Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77055b932ac07489d6fea4593c4359ed555f9ae87c8cc520ff89595b0af08be7
+oid sha256:528baa2122a93497892dd6ecc1702ed77e293895f82b09365731f2befb1ad91a
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16119e1a6c5f533ebf7c84216402d9676c9b8817850d6dd4dc697bd8c29b1a23
+oid sha256:feb6e0e7a6fcccd4866623f6258769cdec7d148381b95d9088f98f3eee269e99
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fef5bc915077fcd0744b5a5ae5559e308832fefbc6ec2dae69822af3f8f1a23
+oid sha256:9ffcdf7705b0527b101f3ef1d300fd6cb08d2a32c1e601d8882a1de3fda1204f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227b8e7eab3b40d533658c531f1e7cd6b0dab0d72c7239b4f7959ee60f8dd0ea
+oid sha256:1f74d061255f2cfd36fd67d98f6ada179bf58700a17b6104b5430c8b2ac82d7c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707d727ea8464d9b17573c7380c39c465701526dec3b4caee1ade2d09f884e4e
+oid sha256:f61037e559b46eda9f9cddd27a608a8cf65bd3ddfb67a93dbf89c9cead7500b5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aee9b86b313e55af54ecee336e7a64a8c07b5acb4bb111c4fe9f52eaa2c622e
+oid sha256:087e2751c288c4c17a48b1118b78aff71fccc334df94d07b9adccfe278a56490
 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": 0.0024255544412881136,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03342804613070366,
+  "best_metric": 0.0015228495467454195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06685609226140732,
   "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": 49.055,
       "eval_steps_per_second": 6.134,
       "step": 25
+    },
+    {
+      "epoch": 0.03476516797593181,
+      "grad_norm": 0.10596287250518799,
+      "learning_rate": 5e-05,
+      "loss": 0.0042,
+      "step": 26
+    },
+    {
+      "epoch": 0.036102289821159955,
+      "grad_norm": 0.05240289866924286,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0029,
+      "step": 27
+    },
+    {
+      "epoch": 0.037439411666388096,
+      "grad_norm": 0.04171014577150345,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.038776533511616244,
+      "grad_norm": 0.019574448466300964,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0013,
+      "step": 29
+    },
+    {
+      "epoch": 0.04011365535684439,
+      "grad_norm": 0.03698131442070007,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.001,
+      "step": 30
+    },
+    {
+      "epoch": 0.04145077720207254,
+      "grad_norm": 0.10602346807718277,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0017,
+      "step": 31
+    },
+    {
+      "epoch": 0.04278789904730069,
+      "grad_norm": 0.049237657338380814,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0009,
+      "step": 32
+    },
+    {
+      "epoch": 0.04412502089252883,
+      "grad_norm": 0.020352071151137352,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0004,
+      "step": 33
+    },
+    {
+      "epoch": 0.04546214273775698,
+      "grad_norm": 0.02474248968064785,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0005,
+      "step": 34
+    },
+    {
+      "epoch": 0.046799264582985126,
+      "grad_norm": 0.20188511908054352,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0029,
+      "step": 35
+    },
+    {
+      "epoch": 0.048136386428213274,
+      "grad_norm": 0.01786266639828682,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0002,
+      "step": 36
+    },
+    {
+      "epoch": 0.049473508273441415,
+      "grad_norm": 0.06426721066236496,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0015,
+      "step": 37
+    },
+    {
+      "epoch": 0.05081063011866956,
+      "grad_norm": 0.0700186938047409,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0039,
+      "step": 38
+    },
+    {
+      "epoch": 0.05214775196389771,
+      "grad_norm": 0.06131847947835922,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0025,
+      "step": 39
+    },
+    {
+      "epoch": 0.05348487380912586,
+      "grad_norm": 0.021232590079307556,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0006,
+      "step": 40
+    },
+    {
+      "epoch": 0.054821995654354,
+      "grad_norm": 0.03514159843325615,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0013,
+      "step": 41
+    },
+    {
+      "epoch": 0.05615911749958215,
+      "grad_norm": 0.040575020015239716,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.001,
+      "step": 42
+    },
+    {
+      "epoch": 0.057496239344810296,
+      "grad_norm": 0.029789714142680168,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0011,
+      "step": 43
+    },
+    {
+      "epoch": 0.058833361190038444,
+      "grad_norm": 0.01341679971665144,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0002,
+      "step": 44
+    },
+    {
+      "epoch": 0.06017048303526659,
+      "grad_norm": 0.023356175050139427,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0006,
+      "step": 45
+    },
+    {
+      "epoch": 0.06150760488049473,
+      "grad_norm": 0.002739351475611329,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.06284472672572289,
+      "grad_norm": 0.007518163416534662,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.06418184857095102,
+      "grad_norm": 0.11280187219381332,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0007,
+      "step": 48
+    },
+    {
+      "epoch": 0.06551897041617917,
+      "grad_norm": 0.1114940270781517,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0036,
+      "step": 49
+    },
+    {
+      "epoch": 0.06685609226140732,
+      "grad_norm": 0.07846508920192719,
+      "learning_rate": 0.0,
+      "loss": 0.0012,
+      "step": 50
+    },
+    {
+      "epoch": 0.06685609226140732,
+      "eval_loss": 0.0015228495467454195,
+      "eval_runtime": 102.6882,
+      "eval_samples_per_second": 49.061,
+      "eval_steps_per_second": 6.135,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null