Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e618b7d89c67c8082c883647d66ff8c7d5be6be58a2ec476480508bf0484d93
+oid sha256:5637be0aec594b8a2fcb6e0fcb24c7052e7bfccaf3c2c02daebe52e28fe37cfe
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9cff5edcb92c538fa46dc4620cdc27c8010a8062e45526facee99065f1e61b
+oid sha256:4caebb5f160c63522deecf7ef7f3c426bc18c9fbdd76a3a9e6d28cb342b62a8f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244fa8387b117ed03fa790162c281e5be692dea750324c3b20dcfad9da126e66
+oid sha256:d98f80bf93cdadd5f33d51b4ed60fd3f98f424d927577ebb1104ef1234ee4ec5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08eb93205120ad48ff3cbf97edd61e29de732256f07b78bf72cf27b6b5606c0
+oid sha256:e1c635aea48d8cc74c524f482c1ff8950767277afe37b49c437f84b84e018024
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d373bd9251abd8a3019eadeba80b0abdd2787dc0941bb29d675d27783b23d45c
+oid sha256:a1994579c5407859309434bb8d31190a1939341296ba5484371a9e70e82d208d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7b234c1bda10b41fb2d0e2c02a973897af826b6bc06d0b0309853161ecfd08
+oid sha256:04e8a3884bba6940cb6f6dad6dfe2ed82baa3b564b20e029cf6d0664894a0728
 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": 0.09752233326435089,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1328462304882099,
+  "best_metric": 0.034579914063215256,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2656924609764198,
   "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": 24.602,
       "eval_steps_per_second": 6.397,
       "step": 25
+    },
+    {
+      "epoch": 0.1381600797077383,
+      "grad_norm": 1.9589002132415771,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1831,
+      "step": 26
+    },
+    {
+      "epoch": 0.14347392892726668,
+      "grad_norm": 2.174701690673828,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1831,
+      "step": 27
+    },
+    {
+      "epoch": 0.14878777814679509,
+      "grad_norm": 2.3990869522094727,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1238,
+      "step": 28
+    },
+    {
+      "epoch": 0.1541016273663235,
+      "grad_norm": 2.058366298675537,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1291,
+      "step": 29
+    },
+    {
+      "epoch": 0.15941547658585187,
+      "grad_norm": 2.2778303623199463,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1427,
+      "step": 30
+    },
+    {
+      "epoch": 0.16472932580538027,
+      "grad_norm": 2.884948492050171,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0802,
+      "step": 31
+    },
+    {
+      "epoch": 0.17004317502490868,
+      "grad_norm": 2.686048984527588,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.155,
+      "step": 32
+    },
+    {
+      "epoch": 0.17535702424443705,
+      "grad_norm": 2.415022611618042,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2073,
+      "step": 33
+    },
+    {
+      "epoch": 0.18067087346396546,
+      "grad_norm": 2.207425117492676,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1384,
+      "step": 34
+    },
+    {
+      "epoch": 0.18598472268349386,
+      "grad_norm": 1.7799278497695923,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1412,
+      "step": 35
+    },
+    {
+      "epoch": 0.19129857190302224,
+      "grad_norm": 1.3226287364959717,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0728,
+      "step": 36
+    },
+    {
+      "epoch": 0.19661242112255065,
+      "grad_norm": 1.6843650341033936,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1343,
+      "step": 37
+    },
+    {
+      "epoch": 0.20192627034207905,
+      "grad_norm": 1.350917935371399,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1155,
+      "step": 38
+    },
+    {
+      "epoch": 0.20724011956160743,
+      "grad_norm": 1.1504665613174438,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0929,
+      "step": 39
+    },
+    {
+      "epoch": 0.21255396878113583,
+      "grad_norm": 1.5761011838912964,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1395,
+      "step": 40
+    },
+    {
+      "epoch": 0.21786781800066424,
+      "grad_norm": 1.5024954080581665,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.107,
+      "step": 41
+    },
+    {
+      "epoch": 0.22318166722019261,
+      "grad_norm": 1.106066346168518,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1,
+      "step": 42
+    },
+    {
+      "epoch": 0.22849551643972102,
+      "grad_norm": 1.5602272748947144,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0827,
+      "step": 43
+    },
+    {
+      "epoch": 0.23380936565924942,
+      "grad_norm": 1.4273624420166016,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0767,
+      "step": 44
+    },
+    {
+      "epoch": 0.2391232148787778,
+      "grad_norm": 1.07826566696167,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0417,
+      "step": 45
+    },
+    {
+      "epoch": 0.2444370640983062,
+      "grad_norm": 1.6851541996002197,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0851,
+      "step": 46
+    },
+    {
+      "epoch": 0.2497509133178346,
+      "grad_norm": 1.4490783214569092,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0528,
+      "step": 47
+    },
+    {
+      "epoch": 0.255064762537363,
+      "grad_norm": 1.4430365562438965,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.05,
+      "step": 48
+    },
+    {
+      "epoch": 0.2603786117568914,
+      "grad_norm": 2.2319040298461914,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0895,
+      "step": 49
+    },
+    {
+      "epoch": 0.2656924609764198,
+      "grad_norm": 1.0726263523101807,
+      "learning_rate": 1e-05,
+      "loss": 0.024,
+      "step": 50
+    },
+    {
+      "epoch": 0.2656924609764198,
+      "eval_loss": 0.034579914063215256,
+      "eval_runtime": 2.0459,
+      "eval_samples_per_second": 24.439,
+      "eval_steps_per_second": 6.354,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null