Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f81b9baf59b723a68dfec8f44098888ce4d26f61aa7f6a22198f3a9e138cd0
+oid sha256:5bbd294c63c30b8ded15e640640301d17630ba26312d5e5d1bbf10630079aade
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e9f9e4c321622a51812976b454c3d98eb7daf4042c51216deb5d76d96d2af0
+oid sha256:495c8f0df1cb029f545f04d3217087e85ea60df6f9eb7e8082200b6373a91c08
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c899caaa1f40add01082c15484b02b356ab654441587ed561e86eefc96d5f9
+oid sha256:f72f293640c90c50823e31afabdf4d9f964892b0a26e6a5836a02875e0f9f3f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
+oid sha256:6230a4f38a0ea478447f5ea0afea90b5855d705f677280e45e7e6abb464194a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4894201755523682,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.14573718727228566,
+  "best_metric": 1.369873285293579,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.17002671848433326,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 16.73,
       "eval_steps_per_second": 4.187,
       "step": 300
+    },
+    {
+      "epoch": 0.15059509351469516,
+      "grad_norm": 9.372559547424316,
+      "learning_rate": 7.694492759663374e-05,
+      "loss": 2.9475,
+      "step": 310
+    },
+    {
+      "epoch": 0.1554529997571047,
+      "grad_norm": 10.691730499267578,
+      "learning_rate": 7.013477507094284e-05,
+      "loss": 2.1435,
+      "step": 320
+    },
+    {
+      "epoch": 0.1603109059995142,
+      "grad_norm": 17.997329711914062,
+      "learning_rate": 6.347743076828492e-05,
+      "loss": 2.7516,
+      "step": 330
+    },
+    {
+      "epoch": 0.16516881224192373,
+      "grad_norm": 16.696796417236328,
+      "learning_rate": 5.700532860090863e-05,
+      "loss": 3.2521,
+      "step": 340
+    },
+    {
+      "epoch": 0.17002671848433326,
+      "grad_norm": 28.0440673828125,
+      "learning_rate": 5.075000000000002e-05,
+      "loss": 2.8703,
+      "step": 350
+    },
+    {
+      "epoch": 0.17002671848433326,
+      "eval_loss": 1.369873285293579,
+      "eval_runtime": 51.81,
+      "eval_samples_per_second": 16.734,
+      "eval_steps_per_second": 4.188,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.36624253370368e+16,
+  "total_flos": 6.26061628932096e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null