Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357fc8f4a2665fa3a804b16c520cef891451c92c479c9924f036727f868c3e9c
+oid sha256:37e6870880a5ad8d93831dad4bce06aa97558937878d00882402d01df9a2401f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f69f09160ed91ec32fcc7a075f3ea9fa4fef0c908c52542e3f8d2e7100bae0
+oid sha256:03401dc0aa15e6b55de1ab2a27609ff9cd74a3224d8b8a530bffa0cb81628ab8
 size 201478138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4338e60828af3efb3dbfac479ffbce4cf22f201f32dd76c072dd2215e2af458f
+oid sha256:1d313fe8b97eb646cf518fab58b5d077a385b0d98110cb7bab5cfdfdaa5f86e5
 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": 2.112894058227539,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008142162151159241,
+  "best_metric": 2.0656561851501465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0016284324302318482,
   "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": 5.812,
       "eval_steps_per_second": 2.906,
       "step": 10
+    },
+    {
+      "epoch": 0.0009770594581391089,
+      "grad_norm": 1.175682544708252,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 8.3941,
+      "step": 12
+    },
+    {
+      "epoch": 0.001221324322673886,
+      "grad_norm": 1.2302436828613281,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 8.6082,
+      "step": 15
+    },
+    {
+      "epoch": 0.001221324322673886,
+      "eval_loss": 2.081014394760132,
+      "eval_runtime": 891.2828,
+      "eval_samples_per_second": 5.803,
+      "eval_steps_per_second": 2.901,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014655891872086633,
+      "grad_norm": 1.4797160625457764,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 8.1861,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016284324302318482,
+      "eval_loss": 2.0656561851501465,
+      "eval_runtime": 890.9267,
+      "eval_samples_per_second": 5.805,
+      "eval_steps_per_second": 2.903,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2440771248586752.0,
+  "total_flos": 5065751648010240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null