Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6af08d76a9fceca32bff48f799195d010dca79f33f8c81d319400ad2402ccb7
+oid sha256:dfb31ff951db086ce0c3e2a11dec3ef45b21fe5e9330f5bae7b20834db104d99
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea6c15f3b7a29a14d859e550c46d3a37ab660f7fac91aa2b67f82f5dfb3e735
+oid sha256:057fec07c52243a3cba898a5d3da8247cf1680e7afac3f129ab09cc367a166fe
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24234b9f02099e93a544d84dde2a4254f3926f51e08f716f06999d6cb929bbeb
+oid sha256:2b2ac2b2cc7705ad7e3ce026f61ab402804e7448c3282575e8e4de6750ba277a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb9c0d62d6b3cf0976c16f73e9bd814b298ebffa1786831bc2a68d8e48809b9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.862091302871704,
-  "best_model_checkpoint": "miner_id_24/checkpoint-550",
-  "epoch": 0.15018089972011742,
+  "best_metric": 1.860011100769043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.16383370878558262,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -488,6 +488,49 @@
       "eval_samples_per_second": 25.161,
       "eval_steps_per_second": 6.29,
       "step": 550
+    },
+    {
+      "epoch": 0.15291146153321045,
+      "grad_norm": 11.77377986907959,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 7.2398,
+      "step": 560
+    },
+    {
+      "epoch": 0.1556420233463035,
+      "grad_norm": 10.591424942016602,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 7.6634,
+      "step": 570
+    },
+    {
+      "epoch": 0.15837258515939653,
+      "grad_norm": 12.146462440490723,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 7.112,
+      "step": 580
+    },
+    {
+      "epoch": 0.1611031469724896,
+      "grad_norm": 15.12509822845459,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 7.505,
+      "step": 590
+    },
+    {
+      "epoch": 0.16383370878558262,
+      "grad_norm": 28.584569931030273,
+      "learning_rate": 0.0,
+      "loss": 7.9429,
+      "step": 600
+    },
+    {
+      "epoch": 0.16383370878558262,
+      "eval_loss": 1.860011100769043,
+      "eval_runtime": 244.4477,
+      "eval_samples_per_second": 25.232,
+      "eval_steps_per_second": 6.308,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -511,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.867212242747392e+17,
+  "total_flos": 4.218776992088064e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null