Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2858ae17c9e809160fd4c780130d7cbdb9ff665c42d06916ca31186217320c90
+oid sha256:a9a437e359cecf6cfe5ffbece33fb2f242d349679083a91f35d24a71dfdf206d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a76e1c96071186254679eb95135d535b279ca9d37f6e14f5a73804622723d2
+oid sha256:ab70219aee6084801a8ddf95f80c571c15b3fce874db11e4ac673a2a90fab867
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c10616b6db17724e17846972facdd56debf0a71a5f856a8d9161a9eb54673cf
+oid sha256:9b740409d965906dcc7afbc9da6dc598afe18b6141719b9977f0d1a009f0f895
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8038806915283203,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011302627860977677,
+  "best_metric": 0.7749077677726746,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.016953941791466517,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 2.138,
       "eval_steps_per_second": 0.535,
       "step": 20
+    },
+    {
+      "epoch": 0.01186775925402656,
+      "grad_norm": 0.1351657211780548,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.782,
+      "step": 21
+    },
+    {
+      "epoch": 0.013563153433173212,
+      "grad_norm": 0.12833859026432037,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.7737,
+      "step": 24
+    },
+    {
+      "epoch": 0.014128284826222097,
+      "eval_loss": 0.7793111205101013,
+      "eval_runtime": 698.6184,
+      "eval_samples_per_second": 2.133,
+      "eval_steps_per_second": 0.534,
+      "step": 25
+    },
+    {
+      "epoch": 0.015258547612319864,
+      "grad_norm": 0.13125252723693848,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.7798,
+      "step": 27
+    },
+    {
+      "epoch": 0.016953941791466517,
+      "grad_norm": 0.13646282255649567,
+      "learning_rate": 0.0,
+      "loss": 0.7686,
+      "step": 30
+    },
+    {
+      "epoch": 0.016953941791466517,
+      "eval_loss": 0.7749077677726746,
+      "eval_runtime": 696.2618,
+      "eval_samples_per_second": 2.14,
+      "eval_steps_per_second": 0.536,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.06592868958208e+16,
+  "total_flos": 7.59889303437312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null