Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e9226eb0c13650147b5ec8e5b179f1a236c7116deb10fb92ba3aaf368f1a7ab
+oid sha256:f0a116ce93eb46e0fb4b5b101383278e6c403ef5a54f611522b147e1a204436e
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50af909fbc8792116dca5743caf68131afbd3a176e3bf3ad743b9f09a25677fd
+oid sha256:a3510bcac0966004a91a6511e439d8526e42568d050e122e8db19278ded0a202
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e320216c8c37453efaf379357cdd82ac7d0fd048ad91bf56ed53f1a26cee7e5f
+oid sha256:0c097931884067265a3ab6ab3bfee8ecda1ecf3376a02f214aa1ed4ddacce75b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5499a551a027da9850bb0d6cc4c5b43b0207603310bc02886d35d8c9f52220e0
+oid sha256:6ae76f7aec08d5f189ca5350da41f075e8c32fc7ee05fbfe4d21d75b82029ea9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55dd6ecd6878ebbb700609ac0e8fd3fe1aecf7f8dc7c1eeeed2f63618a2c3bf0
+oid sha256:92d2f7523d26831dc1a23b3383c965499e243b4fee9cc8d41f9bdd63e68abba2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1921569be3d944cce0e26410e25c17941f7da5422b1f8f119415d8f59362fc30
+oid sha256:0e897941f1a277ccc3de806af581825326cc30d10f2846645da7947542ecb35e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.517699122428894,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.03702104029123218,
+  "epoch": 0.04689331770222743,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 23.177,
       "eval_steps_per_second": 6.026,
       "step": 75
+    },
+    {
+      "epoch": 0.03751465416178194,
+      "grad_norm": 0.715366005897522,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 1.5203,
+      "step": 76
+    },
+    {
+      "epoch": 0.03800826803233171,
+      "grad_norm": 0.7529436945915222,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 1.468,
+      "step": 77
+    },
+    {
+      "epoch": 0.03850188190288147,
+      "grad_norm": 0.8566577434539795,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 1.5055,
+      "step": 78
+    },
+    {
+      "epoch": 0.038995495773431234,
+      "grad_norm": 0.7840465307235718,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 1.525,
+      "step": 79
+    },
+    {
+      "epoch": 0.039489109643980995,
+      "grad_norm": 0.7184439897537231,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 1.5049,
+      "step": 80
+    },
+    {
+      "epoch": 0.039982723514530756,
+      "grad_norm": 0.7097110748291016,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.3389,
+      "step": 81
+    },
+    {
+      "epoch": 0.040476337385080524,
+      "grad_norm": 0.7986069917678833,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 1.5583,
+      "step": 82
+    },
+    {
+      "epoch": 0.040969951255630285,
+      "grad_norm": 0.8031150102615356,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 1.405,
+      "step": 83
+    },
+    {
+      "epoch": 0.041463565126180046,
+      "grad_norm": 0.7863020896911621,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 1.4955,
+      "step": 84
+    },
+    {
+      "epoch": 0.04195717899672981,
+      "grad_norm": 0.8263758420944214,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 1.4869,
+      "step": 85
+    },
+    {
+      "epoch": 0.04245079286727957,
+      "grad_norm": 0.7383260726928711,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 1.4159,
+      "step": 86
+    },
+    {
+      "epoch": 0.04294440673782933,
+      "grad_norm": 0.8411725759506226,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 1.3053,
+      "step": 87
+    },
+    {
+      "epoch": 0.0434380206083791,
+      "grad_norm": 0.7437005639076233,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 1.4478,
+      "step": 88
+    },
+    {
+      "epoch": 0.04393163447892886,
+      "grad_norm": 0.7593280673027039,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 1.5367,
+      "step": 89
+    },
+    {
+      "epoch": 0.04442524834947862,
+      "grad_norm": 0.7815626859664917,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 1.4695,
+      "step": 90
+    },
+    {
+      "epoch": 0.04491886222002838,
+      "grad_norm": 0.7754625678062439,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 1.4679,
+      "step": 91
+    },
+    {
+      "epoch": 0.04541247609057814,
+      "grad_norm": 0.7283334136009216,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 1.4585,
+      "step": 92
+    },
+    {
+      "epoch": 0.04590608996112791,
+      "grad_norm": 0.795418381690979,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 1.4876,
+      "step": 93
+    },
+    {
+      "epoch": 0.04639970383167767,
+      "grad_norm": 0.7504608631134033,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 1.4626,
+      "step": 94
+    },
+    {
+      "epoch": 0.04689331770222743,
+      "grad_norm": 0.7937198281288147,
+      "learning_rate": 1e-05,
+      "loss": 1.4679,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.43721341763584e+17,
+  "total_flos": 3.087136995672064e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null