Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e90ef3a37444d105c9a97106d48bb6eca3d8b7d2e919320690f2892932bfc6
+oid sha256:8a1d2e1f41301fd003168365192189372f309327d370e8f86ac98f8e6da7582d
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e401bee486f1f854d07a3eeb56a7bb5113cdd190863bbe490890b394b31db0b4
+oid sha256:83dc748da72ddadf24f4728d7fd837b1d8413f6ed8ef63ece337fdbf34753f67
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e41105308a2baba23797bcc1e77a18aac124c0e4102beacfeeb0f5770a89da
+oid sha256:0db6cbd720e443cc6d79578a4091c3d210a8b1af07d62db58fcf433075310dfa
 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": 11.931827545166016,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09489916963226572,
+  "best_metric": 11.931747436523438,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1423487544483986,
   "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": 198.131,
       "eval_steps_per_second": 50.089,
       "step": 20
+    },
+    {
+      "epoch": 0.099644128113879,
+      "grad_norm": 0.042521167546510696,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9327,
+      "step": 21
+    },
+    {
+      "epoch": 0.11387900355871886,
+      "grad_norm": 0.04662325605750084,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9348,
+      "step": 24
+    },
+    {
+      "epoch": 0.11862396204033215,
+      "eval_loss": 11.931800842285156,
+      "eval_runtime": 0.8704,
+      "eval_samples_per_second": 204.515,
+      "eval_steps_per_second": 51.703,
+      "step": 25
+    },
+    {
+      "epoch": 0.12811387900355872,
+      "grad_norm": 0.05982173606753349,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9331,
+      "step": 27
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "grad_norm": 0.03850724920630455,
+      "learning_rate": 0.0,
+      "loss": 11.9307,
+      "step": 30
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "eval_loss": 11.931747436523438,
+      "eval_runtime": 0.8532,
+      "eval_samples_per_second": 208.63,
+      "eval_steps_per_second": 52.744,
+      "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": 14989393920.0,
+  "total_flos": 22484090880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null