Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8cdd5bed4e2bcd79b54f48a61b57142be79c52e566d0b3afe6d9cb184b9768
+oid sha256:7681dcf33e4a3764bebeefb8fa0fba2ee8f3acb9875109778363b66d75c678b9
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfe3cfc5ba10c690d3925af9fddca3d1b30a5d1d9823321696dc76055687e7b
+oid sha256:3045366b307950658dab0e4e641ce0706a627102e01d92b61cf4149e6b1d053d
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4764512888b2a50c54ee9e6dff725e56e122d9d7fe17ce385c4a79f0bd32d51b
+oid sha256:309ae5284f0eab6e59937f47a0594dd123863a474cdfe6d07a7dbf6403c77da0
 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": 4.053124904632568,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.009029345372460496,
+  "best_metric": 3.565016269683838,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.01805869074492099,
   "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": 6.423,
       "eval_steps_per_second": 3.218,
       "step": 10
+    },
+    {
+      "epoch": 0.009932279909706547,
+      "grad_norm": 0.835163414478302,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.4282,
+      "step": 11
+    },
+    {
+      "epoch": 0.010835214446952596,
+      "grad_norm": 1.1635563373565674,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.6538,
+      "step": 12
+    },
+    {
+      "epoch": 0.011738148984198645,
+      "grad_norm": 1.4114489555358887,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.7767,
+      "step": 13
+    },
+    {
+      "epoch": 0.012641083521444696,
+      "grad_norm": 1.5940505266189575,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.1882,
+      "step": 14
+    },
+    {
+      "epoch": 0.013544018058690745,
+      "grad_norm": 1.4813003540039062,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.06,
+      "step": 15
+    },
+    {
+      "epoch": 0.013544018058690745,
+      "eval_loss": 3.730433940887451,
+      "eval_runtime": 72.6114,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.223,
+      "step": 15
+    },
+    {
+      "epoch": 0.014446952595936794,
+      "grad_norm": 1.7925143241882324,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.1655,
+      "step": 16
+    },
+    {
+      "epoch": 0.015349887133182845,
+      "grad_norm": 1.607529878616333,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.8114,
+      "step": 17
+    },
+    {
+      "epoch": 0.016252821670428894,
+      "grad_norm": 1.4072641134262085,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.7555,
+      "step": 18
+    },
+    {
+      "epoch": 0.017155756207674944,
+      "grad_norm": 1.3798819780349731,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.8308,
+      "step": 19
+    },
+    {
+      "epoch": 0.01805869074492099,
+      "grad_norm": 1.4967929124832153,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.369,
+      "step": 20
+    },
+    {
+      "epoch": 0.01805869074492099,
+      "eval_loss": 3.565016269683838,
+      "eval_runtime": 72.8542,
+      "eval_samples_per_second": 6.41,
+      "eval_steps_per_second": 3.212,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1873333749547008.0,
+  "total_flos": 3659535696789504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null