Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d7e4a616242a8ccbeb438b98421f0be481edb7bd3dfaa3fa392b185e18f7c0c
+oid sha256:caf43d7ee38d32144d66b6374633818a3e562433296261cb919d7209c1f61309
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5944558899ef544bfa4ed171cf2546f64d41350e01d53000113a170c27ff2146
+oid sha256:46be77b65053903f28108f3950dc55622ddee96cf5a8a2b26870546ae31b8e19
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb60a6ffe8ef9e5fce9d63efc6be2357546fb0493004894178b1ab2ce90cf914
+oid sha256:3344af689521146e9ec080efa24caef17a8d8781a3937d8f1997beee63ec21f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662c9e898ac39a71b423a2785b52925d7ca06517ad79ef8a45be543246b1a1b6
+oid sha256:ae20548bf37ed9ce24a89f932598e5e41d81b46882f80f29333348ce3845be91
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1874332427978516,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.009777401166769872,
+  "best_metric": 1.1086701154708862,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.013036534889026497,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 14.431,
       "eval_steps_per_second": 3.608,
       "step": 150
+    },
+    {
+      "epoch": 0.010429227911221197,
+      "grad_norm": 2.5995352268218994,
+      "learning_rate": 0.00017881133923521971,
+      "loss": 1.0265,
+      "step": 160
+    },
+    {
+      "epoch": 0.011081054655672521,
+      "grad_norm": 2.5440680980682373,
+      "learning_rate": 0.00017358958306132124,
+      "loss": 0.9651,
+      "step": 170
+    },
+    {
+      "epoch": 0.011732881400123848,
+      "grad_norm": 2.6204676628112793,
+      "learning_rate": 0.00016802879343386844,
+      "loss": 1.0322,
+      "step": 180
+    },
+    {
+      "epoch": 0.012384708144575172,
+      "grad_norm": 2.2899601459503174,
+      "learning_rate": 0.00016215606196095766,
+      "loss": 1.1977,
+      "step": 190
+    },
+    {
+      "epoch": 0.013036534889026497,
+      "grad_norm": 3.2127535343170166,
+      "learning_rate": 0.000156,
+      "loss": 1.6102,
+      "step": 200
+    },
+    {
+      "epoch": 0.013036534889026497,
+      "eval_loss": 1.1086701154708862,
+      "eval_runtime": 446.4333,
+      "eval_samples_per_second": 14.47,
+      "eval_steps_per_second": 3.618,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.128632256810189e+16,
+  "total_flos": 4.160326003693978e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null