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:b50237a3d15d804125a5675b4ce9cca1a869fd78e52cc404b874aec95f7c7dcf
+oid sha256:97bd4a5e24dbfd88be318c5fb77f75de85b3c8b2197c2ad8edddbf493e0dfe68
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7915f1e8b14fc4d269d7b8160466ba5ac1188fba4468083b93cbdb93e8a5d8bd
+oid sha256:c913b5c9d90c0696f9339ff4995b85847671f643e1bdd85c2e8213c953f081f1
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e7378d99b36344b8b6a4a7ba876fd02c18a1120c409c7a3963e87dd6ba238a
+oid sha256:44626dc9e8737a032ebeabbdc4cb0af21be9285006b2991ff04d45d781671bf5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea741dad6929a2e8347a88a6e20ecf6efacfc6aa1e8ff390232f82872415b799
+oid sha256:024576972d0d06c703fac70b9ff96bed35ab5b71a56cfa90d8c4b207916f4675
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc08b80d79761b5a208c9528a677cc92f9aca6e161b67a592586ca800ff7f823
+oid sha256:e360ba75c165a83b29577b042a3ef1e63f427b2e775d0d8f286effb84be693ca
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4634e16f4da2d202b561fea7c0169f3ae015f6a23a3a10550ea0f00b925c8952
+oid sha256:df44603e7d7e6632ddd1ba047fa007f7e26b49a08fdf968890db8363161091c2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7558532953262329,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34572169403630076,
+  "best_metric": 0.6048961877822876,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6914433880726015,
   "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": 39.985,
       "eval_steps_per_second": 10.396,
       "step": 25
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 4.026302814483643,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6363,
+      "step": 26
+    },
+    {
+      "epoch": 0.37337942955920483,
+      "grad_norm": 1.810630202293396,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5036,
+      "step": 27
+    },
+    {
+      "epoch": 0.38720829732065687,
+      "grad_norm": 2.4514455795288086,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4986,
+      "step": 28
+    },
+    {
+      "epoch": 0.4010371650821089,
+      "grad_norm": 3.9547641277313232,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7143,
+      "step": 29
+    },
+    {
+      "epoch": 0.41486603284356094,
+      "grad_norm": 3.1139731407165527,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6038,
+      "step": 30
+    },
+    {
+      "epoch": 0.428694900605013,
+      "grad_norm": 2.0004587173461914,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4481,
+      "step": 31
+    },
+    {
+      "epoch": 0.442523768366465,
+      "grad_norm": 1.9126585721969604,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5361,
+      "step": 32
+    },
+    {
+      "epoch": 0.45635263612791704,
+      "grad_norm": 1.7938328981399536,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4805,
+      "step": 33
+    },
+    {
+      "epoch": 0.4701815038893691,
+      "grad_norm": 1.4720524549484253,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4319,
+      "step": 34
+    },
+    {
+      "epoch": 0.4840103716508211,
+      "grad_norm": 1.2695094347000122,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.466,
+      "step": 35
+    },
+    {
+      "epoch": 0.4978392394122731,
+      "grad_norm": 1.4350192546844482,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4778,
+      "step": 36
+    },
+    {
+      "epoch": 0.5116681071737251,
+      "grad_norm": 2.107414722442627,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6617,
+      "step": 37
+    },
+    {
+      "epoch": 0.5254969749351772,
+      "grad_norm": 1.9258248805999756,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5402,
+      "step": 38
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 3.372992515563965,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4107,
+      "step": 39
+    },
+    {
+      "epoch": 0.5531547104580813,
+      "grad_norm": 2.1692512035369873,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4895,
+      "step": 40
+    },
+    {
+      "epoch": 0.5669835782195333,
+      "grad_norm": 2.00020170211792,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.504,
+      "step": 41
+    },
+    {
+      "epoch": 0.5808124459809854,
+      "grad_norm": 2.7335145473480225,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4922,
+      "step": 42
+    },
+    {
+      "epoch": 0.5946413137424373,
+      "grad_norm": 2.1037230491638184,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5219,
+      "step": 43
+    },
+    {
+      "epoch": 0.6084701815038893,
+      "grad_norm": 1.8822736740112305,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.445,
+      "step": 44
+    },
+    {
+      "epoch": 0.6222990492653414,
+      "grad_norm": 1.46221923828125,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4146,
+      "step": 45
+    },
+    {
+      "epoch": 0.6361279170267934,
+      "grad_norm": 1.7882673740386963,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4299,
+      "step": 46
+    },
+    {
+      "epoch": 0.6499567847882455,
+      "grad_norm": 1.2945713996887207,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3671,
+      "step": 47
+    },
+    {
+      "epoch": 0.6637856525496975,
+      "grad_norm": 2.039731740951538,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5587,
+      "step": 48
+    },
+    {
+      "epoch": 0.6776145203111495,
+      "grad_norm": 1.9501632452011108,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.471,
+      "step": 49
+    },
+    {
+      "epoch": 0.6914433880726015,
+      "grad_norm": 2.397514820098877,
+      "learning_rate": 1e-05,
+      "loss": 0.747,
+      "step": 50
+    },
+    {
+      "epoch": 0.6914433880726015,
+      "eval_loss": 0.6048961877822876,
+      "eval_runtime": 1.2504,
+      "eval_samples_per_second": 39.987,
+      "eval_steps_per_second": 10.397,
+      "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