Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e04781f11aef4f8e251b51bcf4df39e10f1389cdd0984b0d62615ded631ae2a
+oid sha256:b9fe6983da049f0c41ec5b43df746b607311eb9d5ea393f9fd5c2b1b2d444346
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d309a0fe44de7cc9230141e9fa7ff74c1214b9e40e7084ce01f8d219dd7de6c5
+oid sha256:94a94fac3f1ad46d4cf0703402f7747dd3c3e4cbfa9767af12889d8a2ead5f10
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9d409a290674bbbf002d151060c40fb09db12e926626cb1d6e587c518d19b7
+oid sha256:387dfd6dfe741a0b34c6f6c61040ee4a533c506b6c6d1cac9223c508941357bf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c328dd1baeb8e509d6021039e4828dd873d8f446a32c7b0a0f1124f50a6a187
+oid sha256:aeb5382fb74fa78273273de65fd109f24d458b0ee7c8185eedd044abcc68e9c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4ff9db4bf3e9f53633885cd47615ff37af25396e668b96d6f519f738ab6edf
+oid sha256:c92a48b844813083ebe0117e4878b41bab78e8dc096dc101cde4d6a23b35852b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784d917e6ec419b422c0692bfc72aed61d2168de0df8757559c3928abc1bf30d
+oid sha256:718e7097cfe8368bf1aa1590e471b3bd734944333ff85d0482277f6a58159a9a
 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": 0.32884421944618225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12330456226880394,
+  "best_metric": 0.3012233078479767,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2466091245376079,
   "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": 67.471,
       "eval_steps_per_second": 8.446,
       "step": 25
+    },
+    {
+      "epoch": 0.1282367447595561,
+      "grad_norm": 0.9765304327011108,
+      "learning_rate": 5e-05,
+      "loss": 0.3001,
+      "step": 26
+    },
+    {
+      "epoch": 0.13316892725030827,
+      "grad_norm": 0.5973970890045166,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3099,
+      "step": 27
+    },
+    {
+      "epoch": 0.1381011097410604,
+      "grad_norm": 0.4834292531013489,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3176,
+      "step": 28
+    },
+    {
+      "epoch": 0.14303329223181258,
+      "grad_norm": 0.42007580399513245,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3156,
+      "step": 29
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.5430471301078796,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2989,
+      "step": 30
+    },
+    {
+      "epoch": 0.15289765721331688,
+      "grad_norm": 0.5922935605049133,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3115,
+      "step": 31
+    },
+    {
+      "epoch": 0.15782983970406905,
+      "grad_norm": 0.5440362691879272,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3028,
+      "step": 32
+    },
+    {
+      "epoch": 0.16276202219482122,
+      "grad_norm": 0.536367654800415,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3017,
+      "step": 33
+    },
+    {
+      "epoch": 0.16769420468557336,
+      "grad_norm": 0.5181109309196472,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2986,
+      "step": 34
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.6546456813812256,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3319,
+      "step": 35
+    },
+    {
+      "epoch": 0.17755856966707767,
+      "grad_norm": 0.6339057087898254,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3259,
+      "step": 36
+    },
+    {
+      "epoch": 0.18249075215782984,
+      "grad_norm": 1.3519337177276611,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3915,
+      "step": 37
+    },
+    {
+      "epoch": 0.187422934648582,
+      "grad_norm": 0.47506600618362427,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2711,
+      "step": 38
+    },
+    {
+      "epoch": 0.19235511713933415,
+      "grad_norm": 0.6212289333343506,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2839,
+      "step": 39
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.6477142572402954,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2859,
+      "step": 40
+    },
+    {
+      "epoch": 0.20221948212083848,
+      "grad_norm": 0.8822614550590515,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3087,
+      "step": 41
+    },
+    {
+      "epoch": 0.20715166461159062,
+      "grad_norm": 0.7327987551689148,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2934,
+      "step": 42
+    },
+    {
+      "epoch": 0.2120838471023428,
+      "grad_norm": 0.5722291469573975,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2892,
+      "step": 43
+    },
+    {
+      "epoch": 0.21701602959309493,
+      "grad_norm": 0.6610158085823059,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3084,
+      "step": 44
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.583101212978363,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2954,
+      "step": 45
+    },
+    {
+      "epoch": 0.22688039457459927,
+      "grad_norm": 0.5043917298316956,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2806,
+      "step": 46
+    },
+    {
+      "epoch": 0.2318125770653514,
+      "grad_norm": 0.624017059803009,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3121,
+      "step": 47
+    },
+    {
+      "epoch": 0.23674475955610358,
+      "grad_norm": 0.4712766110897064,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2941,
+      "step": 48
+    },
+    {
+      "epoch": 0.24167694204685575,
+      "grad_norm": 0.6848615407943726,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3745,
+      "step": 49
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.3380556106567383,
+      "learning_rate": 0.0,
+      "loss": 0.2895,
+      "step": 50
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "eval_loss": 0.3012233078479767,
+      "eval_runtime": 20.2561,
+      "eval_samples_per_second": 67.437,
+      "eval_steps_per_second": 8.442,
+      "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": 2.898563020567347e+16,
+  "total_flos": 5.80081729709015e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null