Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737b3b81471290f216f550edbb32d5e2f8ccb70f50d6d7db78358015e02348aa
+oid sha256:47f78175246f93841e4614f3ac5524ebe20072074f61b4704260776355993c8f
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4685161137cec441ee867b2ec73724520377d281e573da60cd05c0a611235079
+oid sha256:2e282d14f6d1a81c7db381fb09fb0e52a3dd281b44bb3f9f15fc6529e741f46d
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00fe2703438caf8f34765aaa829ebca35723d3851968a6377698684b1653e32
+oid sha256:be60579b2fb761135f28ae224981e51a37f04047be87570511252fd870280104
 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": 0.8296452760696411,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0012974586029614492,
+  "best_metric": 0.8028371334075928,
+  "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": 10.625,
       "eval_steps_per_second": 5.313,
       "step": 20
+    },
+    {
+      "epoch": 0.0013623315331095216,
+      "grad_norm": 7.80236291885376,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.3949,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014272044632575942,
+      "grad_norm": 7.568052768707275,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.0615,
+      "step": 22
+    },
+    {
+      "epoch": 0.0014920773934056666,
+      "grad_norm": 13.245499610900879,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.7618,
+      "step": 23
+    },
+    {
+      "epoch": 0.001556950323553739,
+      "grad_norm": 9.530472755432129,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.1139,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016218232537018116,
+      "grad_norm": 7.105537414550781,
+      "learning_rate": 0.0,
+      "loss": 2.4744,
+      "step": 25
+    },
+    {
+      "epoch": 0.0016218232537018116,
+      "eval_loss": 0.8028371334075928,
+      "eval_runtime": 578.5339,
+      "eval_samples_per_second": 11.22,
+      "eval_steps_per_second": 5.611,
+      "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