Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265a547e14b47c71afa038498cd80e1ae4cd32ef06066a837c1bcd242222e613
+oid sha256:126beb816f483656af6cb2f8ee8d6d5131da8ceb2e966f5306048e43d6118bda
 size 51431872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45872ef868e7360d9ab367f57b14d6269205d65966f36d3b735d397e170756b2
+oid sha256:c44c37c405fb95fa480bf32e223633ad3a81c219a050395f032703e5d9898d0f
 size 26550260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc46e58008fcfaf26de2fc50b7a399e2d6e44f2214266c62484151ce8f2a61a1
+oid sha256:6f2ec64b5bc1a5dee2c141e3e217e5feaa4634a87a716b0ea918096c3fa7861f
 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": 1.3041226863861084,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004067314047485892,
+  "best_metric": 1.298373818397522,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005084142559357364,
   "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": 9.571,
       "eval_steps_per_second": 4.788,
       "step": 20
+    },
+    {
+      "epoch": 0.004270679749860186,
+      "grad_norm": 1.1199743747711182,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2086,
+      "step": 21
+    },
+    {
+      "epoch": 0.004474045452234481,
+      "grad_norm": 1.324095606803894,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3939,
+      "step": 22
+    },
+    {
+      "epoch": 0.004677411154608775,
+      "grad_norm": 1.1704427003860474,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.3285,
+      "step": 23
+    },
+    {
+      "epoch": 0.0048807768569830694,
+      "grad_norm": 1.2591584920883179,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.3386,
+      "step": 24
+    },
+    {
+      "epoch": 0.005084142559357364,
+      "grad_norm": 1.2384811639785767,
+      "learning_rate": 0.0,
+      "loss": 1.2469,
+      "step": 25
+    },
+    {
+      "epoch": 0.005084142559357364,
+      "eval_loss": 1.298373818397522,
+      "eval_runtime": 216.2229,
+      "eval_samples_per_second": 9.578,
+      "eval_steps_per_second": 4.791,
+      "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": 1540684932710400.0,
+  "total_flos": 1921100965478400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null