Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861db575f6af24e47877effc2222b4f547e3e95f03d7637d99c152f42e88e281
+oid sha256:72626c182c2674d4099c9525d3f82d91948a977b16d68d6759884379f63bacb2
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2121913be0912fdbdc5701d9bb3b65d81b6a68a3c92e86856301a82dff70e134
+oid sha256:d3a1946acd46623c24d05b0851ff7e2d657ce44bd52b84932df54b80950229f4
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c73acd1611361430c952163a5deb283e868c1eb83d40cd71e9806df85439f5
+oid sha256:d79e2e2af537356d4498979a0ab44c07896f5ac76ba667f3801e07fd1886d591
 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": 0.828849196434021,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0012974586029614492,
+  "best_metric": 0.8024803996086121,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0016218232537018116,
   "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": 11.244,
       "eval_steps_per_second": 5.623,
       "step": 20
+    },
+    {
+      "epoch": 0.0013623315331095216,
+      "grad_norm": 9.708341598510742,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.4255,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014272044632575942,
+      "grad_norm": 7.934423923492432,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.0924,
+      "step": 22
+    },
+    {
+      "epoch": 0.0014920773934056666,
+      "grad_norm": 10.388670921325684,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.675,
+      "step": 23
+    },
+    {
+      "epoch": 0.001556950323553739,
+      "grad_norm": 9.769749641418457,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.0469,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016218232537018116,
+      "grad_norm": 7.18924617767334,
+      "learning_rate": 0.0,
+      "loss": 2.4988,
+      "step": 25
+    },
+    {
+      "epoch": 0.0016218232537018116,
+      "eval_loss": 0.8024803996086121,
+      "eval_runtime": 593.6732,
+      "eval_samples_per_second": 10.934,
+      "eval_steps_per_second": 5.468,
+      "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": 761852388704256.0,
+  "total_flos": 956050056413184.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null