Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e3246bb74e088073ed09a8ef6e04fdca9108c1faaa3cf9ef9c9431056cd0f6
+oid sha256:d8a1dcae74333aec471f7785abe435082090ebef8ac1945eb4e05a6f0b8cba95
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb55c7aa35d93abe378158ac17e661b0d49b7f5c5484c28c7f7c9ebc5219c590
+oid sha256:0abc46e3f04fcd7b3613e8a6e20453d6486f115971e280b637d5e63b44e6e1d5
 size 14714068

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0242d03bff2e9823ea6f9cce280abc96a821f23bdea70dcfb7ee3146b5dbff08
+oid sha256:89c5508d001f8bf1dfcd1a1341f030027f1d5c0112b1024227206efb7be77253
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c0459891b56fe0f29c14253aae1bf3299d41decf0145418fd0c67479538554
+oid sha256:59f7d4b72a8f7c4215683bd5f1152ceabae62c49ad9b04b70e988a500dcc6f74
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadc1644b3e9e22b1df0c973b4aed74702021d5895c7c1460b50bc235f1d6c4e
+oid sha256:35047986009cd6052adf2007176fc87df149ea2be4b55a657f0d1f59f0f176f4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e0831e0ebf307af5e8447d899439e7794e9bcef4f527a05a98f4b51cd902cf
+oid sha256:faed674125ca290d326480bf2b7bf7341ea0834a921a7c81fd680bc5722ab7a7
 size 15024

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": 1.435750961303711,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00658165364047717,
+  "best_metric": 1.433142900466919,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.008227067050596462,
   "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": 235.714,
       "eval_steps_per_second": 29.476,
       "step": 20
+    },
+    {
+      "epoch": 0.006910736322501028,
+      "grad_norm": 1.3599357604980469,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 5.6457,
+      "step": 21
+    },
+    {
+      "epoch": 0.007239819004524887,
+      "grad_norm": 1.4118783473968506,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.9557,
+      "step": 22
+    },
+    {
+      "epoch": 0.007568901686548745,
+      "grad_norm": 1.0612080097198486,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.4395,
+      "step": 23
+    },
+    {
+      "epoch": 0.007897984368572603,
+      "grad_norm": 1.4210026264190674,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.6698,
+      "step": 24
+    },
+    {
+      "epoch": 0.008227067050596462,
+      "grad_norm": 1.2065868377685547,
+      "learning_rate": 0.0,
+      "loss": 5.5612,
+      "step": 25
+    },
+    {
+      "epoch": 0.008227067050596462,
+      "eval_loss": 1.433142900466919,
+      "eval_runtime": 21.7914,
+      "eval_samples_per_second": 234.864,
+      "eval_steps_per_second": 29.369,
+      "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": 3361113462800384.0,
+  "total_flos": 4279817805496320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null