Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ab4b5d668a646f26d96f6dbb21c13dfeec990cb143f4c6e69304b25b56b93a
+oid sha256:956683e9f9d995e13129be72e08522d432a578452f5c277aefb81b9662017613
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7081c32460c2b00a7f9aae5ea2f0fd32b9164d298343236f71c51b7735457c18
-size 509176980
+oid sha256:89cd898cb2f5773a1f14451c64b3ab98466c0673060423ef2742dd0d3e89a87f
+size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497a369390e6a383eac0de681b4a7d0ac9b6457e419072bfbbdb16ca18ffbad6
+oid sha256:b9869a7586932c827ff9999f77838db85a0c26d3be47f91a4f32bab202da0f96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180579b18c9e708a5cf9b411c96230bb3cb8d2c4c87c23004deaa70e5c990f72
+oid sha256:eb7fb5f22874147e56941b0c2b0e6e106f9317ff78b343462a5df511f2b8d1e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.13536955416202545,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.13601741022850924,
+  "best_metric": 0.12240716814994812,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.1632208922742111,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 5.808,
       "eval_steps_per_second": 1.456,
       "step": 250
+    },
+    {
+      "epoch": 0.14145810663764963,
+      "grad_norm": 0.5093297958374023,
+      "learning_rate": 0.00011652775287473745,
+      "loss": 0.1836,
+      "step": 260
+    },
+    {
+      "epoch": 0.14689880304678998,
+      "grad_norm": 0.5727118849754333,
+      "learning_rate": 0.00010918189690211387,
+      "loss": 0.2044,
+      "step": 270
+    },
+    {
+      "epoch": 0.15233949945593037,
+      "grad_norm": 0.4531668424606323,
+      "learning_rate": 0.00010181810309788618,
+      "loss": 0.2924,
+      "step": 280
+    },
+    {
+      "epoch": 0.15778019586507072,
+      "grad_norm": 0.9934888482093811,
+      "learning_rate": 9.447224712526258e-05,
+      "loss": 0.3537,
+      "step": 290
+    },
+    {
+      "epoch": 0.1632208922742111,
+      "grad_norm": 0.6647962927818298,
+      "learning_rate": 8.718011725613886e-05,
+      "loss": 0.4845,
+      "step": 300
+    },
+    {
+      "epoch": 0.1632208922742111,
+      "eval_loss": 0.12240716814994812,
+      "eval_runtime": 66.1711,
+      "eval_samples_per_second": 5.848,
+      "eval_steps_per_second": 1.466,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.826525156442112e+16,
+  "total_flos": 7.816693310029824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null