norm": 0.009638285264372826,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0005,
+      "step": 48
+    },
+    {
+      "epoch": 1.0287581699346404,
+      "grad_norm": 0.007980446331202984,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0004,
+      "step": 49
+    },
+    {
+      "epoch": 1.0496732026143791,
+      "grad_norm": 0.006425910629332066,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 50
+    },
+    {
+      "epoch": 1.0496732026143791,
+      "eval_loss": 4.127087231609039e-05,
+      "eval_runtime": 26.0704,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 1.573,
+      "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": 6.57394539429888e+16,
+  "total_flos": 1.314789078859776e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null