Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac41a59133739c13b930cfedd3498ffe1284f1a8d4e5b4a51146b6399bda6a9
+oid sha256:028d308d2b2975c71a859c1db9eec7b73b4e60cf2d64c6ed4ab844b74612c0e0
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d54c05bdff0bdef810dd070938938ce12992b7fcef943cd2fd95653e84d61b
+oid sha256:7c9ffc7737d4f9bb687d2342d640e3f10d15c7b8587c8f6af1a14522dd3f4428
 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:ff293d6444222bd1d89236cd1763caa87bb59d6363a546a504877debc45066aa
+oid sha256:aa1bfb19ac7a71e5a662427e7488d4a4d957109537750c19fd28e94a30346c50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4160047173500061,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0437636761487965,
+  "best_metric": 0.35316547751426697,
+  "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": 10.007,
       "eval_steps_per_second": 2.517,
       "step": 50
+    },
+    {
+      "epoch": 0.0525164113785558,
+      "grad_norm": 0.5463985204696655,
+      "learning_rate": 0.00021074300730241147,
+      "loss": 0.6921,
+      "step": 60
+    },
+    {
+      "epoch": 0.061269146608315096,
+      "grad_norm": 0.8098825812339783,
+      "learning_rate": 0.00020997328125223568,
+      "loss": 0.5244,
+      "step": 70
+    },
+    {
+      "epoch": 0.0700218818380744,
+      "grad_norm": 0.38064104318618774,
+      "learning_rate": 0.0002086945718774165,
+      "loss": 0.2607,
+      "step": 80
+    },
+    {
+      "epoch": 0.0787746170678337,
+      "grad_norm": 0.050267886370420456,
+      "learning_rate": 0.00020691310892149265,
+      "loss": 0.0061,
+      "step": 90
+    },
+    {
+      "epoch": 0.087527352297593,
+      "grad_norm": 0.3279358148574829,
+      "learning_rate": 0.00020463757149291335,
+      "loss": 0.0024,
+      "step": 100
+    },
+    {
+      "epoch": 0.087527352297593,
+      "eval_loss": 0.35316547751426697,
+      "eval_runtime": 48.4486,
+      "eval_samples_per_second": 9.928,
+      "eval_steps_per_second": 2.497,
+      "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