Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c7e776d5794046cb408b50d731a03e3f9114b6274813c178f17b3fb411d5b6
+oid sha256:2016ba667e54d0f0e7d2c4cf299c1ca7515b88863882a80947957f8d260a3700
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c98f4d06dffde18e78a6df00d0128f648b53575ce68724e09f70a75d8fc0ba
+oid sha256:8f2b83c2f990438f3ee1cf4f36575203d1a09199b67a7a523e4ae8a2be26aa1c
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d3f36f7404688de11b22d84f32e4c30f7d364fb1e74fd97db5167b06e22e57
+oid sha256:cde923dd25d49a18608ad2195296261a163ab1cd44e1c0838d6b8c98ee7e817b
 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": 1.3078378438949585,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.018412815319462345,
+  "best_metric": 1.1180486679077148,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.03682563063892469,
   "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": 10.899,
       "eval_steps_per_second": 2.725,
       "step": 50
+    },
+    {
+      "epoch": 0.022095378383354815,
+      "grad_norm": 1.3702597618103027,
+      "learning_rate": 0.00020275275110137215,
+      "loss": 2.5237,
+      "step": 60
+    },
+    {
+      "epoch": 0.025777941447247283,
+      "grad_norm": 1.518210768699646,
+      "learning_rate": 0.00020201220897726938,
+      "loss": 2.4878,
+      "step": 70
+    },
+    {
+      "epoch": 0.029460504511139754,
+      "grad_norm": 1.3466520309448242,
+      "learning_rate": 0.00020078198147448128,
+      "loss": 2.3046,
+      "step": 80
+    },
+    {
+      "epoch": 0.03314306757503222,
+      "grad_norm": 1.2383614778518677,
+      "learning_rate": 0.00019906806213773937,
+      "loss": 2.3387,
+      "step": 90
+    },
+    {
+      "epoch": 0.03682563063892469,
+      "grad_norm": 1.4980638027191162,
+      "learning_rate": 0.0001968788010097697,
+      "loss": 2.0506,
+      "step": 100
+    },
+    {
+      "epoch": 0.03682563063892469,
+      "eval_loss": 1.1180486679077148,
+      "eval_runtime": 105.0543,
+      "eval_samples_per_second": 10.89,
+      "eval_steps_per_second": 2.722,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5300701404004352e+16,
+  "total_flos": 3.026877886444339e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null