Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc65fb019fa665dae1808c37f0727df27e6a6e4af0be39c6433e3290ab114b5a
+oid sha256:dc8ab57e4cbb1c9cf96c326d5f84eb9093228d3c32a3c69855c48eb35341ee29
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e38514469fdca3666e0538028996e06ebc11d3eeb5d10fe5afdfc2bb7be172d
+oid sha256:d1fd0bb88e3dcbfe2b72559fd991af5d938ab5c0fa83d9f04ccdc12cfd590668
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8533ac5c809e23e45fa3502773ae0eeaf07bc3c38c0faa86616fda6bd7fa0465
+oid sha256:5e1905041c7e88cb467c61d7ad300e7b06f131aed532d9287ae4df2b9bb76d72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.878531455993652,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0004286694101508916,
+  "best_metric": 4.590373992919922,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0008573388203017832,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 13.188,
       "eval_steps_per_second": 6.594,
       "step": 10
+    },
+    {
+      "epoch": 0.00051440329218107,
+      "grad_norm": 98.51611328125,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.8034,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006430041152263374,
+      "grad_norm": 77.14884185791016,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.3444,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006430041152263374,
+      "eval_loss": 4.691795825958252,
+      "eval_runtime": 190.2025,
+      "eval_samples_per_second": 12.913,
+      "eval_steps_per_second": 6.456,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007716049382716049,
+      "grad_norm": 75.92028045654297,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.3554,
+      "step": 18
+    },
+    {
+      "epoch": 0.0008573388203017832,
+      "eval_loss": 4.590373992919922,
+      "eval_runtime": 190.5313,
+      "eval_samples_per_second": 12.89,
+      "eval_steps_per_second": 6.445,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 44250829946880.0,
+  "total_flos": 88501659893760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null