Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971511865a34cde982b550b88fb5be87eff5eb28f53513f321378ac2241f01e4
+oid sha256:2be8ec18da183a3c35991b8321232ef64c8e5dcbb1e949423db59d0200299d99
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8280b2ecbc31b0c972574af848f18c4dcdf802a0e26b973d18c08ab35bf2e2c
+oid sha256:5bb33b6ed97ea320ce9c340b7af9661094e88d7914c4dddf0d4392f106a0bdaf
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:accf9bedcce16bf41114efae3e98d5def5834f7019b44d6425eda4dfe4f295d3
+oid sha256:ed816f3faa53993e8109cf12571c7f2f663bfd2497e7184faa813a553546717f
 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": 0.49634602665901184,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008487163165711862,
+  "best_metric": 0.48906123638153076,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.010608953957139827,
   "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": 5.431,
       "eval_steps_per_second": 2.718,
       "step": 20
+    },
+    {
+      "epoch": 0.008911521323997454,
+      "grad_norm": 0.7227087616920471,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.4094,
+      "step": 21
+    },
+    {
+      "epoch": 0.009335879482283047,
+      "grad_norm": 0.7042548656463623,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4363,
+      "step": 22
+    },
+    {
+      "epoch": 0.00976023764056864,
+      "grad_norm": 1.0040162801742554,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4639,
+      "step": 23
+    },
+    {
+      "epoch": 0.010184595798854232,
+      "grad_norm": 0.7967023253440857,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4846,
+      "step": 24
+    },
+    {
+      "epoch": 0.010608953957139827,
+      "grad_norm": 0.7558794021606445,
+      "learning_rate": 0.0,
+      "loss": 0.4604,
+      "step": 25
+    },
+    {
+      "epoch": 0.010608953957139827,
+      "eval_loss": 0.48906123638153076,
+      "eval_runtime": 185.4008,
+      "eval_samples_per_second": 5.356,
+      "eval_steps_per_second": 2.681,
+      "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": 8461756435267584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null