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:fb700ee4d8d4125fca46924e5c147f2746696ccdc641cc3d6cf9fd0badaa7b13
+oid sha256:69e9f43d2d4d787f3b75b39b77aca7786fceb0cd72be84524f8ccb6d33bcb9a2
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0cf6fc5857c51707ecd283fcb349423c8df43803f0bb8f8db5b22295b1b580a
+oid sha256:503d0b04bf380ce32ce0dfc6d1426c8a23ea6587e15a2d1c221ae1ae28f8f861
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67be52aaad59dc496b70a124a3cce20198b4ca4f0a0d477a71ee547b5bed2ea
+oid sha256:fe5c44cb237becb14767ff89ac17ebe09ec9364950e67092ac1150bc8db0f263
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafcafa93344e734000a1bd1b561500d69d1ccecac0e67c8cade94cdf739e25e
+oid sha256:cd10496d8a5f7e45002ec724483dbe1d4186b3c7101bd21f93cd0629ecfe77be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.746705055236816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05830903790087463,
+  "best_metric": 11.742330551147461,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.11661807580174927,
   "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": 221.02,
       "eval_steps_per_second": 55.714,
       "step": 50
+    },
+    {
+      "epoch": 0.06997084548104957,
+      "grad_norm": 0.2140980362892151,
+      "learning_rate": 0.00020275275110137215,
+      "loss": 11.7573,
+      "step": 60
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 0.1588020920753479,
+      "learning_rate": 0.00020201220897726938,
+      "loss": 11.7488,
+      "step": 70
+    },
+    {
+      "epoch": 0.09329446064139942,
+      "grad_norm": 0.20971915125846863,
+      "learning_rate": 0.00020078198147448128,
+      "loss": 11.7447,
+      "step": 80
+    },
+    {
+      "epoch": 0.10495626822157435,
+      "grad_norm": 0.19178971648216248,
+      "learning_rate": 0.00019906806213773937,
+      "loss": 11.7421,
+      "step": 90
+    },
+    {
+      "epoch": 0.11661807580174927,
+      "grad_norm": 0.22939780354499817,
+      "learning_rate": 0.0001968788010097697,
+      "loss": 11.7342,
+      "step": 100
+    },
+    {
+      "epoch": 0.11661807580174927,
+      "eval_loss": 11.742330551147461,
+      "eval_runtime": 1.6574,
+      "eval_samples_per_second": 217.817,
+      "eval_steps_per_second": 54.907,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2589661593600.0,
+  "total_flos": 5179323187200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null