Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66e0861fd4a47d074942aeadbfff8f977dec4375fa4662e6c4c7bf663e96b91d
+oid sha256:8e0fcf4bbf1f9f1970a46c89e2a233572a7ba3e29e3a7a3b624008c93730d734
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd35dd6341008108c693da7f7bd1b657521257e87040ee11da0822baf363ade3
+oid sha256:a43367a4318965846711a981dde352d79975ad377cf0920ddb76f167a4a286f1
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b9df4e28e8228c4a4618982fd2766146ea7a9c254a647008c60dcfaeda7100
+oid sha256:c2cf22bc849b00644528515dfcd0ca607f9eb83dcba27f583e44fe76c71bd4dd
 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": 2.044189214706421,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0009141394519733985,
+  "best_metric": 1.9001489877700806,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001828278903946797,
   "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": 3.147,
       "eval_steps_per_second": 1.574,
       "step": 10
+    },
+    {
+      "epoch": 0.0010969673423680782,
+      "grad_norm": 0.6598482728004456,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.0666,
+      "step": 12
+    },
+    {
+      "epoch": 0.0013712091779600978,
+      "grad_norm": 0.5164814591407776,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.982,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013712091779600978,
+      "eval_loss": 1.9511953592300415,
+      "eval_runtime": 1464.7107,
+      "eval_samples_per_second": 3.145,
+      "eval_steps_per_second": 1.573,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016454510135521174,
+      "grad_norm": 0.4864216148853302,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9117,
+      "step": 18
+    },
+    {
+      "epoch": 0.001828278903946797,
+      "eval_loss": 1.9001489877700806,
+      "eval_runtime": 1463.8603,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 1.574,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3169216057835520.0,
+  "total_flos": 6132638865162240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null