Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fb90da4041021f8878bc4e3cdd3a22940be82924a4bf2eb3f08634f92acc03
+oid sha256:c31252227a6af7a6e65f9d45c7494011d167c4f702a14da71d94d44964bd947f
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488fe6ef402eacc1e174574857e563d54be7f8bcf5f01774333d67a9ecbcd448
+oid sha256:e7b25f7b58da1e29481438dbf5ec2bbbeda853a96efc7ef790748a1310fd658d
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11e9eeb882b9ad49f37b80490e86306dcedb0650b3f6dc874e57dfd31d605ec
+oid sha256:51b32667b227f6275884c5848fe8070c6219d70bf14c4e440c0b1b379a04dba2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f43eae3d8b1b29d23e364f4f65c01c337c44f0992ce19d5a6cf14f65803d2b
+oid sha256:0873218b672c06f65bcbdbef35d38ce732851774107c53582718a1316dbb1e40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5164891481399536,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.04434589800443459,
+  "best_metric": 0.38211727142333984,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.08869179600886919,
   "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": 12.386,
       "eval_steps_per_second": 3.103,
       "step": 50
+    },
+    {
+      "epoch": 0.05321507760532151,
+      "grad_norm": 1.0847694873809814,
+      "learning_rate": 0.00020075518705111234,
+      "loss": 0.412,
+      "step": 60
+    },
+    {
+      "epoch": 0.06208425720620843,
+      "grad_norm": 2.6469056606292725,
+      "learning_rate": 0.00020002194090852784,
+      "loss": 0.4117,
+      "step": 70
+    },
+    {
+      "epoch": 0.07095343680709534,
+      "grad_norm": 1.295844554901123,
+      "learning_rate": 0.00019880383387374748,
+      "loss": 0.4179,
+      "step": 80
+    },
+    {
+      "epoch": 0.07982261640798226,
+      "grad_norm": 1.5523910522460938,
+      "learning_rate": 0.00019710680044180106,
+      "loss": 0.3102,
+      "step": 90
+    },
+    {
+      "epoch": 0.08869179600886919,
+      "grad_norm": 1.0117522478103638,
+      "learning_rate": 0.0001949391083889838,
+      "loss": 0.2715,
+      "step": 100
+    },
+    {
+      "epoch": 0.08869179600886919,
+      "eval_loss": 0.38211727142333984,
+      "eval_runtime": 38.181,
+      "eval_samples_per_second": 12.441,
+      "eval_steps_per_second": 3.117,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2665508599955456e+16,
+  "total_flos": 2.5247139659513856e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null