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:c07829443a6b16d29943fbfa5c6596d2d04ca9631dc4c5ef2575ea447a2888c1
+oid sha256:ea3a360f5343e976710653feed24558cd831ac8f25b847c85db2be40216fbbae
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0995442cd537a64c88eb90eb0032bdfc2c75b6e4d17b994883c0773a983e740c
+oid sha256:c4014c57ae0f27f8a68740a911e0d9536d3fb65c1b027c33fbca28bbadd6f33a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7589aa544886f8d90468d8c7e34ecc977596f813770455064d4b524afd866693
+oid sha256:20efeed8359c730e586f1b7f06278afa1441ab77b8079094afd4d1c8544d9bf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d69ac2beb8e330f34449ba996c50f5a61dd8a9dd66a6eb15738df4da44cca1
+oid sha256:fd4836ddf60b44e58a6b1c94aa6a6c90a55c6b9d3781b50bd68866141db98eb6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7819404602050781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.002620339071875901,
+  "best_metric": 1.7514146566390991,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.005240678143751802,
   "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": 16.423,
       "eval_steps_per_second": 4.106,
       "step": 50
+    },
+    {
+      "epoch": 0.003144406886251081,
+      "grad_norm": 1.8030827045440674,
+      "learning_rate": 0.00020375153312650207,
+      "loss": 1.3647,
+      "step": 60
+    },
+    {
+      "epoch": 0.003668474700626261,
+      "grad_norm": 1.8373987674713135,
+      "learning_rate": 0.00020300734301164017,
+      "loss": 1.1339,
+      "step": 70
+    },
+    {
+      "epoch": 0.004192542515001441,
+      "grad_norm": 1.8776074647903442,
+      "learning_rate": 0.00020177105527484818,
+      "loss": 1.1834,
+      "step": 80
+    },
+    {
+      "epoch": 0.004716610329376621,
+      "grad_norm": 2.3595855236053467,
+      "learning_rate": 0.00020004869298570854,
+      "loss": 1.2042,
+      "step": 90
+    },
+    {
+      "epoch": 0.005240678143751802,
+      "grad_norm": 11.033510208129883,
+      "learning_rate": 0.00019784864732016265,
+      "loss": 1.8743,
+      "step": 100
+    },
+    {
+      "epoch": 0.005240678143751802,
+      "eval_loss": 1.7514146566390991,
+      "eval_runtime": 489.1456,
+      "eval_samples_per_second": 16.427,
+      "eval_steps_per_second": 4.107,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9428209867161600.0,
+  "total_flos": 1.88564197343232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null