Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ded494ff3840717e7e954d74a199a45ecf38e1d1b49f9727f21b7ea73e0d20c
+oid sha256:8ee8892c6a34abda640f64e7a91d76b8219cd398964477e7664afac7043b8f5b
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aee7cc282a3475fb8cc91b61380aa143f379a1f0c68f5f198a9302a4ed207aa
+oid sha256:bc8a9b3a677f874dc58edc1dafd22e53a8b16cfad305b6ad901169b15c8dd672
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a6ad6815471e732f3d8d09c5bc2c7745abd52b8ecf0816fa0d3ea9b7f21098
+oid sha256:19b74bd0b803be2e0f9123d9d572dd589735848f96ccad92527953777bbe2721
 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": 11.092714309692383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005617780274569011,
+  "best_metric": 11.09123420715332,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0007022225343211264,
   "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": 144.182,
       "eval_steps_per_second": 72.091,
       "step": 20
+    },
+    {
+      "epoch": 0.0005898669288297462,
+      "grad_norm": 0.8569645285606384,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 44.351,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006179558302025912,
+      "grad_norm": 0.7747932076454163,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.3767,
+      "step": 22
+    },
+    {
+      "epoch": 0.0006460447315754362,
+      "grad_norm": 0.8021819591522217,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 44.3654,
+      "step": 23
+    },
+    {
+      "epoch": 0.0006741336329482813,
+      "grad_norm": 0.8448837995529175,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 44.3871,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007022225343211264,
+      "grad_norm": 0.8849800825119019,
+      "learning_rate": 0.0,
+      "loss": 44.3408,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007022225343211264,
+      "eval_loss": 11.09123420715332,
+      "eval_runtime": 103.5033,
+      "eval_samples_per_second": 144.826,
+      "eval_steps_per_second": 72.413,
+      "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": 327923269632.0,
+  "total_flos": 412315287552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null