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:e4d01b9d9e8751b1a145f119a7b4d8f4c20bf1634cefc1d7093f74bbef2beebc
+oid sha256:a792ab734fdb12fcd9be0bb1e867fe91183c7f9ecf21c1163b4b797a274441b8
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4866b3c82b5b3672e1d5a81e782416eaa1964bceeeecc9e5a6cb0eeedbbe2c77
+oid sha256:7356b4fe4d49ca57dbf8d429321cdac26633c7d44a51745b879f8b6570da2d09
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abba591c018c35144b1b28feca1d3f55916a65a9a80c613c6d8e6481c2a156f3
+oid sha256:f5260c8125a24537a0b9406dcd050daa45aa08666d31e6a0297dc30b84741333
 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": 0.41450178623199463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0437636761487965,
+  "best_metric": 0.3669174313545227,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.087527352297593,
   "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": 10.002,
       "eval_steps_per_second": 2.516,
       "step": 50
+    },
+    {
+      "epoch": 0.0525164113785558,
+      "grad_norm": 0.523928165435791,
+      "learning_rate": 0.00020275275110137215,
+      "loss": 0.6924,
+      "step": 60
+    },
+    {
+      "epoch": 0.061269146608315096,
+      "grad_norm": 0.6150461435317993,
+      "learning_rate": 0.00020201220897726938,
+      "loss": 0.5178,
+      "step": 70
+    },
+    {
+      "epoch": 0.0700218818380744,
+      "grad_norm": 0.3789159655570984,
+      "learning_rate": 0.00020078198147448128,
+      "loss": 0.2702,
+      "step": 80
+    },
+    {
+      "epoch": 0.0787746170678337,
+      "grad_norm": 1.880570411682129,
+      "learning_rate": 0.00019906806213773937,
+      "loss": 0.0048,
+      "step": 90
+    },
+    {
+      "epoch": 0.087527352297593,
+      "grad_norm": 0.6373544335365295,
+      "learning_rate": 0.0001968788010097697,
+      "loss": 0.0049,
+      "step": 100
+    },
+    {
+      "epoch": 0.087527352297593,
+      "eval_loss": 0.3669174313545227,
+      "eval_runtime": 48.1037,
+      "eval_samples_per_second": 9.999,
+      "eval_steps_per_second": 2.515,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.617398379577344e+16,
+  "total_flos": 3.252570367721472e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null