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:fb9961060d2d3abf37d928e144233a98e2c264f61b8406d521a16374f1f36eb6
+oid sha256:1eb8c47755f16be226eed222918566e06f2d55805b8145753459cc8396b59530
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8095c578c18c53810fe54e857290e2e9b4cc00f0868127a3b3ee1e909217963
+oid sha256:269972c29e1d16bb1714f061845663095adb1d0c42118b5da03a248b247d433d
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403cde01eafe280ab9250ddae0119a2c73ca722b9b49e204b79f2bffed8014a4
+oid sha256:8b6710a15fc5389884ea49c90dde5314b053d0f516c718124c7669dbb0da4838
 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": 1.0705658197402954,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005866392901664589,
+  "best_metric": 1.0664842128753662,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.007332991127080736,
   "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": 6.817,
       "eval_steps_per_second": 3.408,
       "step": 20
+    },
+    {
+      "epoch": 0.006159712546747818,
+      "grad_norm": 0.3223705589771271,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2469,
+      "step": 21
+    },
+    {
+      "epoch": 0.006453032191831048,
+      "grad_norm": 0.3321499228477478,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2214,
+      "step": 22
+    },
+    {
+      "epoch": 0.006746351836914278,
+      "grad_norm": 0.2950405478477478,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.0988,
+      "step": 23
+    },
+    {
+      "epoch": 0.007039671481997507,
+      "grad_norm": 0.25605347752571106,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0561,
+      "step": 24
+    },
+    {
+      "epoch": 0.007332991127080736,
+      "grad_norm": 0.2790612578392029,
+      "learning_rate": 0.0,
+      "loss": 0.86,
+      "step": 25
+    },
+    {
+      "epoch": 0.007332991127080736,
+      "eval_loss": 1.0664842128753662,
+      "eval_runtime": 214.1269,
+      "eval_samples_per_second": 6.706,
+      "eval_steps_per_second": 3.353,
+      "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": 3528837993332736.0,
+  "total_flos": 4400156016377856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null