Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8434a579ee2251a8a64eb6443e06cfb9cf6144a0d1ec2b089cd23bb5239e4347
+oid sha256:37837b678ff32a9d46081fef5c965b72178328008b67cdf3fcbf58782633ac71
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691373b2b057eef2b85f7a665f1097862234abdeab102977bf6b30411e9735f6
+oid sha256:c1f25225d7d4d67cdba238771305e91331c0d5d241af925125c2d71a05d3e215
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491684c200efe919e54e664829adbbaa262ab96583c8009b878e33a2f5673771
+oid sha256:d98e31570c65c1304aa3ca79af60e9837b5f8bda25e97642e96d222a6719c140
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f939f73d23e2dbcf206924457b3eb57b1e3cb5e54dc5c680d84d6737616b0365
+oid sha256:b0f69d9f90a0d5ce8ac61f1f875459a761943b0c4252d8391ecd4046776d8753
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.230445384979248,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.08099039685294458,
+  "best_metric": 1.2252267599105835,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.09256045354622237,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 23.672,
       "eval_steps_per_second": 5.918,
       "step": 350
+    },
+    {
+      "epoch": 0.08330440819160013,
+      "grad_norm": 0.20531992614269257,
+      "learning_rate": 4.496232384598384e-05,
+      "loss": 1.2353,
+      "step": 360
+    },
+    {
+      "epoch": 0.0856184195302557,
+      "grad_norm": 0.20734241604804993,
+      "learning_rate": 3.9202529516782854e-05,
+      "loss": 1.2522,
+      "step": 370
+    },
+    {
+      "epoch": 0.08793243086891125,
+      "grad_norm": 0.20165283977985382,
+      "learning_rate": 3.374867815139649e-05,
+      "loss": 1.2345,
+      "step": 380
+    },
+    {
+      "epoch": 0.09024644220756682,
+      "grad_norm": 0.20317639410495758,
+      "learning_rate": 2.8627340365457602e-05,
+      "loss": 1.2272,
+      "step": 390
+    },
+    {
+      "epoch": 0.09256045354622237,
+      "grad_norm": 0.39954468607902527,
+      "learning_rate": 2.3863466801864254e-05,
+      "loss": 1.2192,
+      "step": 400
+    },
+    {
+      "epoch": 0.09256045354622237,
+      "eval_loss": 1.2252267599105835,
+      "eval_runtime": 76.3538,
+      "eval_samples_per_second": 23.836,
+      "eval_steps_per_second": 5.959,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7899344384425984e+16,
+  "total_flos": 3.1870192510304256e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null