Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8791fae23023cf2106e0168a68fe7cfc76cf5009e3729f4af35acf290bf1f97
+oid sha256:6f2f0a76da24a1ad81dcda706248e253d52a191704ea53265b6d9465df517e2d
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715153c301e34bc9e1ba77f1996ccb2e9a6de47d2fddaab7f57690744eaa6ccb
+oid sha256:501e40adaa4f70964a8cd6a1dfdb25bf4ad0f9592e59902ac2cdb07292b6512f
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e92355acea1d637dfee0848ce97e0a35db7f2918dda84a5212f2ddf67f03a2c
+oid sha256:17a037725bec0a8d6f8f48eff9706f34e57cf5ea36d4c0fe1640235ccea83807
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3b597e507c818a1b809c10b26354c2c68ff2bc801d315b5aadc95eb0081237
+oid sha256:c35e24dc9e28d5479cc0116b5a139eadfaf05e8ad587dfecd6be3b09104334b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.018733024597168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-340",
-  "epoch": 0.01536688436419516,
+  "best_metric": 11.018669128417969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.01581885155137737,
   "eval_steps": 5,
-  "global_step": 340,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2939,6 +2939,92 @@
       "eval_samples_per_second": 52.85,
       "eval_steps_per_second": 26.428,
       "step": 340
+    },
+    {
+      "epoch": 0.01541208108291338,
+      "grad_norm": 0.46714112162590027,
+      "learning_rate": 4.7613544987293446e-05,
+      "loss": 44.007,
+      "step": 341
+    },
+    {
+      "epoch": 0.015457277801631602,
+      "grad_norm": 0.449789434671402,
+      "learning_rate": 4.706850020762126e-05,
+      "loss": 44.0599,
+      "step": 342
+    },
+    {
+      "epoch": 0.015502474520349823,
+      "grad_norm": 0.5278406739234924,
+      "learning_rate": 4.6525631234587034e-05,
+      "loss": 44.0606,
+      "step": 343
+    },
+    {
+      "epoch": 0.015547671239068044,
+      "grad_norm": 0.5856757760047913,
+      "learning_rate": 4.5984960383408005e-05,
+      "loss": 44.0862,
+      "step": 344
+    },
+    {
+      "epoch": 0.015592867957786265,
+      "grad_norm": 0.48914504051208496,
+      "learning_rate": 4.544650987894514e-05,
+      "loss": 44.0642,
+      "step": 345
+    },
+    {
+      "epoch": 0.015592867957786265,
+      "eval_loss": 11.018689155578613,
+      "eval_runtime": 176.1852,
+      "eval_samples_per_second": 52.882,
+      "eval_steps_per_second": 26.444,
+      "step": 345
+    },
+    {
+      "epoch": 0.015638064676504485,
+      "grad_norm": 0.5346770882606506,
+      "learning_rate": 4.491030185478976e-05,
+      "loss": 44.122,
+      "step": 346
+    },
+    {
+      "epoch": 0.015683261395222706,
+      "grad_norm": 0.4303387701511383,
+      "learning_rate": 4.437635835235353e-05,
+      "loss": 44.0754,
+      "step": 347
+    },
+    {
+      "epoch": 0.015728458113940927,
+      "grad_norm": 0.3995809555053711,
+      "learning_rate": 4.384470131996252e-05,
+      "loss": 44.1039,
+      "step": 348
+    },
+    {
+      "epoch": 0.015773654832659148,
+      "grad_norm": 0.44882121682167053,
+      "learning_rate": 4.331535261195504e-05,
+      "loss": 44.1023,
+      "step": 349
+    },
+    {
+      "epoch": 0.01581885155137737,
+      "grad_norm": 0.4910334646701813,
+      "learning_rate": 4.278833398778306e-05,
+      "loss": 44.0906,
+      "step": 350
+    },
+    {
+      "epoch": 0.01581885155137737,
+      "eval_loss": 11.018669128417969,
+      "eval_runtime": 176.2273,
+      "eval_samples_per_second": 52.869,
+      "eval_steps_per_second": 26.437,
+      "step": 350
     }
   ],
   "logging_steps": 1,
@@ -2967,7 +3053,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3572288716800.0,
+  "total_flos": 3677356032000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null