Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ba72246875182be09075439d0f38558b9840f995f8117a6a158fe5a2346ad2
+oid sha256:24e1958a3fb7dfb9a10d3876b0df8f57bbe845dbb0122a98e54ee8fdd1661f84
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0c1dbf9d2f8c95489057312bdc267fe51dfc1260c4c9a201163a2de25e1c82
+oid sha256:639f0013b7a66674bbb77654280be294b0658ef1c38bdf4eb21a672bb5b6bf6d
 size 323193274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae30e70644334ba58e5c990bb22075127b24ef6e4c7a0b149c16de65cbd225fb
+oid sha256:bf4678f22263b499b2336dd8c5f6a0b45dbd7d6f97aa6e1ba4fd1b5dc1d9be75
 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": 1.9601075649261475,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0006386613657773307,
+  "best_metric": 1.086385726928711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0012773227315546615,
   "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": 8.242,
       "eval_steps_per_second": 4.122,
       "step": 10
+    },
+    {
+      "epoch": 0.0007663936389327968,
+      "grad_norm": 0.5967190265655518,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.0067,
+      "step": 12
+    },
+    {
+      "epoch": 0.0009579920486659961,
+      "grad_norm": 0.6117227077484131,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.5435,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009579920486659961,
+      "eval_loss": 1.4523731470108032,
+      "eval_runtime": 800.3189,
+      "eval_samples_per_second": 8.238,
+      "eval_steps_per_second": 4.12,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011495904583991954,
+      "grad_norm": 0.7093020677566528,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.3667,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012773227315546615,
+      "eval_loss": 1.086385726928711,
+      "eval_runtime": 800.5836,
+      "eval_samples_per_second": 8.235,
+      "eval_steps_per_second": 4.118,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 6990386933268480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null