Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f4f7c7cf24074abcfc82cbf748b002ff0a3b121e169d63402fe8620f5fb52b
+oid sha256:62ad28e04697f14853133a90e86617947450e04231df6fcdeba767536df7368a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad45889b40cd883c2d7ef11bb6bd5736bd1e57d92bb0cbc05497c074b78abb27
+oid sha256:7bdc509809155cdf7c480d70335ff7ea69867b3988a3612d75787ad8c7eb3062
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 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": 0.9832201600074768,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0053433075073470475,
+  "best_metric": 0.8237693309783936,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.010686615014694095,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.586,
       "eval_steps_per_second": 2.293,
       "step": 10
+    },
+    {
+      "epoch": 0.005877638258081752,
+      "grad_norm": 3.8575327396392822,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.5685,
+      "step": 11
+    },
+    {
+      "epoch": 0.006411969008816457,
+      "grad_norm": 3.1404190063476562,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.4437,
+      "step": 12
+    },
+    {
+      "epoch": 0.006946299759551162,
+      "grad_norm": 3.9936773777008057,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.7143,
+      "step": 13
+    },
+    {
+      "epoch": 0.007480630510285867,
+      "grad_norm": 4.532442092895508,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.8547,
+      "step": 14
+    },
+    {
+      "epoch": 0.008014961261020572,
+      "grad_norm": 4.569597244262695,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.3982,
+      "step": 15
+    },
+    {
+      "epoch": 0.008014961261020572,
+      "eval_loss": 0.8725337982177734,
+      "eval_runtime": 171.3387,
+      "eval_samples_per_second": 4.599,
+      "eval_steps_per_second": 2.3,
+      "step": 15
+    },
+    {
+      "epoch": 0.008549292011755277,
+      "grad_norm": 4.278989791870117,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8996,
+      "step": 16
+    },
+    {
+      "epoch": 0.009083622762489982,
+      "grad_norm": 4.710971355438232,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.6165,
+      "step": 17
+    },
+    {
+      "epoch": 0.009617953513224685,
+      "grad_norm": 5.305459976196289,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.6981,
+      "step": 18
+    },
+    {
+      "epoch": 0.01015228426395939,
+      "grad_norm": 4.7451934814453125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.6357,
+      "step": 19
+    },
+    {
+      "epoch": 0.010686615014694095,
+      "grad_norm": 4.512779712677002,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.6611,
+      "step": 20
+    },
+    {
+      "epoch": 0.010686615014694095,
+      "eval_loss": 0.8237693309783936,
+      "eval_runtime": 171.3489,
+      "eval_samples_per_second": 4.599,
+      "eval_steps_per_second": 2.299,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257466271825920.0,
+  "total_flos": 6514932543651840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null