Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba57f8667709f0ebfa33e385d5933859462d67be0e7e7afad99938b995f67d9
+oid sha256:a836deec4b3bb03f50ac049c94a57064a2cedee6f57449429b8f633c913e05f9
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f93e8c14a5b8cbf2d9477bb227e46431cd30555f7cb2b753bd21f90b5b46928
+oid sha256:ef6b098145b7cc58c327557c70e52112ad6b4d4a920bc2d5fb7e65490f403b14
 size 70584314

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a996b0afeb762013a5d1bbc12322068270ba60f6975cd7e0cb0252d24278e9
+oid sha256:f108ec767e229a767e3d8a697ef9ce2b2a773115cacb416ea44871e02516790e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.483530044555664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007697192449054208,
+  "best_metric": 3.069991111755371,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0015394384898108416,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 31.048,
       "eval_steps_per_second": 15.527,
       "step": 10
+    },
+    {
+      "epoch": 0.0009236630938865049,
+      "grad_norm": 3.90388560295105,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.2477,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011545788673581311,
+      "grad_norm": 4.050303936004639,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.3388,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011545788673581311,
+      "eval_loss": 3.221691370010376,
+      "eval_runtime": 176.2999,
+      "eval_samples_per_second": 31.032,
+      "eval_steps_per_second": 15.519,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013854946408297574,
+      "grad_norm": 5.06642484664917,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.9946,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015394384898108416,
+      "eval_loss": 3.069991111755371,
+      "eval_runtime": 175.5541,
+      "eval_samples_per_second": 31.164,
+      "eval_steps_per_second": 15.585,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180238575206400.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null