Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792e35fb60396d9b8e7db932bf2dcf92f78aba70512d1e40854d4b912c624e54
+oid sha256:9a6f7c977941f088492ea8fa4ce8fcba8fcaede7e7078b110d1447916b3e2f87
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03711935d7ce18de162ab925d6a4c6ff97d0a93db690904f1284552721051ace
+oid sha256:ac8d0eb85dac2629c857833d31e29b566cdbebace4f5516df5845b3845bae0b6
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cadab99cb737fd145d8498d991019e423b3a3da1ae160d70a0eb85b120d70a
+oid sha256:894f47eeca20f821985a1dbdab92534a48fb040caa0f64f2aa8078dfd596adbe
 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": 11.035008430480957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07380073800738007,
+  "best_metric": 11.026297569274902,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.09225092250922509,
   "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": 145.842,
       "eval_steps_per_second": 73.555,
       "step": 20
+    },
+    {
+      "epoch": 0.07749077490774908,
+      "grad_norm": 3.1229958534240723,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 44.0982,
+      "step": 21
+    },
+    {
+      "epoch": 0.08118081180811808,
+      "grad_norm": 2.5841705799102783,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.2067,
+      "step": 22
+    },
+    {
+      "epoch": 0.08487084870848709,
+      "grad_norm": 3.5494275093078613,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 44.0395,
+      "step": 23
+    },
+    {
+      "epoch": 0.08856088560885608,
+      "grad_norm": 2.663440704345703,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 44.2512,
+      "step": 24
+    },
+    {
+      "epoch": 0.09225092250922509,
+      "grad_norm": 3.1340599060058594,
+      "learning_rate": 0.0,
+      "loss": 44.0613,
+      "step": 25
+    },
+    {
+      "epoch": 0.09225092250922509,
+      "eval_loss": 11.026297569274902,
+      "eval_runtime": 0.7788,
+      "eval_samples_per_second": 147.658,
+      "eval_steps_per_second": 74.471,
+      "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": 383380881408.0,
+  "total_flos": 479828901888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null