Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147dd2bbd8c59ad87a0f9123532552fadc123092a3241f0bd04299d9b6aedfe2
+oid sha256:cac02adf9d81add4023ec57631e03b536f61446bf5a4f96a7bdfcb8eca443eb1
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a308d99297028c5f12e7bd85d05828f4a1c6d70ac7098006c85457985cad283
+oid sha256:98730cbcef82a0e9a0e45416aea663b29a9865b64e9378872f6582b06960142c
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e6c6250014f0ebe3f1afa18b2b41fae8f20d2a7f8de74786c53ffc176ba771
+oid sha256:8cdf91920bf12b0942f94382d08daf63cd5a03f45a86e9d36717402c9552705f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8287a4e3b9ef10f63afa9fbb14ef771e3148548ab75efa98b4ac9026c4b7f4
+oid sha256:e231c2c515a5ff10f1e544b2aa46a8eaae94bd71a11db0123cabe0d1726bb1ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9912269115448,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0029735355337496285,
+  "best_metric": 2.934997797012329,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.005947071067499257,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 47.787,
       "eval_steps_per_second": 11.947,
       "step": 50
+    },
+    {
+      "epoch": 0.003568242640499554,
+      "grad_norm": 0.7799744009971619,
+      "learning_rate": 0.00020674787920189178,
+      "loss": 3.003,
+      "step": 60
+    },
+    {
+      "epoch": 0.004162949747249479,
+      "grad_norm": 0.8374800682067871,
+      "learning_rate": 0.00020599274511475253,
+      "loss": 3.0247,
+      "step": 70
+    },
+    {
+      "epoch": 0.004757656853999405,
+      "grad_norm": 0.9920192956924438,
+      "learning_rate": 0.00020473827667594888,
+      "loss": 2.9491,
+      "step": 80
+    },
+    {
+      "epoch": 0.0053523639607493305,
+      "grad_norm": 1.210517168045044,
+      "learning_rate": 0.00020299058552961598,
+      "loss": 2.9129,
+      "step": 90
+    },
+    {
+      "epoch": 0.005947071067499257,
+      "grad_norm": 2.20344614982605,
+      "learning_rate": 0.00020075818625134152,
+      "loss": 2.9891,
+      "step": 100
+    },
+    {
+      "epoch": 0.005947071067499257,
+      "eval_loss": 2.934997797012329,
+      "eval_runtime": 149.0913,
+      "eval_samples_per_second": 47.488,
+      "eval_steps_per_second": 11.872,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 513679939338240.0,
+  "total_flos": 1031865843056640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null