Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f326f334eef37db7e81d1bdc92c8688331a0abc7cc3fb88f688626369d739878
+oid sha256:8d7e4a616242a8ccbeb438b98421f0be481edb7bd3dfaa3fa392b185e18f7c0c
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb7967971c95e1cb3bec161bb5c36617b4c72d2f099ade3d966881a7c490888
+oid sha256:5944558899ef544bfa4ed171cf2546f64d41350e01d53000113a170c27ff2146
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25eaed32035452f61b530f05ddb1757ce562ec2a5b996368ee4ed21c4aef9551
+oid sha256:bb60a6ffe8ef9e5fce9d63efc6be2357546fb0493004894178b1ab2ce90cf914
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d9d26262db0192551c63e8e2cb503f12fb8cb162ff6ce7f18ac6f7e9d328d6
+oid sha256:662c9e898ac39a71b423a2785b52925d7ca06517ad79ef8a45be543246b1a1b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.273123025894165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.006518267444513249,
+  "best_metric": 1.1874332427978516,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.009777401166769872,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 14.474,
       "eval_steps_per_second": 3.619,
       "step": 100
+    },
+    {
+      "epoch": 0.007170094188964573,
+      "grad_norm": 2.3844895362854004,
+      "learning_rate": 0.00019900872759483047,
+      "loss": 1.0244,
+      "step": 110
+    },
+    {
+      "epoch": 0.007821920933415898,
+      "grad_norm": 2.4352855682373047,
+      "learning_rate": 0.0001958265496573284,
+      "loss": 1.1891,
+      "step": 120
+    },
+    {
+      "epoch": 0.008473747677867223,
+      "grad_norm": 3.231959819793701,
+      "learning_rate": 0.00019219700200026827,
+      "loss": 1.2308,
+      "step": 130
+    },
+    {
+      "epoch": 0.009125574422318547,
+      "grad_norm": 2.5154852867126465,
+      "learning_rate": 0.0001881377674149945,
+      "loss": 1.2077,
+      "step": 140
+    },
+    {
+      "epoch": 0.009777401166769872,
+      "grad_norm": 3.0093817710876465,
+      "learning_rate": 0.00018366862208437368,
+      "loss": 1.3988,
+      "step": 150
+    },
+    {
+      "epoch": 0.009777401166769872,
+      "eval_loss": 1.1874332427978516,
+      "eval_runtime": 447.657,
+      "eval_samples_per_second": 14.431,
+      "eval_steps_per_second": 3.608,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0633874937675776e+16,
+  "total_flos": 3.128632256810189e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null