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:b6d4b69f07223ef588c6ad3bb99e1dd0336ad0303ea1de5235b3a591b57552c8
+oid sha256:316e80eb56bcf4d9e068c47d3076563fb046d9a57ea49c43348f31561f9faf6a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b06831ef948192e1eef4069f7601a7596fdc617f8dec5fa8785b85eabde564
+oid sha256:83094fa40340692c71bcbd7396ca1f12a6adf77fa7eeee8be4e4b45acce4fbbf
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab4ee31908d908bc8411c98316fd68f161d0f80223a89bcb3bc3e6c94a3a7b9
+oid sha256:a9477a2cce5b8921e8b2e2bf565b022b24e84a6201af674bc0b5c9ea3dc23d55
 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": 1.6070237159729004,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03475238922675934,
+  "best_metric": 1.5941076278686523,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.043440486533449174,
   "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": 5.148,
       "eval_steps_per_second": 2.584,
       "step": 20
+    },
+    {
+      "epoch": 0.036490008688097306,
+      "grad_norm": 0.5803474187850952,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.7383,
+      "step": 21
+    },
+    {
+      "epoch": 0.038227628149435276,
+      "grad_norm": 0.7997701168060303,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.7855,
+      "step": 22
+    },
+    {
+      "epoch": 0.03996524761077324,
+      "grad_norm": 0.5163703560829163,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.5399,
+      "step": 23
+    },
+    {
+      "epoch": 0.04170286707211121,
+      "grad_norm": 0.6158132553100586,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.6514,
+      "step": 24
+    },
+    {
+      "epoch": 0.043440486533449174,
+      "grad_norm": 0.7691506147384644,
+      "learning_rate": 0.0,
+      "loss": 1.638,
+      "step": 25
+    },
+    {
+      "epoch": 0.043440486533449174,
+      "eval_loss": 1.5941076278686523,
+      "eval_runtime": 47.3248,
+      "eval_samples_per_second": 5.135,
+      "eval_steps_per_second": 2.578,
+      "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": 3913579442995200.0,
+  "total_flos": 4861077623930880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null