Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b664475d30cddabc74617e824e3c426b164cc9c0db4faa041ccb4ad70326f1
+oid sha256:94a73a15b32e2cc84ae73b4111a0903f366a283ce555582cc7c11049f6b9a79a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42cff559b6cf9bc6dc5b88977771bbf33880829ab96bba824d8387d4489b301
+oid sha256:122f4d80e43d9966365138c709839908504c0697fdd52cf1fcc4739bd97dc37f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:accf9bedcce16bf41114efae3e98d5def5834f7019b44d6425eda4dfe4f295d3
+oid sha256:f9fff67724aa99087c058ac2f89f5995e22c8300741761872cd863898979a603
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5228610634803772,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 0.519059956073761,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01063264221158958,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 5.23,
       "eval_steps_per_second": 2.615,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 0.4729395806789398,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5609,
+      "step": 21
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": 0.5044227838516235,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5515,
+      "step": 22
+    },
+    {
+      "epoch": 0.009782030834662414,
+      "grad_norm": 0.49624571204185486,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5538,
+      "step": 23
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 0.5628948211669922,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5428,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "grad_norm": 0.475276917219162,
+      "learning_rate": 0.0,
+      "loss": 0.5549,
+      "step": 25
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 0.519059956073761,
+      "eval_runtime": 190.5894,
+      "eval_samples_per_second": 5.194,
+      "eval_steps_per_second": 2.597,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6704670399528960.0,
+  "total_flos": 8230560904249344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null