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:e378342ca689348e32f597d74c966e8ffe89b6bb4c8e6e7b01c816bf03a2b870
+oid sha256:90fcafddbbd383f05f6f0d4286d09c60f4fcf01ee05c6980318b5d85bc0f0aaa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bc3ae7152b525d2c089da8497e8740c0ff42cedba320626e06ce25a3cf3907
+oid sha256:f16d53d9b9660bb9631bb49428c79160b8336a5a94b343664a89dac024f90861
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79ce16733b6db80aea90add053d7250afe407dd6159d54ee4a13e9dc59595aa
+oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
 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": 0.35940802097320557,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0014834044131281292,
+  "best_metric": 0.2911243438720703,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0029668088262562583,
   "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": 3.386,
       "eval_steps_per_second": 1.694,
       "step": 10
+    },
+    {
+      "epoch": 0.001631744854440942,
+      "grad_norm": 0.9124795198440552,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.111,
+      "step": 11
+    },
+    {
+      "epoch": 0.0017800852957537549,
+      "grad_norm": 1.250625729560852,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.1819,
+      "step": 12
+    },
+    {
+      "epoch": 0.0019284257370665678,
+      "grad_norm": 1.2839001417160034,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.3323,
+      "step": 13
+    },
+    {
+      "epoch": 0.0020767661783793806,
+      "grad_norm": 0.8916730880737305,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.2431,
+      "step": 14
+    },
+    {
+      "epoch": 0.0022251066196921935,
+      "grad_norm": 1.020967721939087,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2165,
+      "step": 15
+    },
+    {
+      "epoch": 0.0022251066196921935,
+      "eval_loss": 0.2991584539413452,
+      "eval_runtime": 817.2334,
+      "eval_samples_per_second": 3.474,
+      "eval_steps_per_second": 1.738,
+      "step": 15
+    },
+    {
+      "epoch": 0.0023734470610050065,
+      "grad_norm": 1.7947708368301392,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7359,
+      "step": 16
+    },
+    {
+      "epoch": 0.0025217875023178194,
+      "grad_norm": 1.6612706184387207,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.3233,
+      "step": 17
+    },
+    {
+      "epoch": 0.0026701279436306324,
+      "grad_norm": 0.9745355248451233,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0537,
+      "step": 18
+    },
+    {
+      "epoch": 0.0028184683849434454,
+      "grad_norm": 0.889968752861023,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2411,
+      "step": 19
+    },
+    {
+      "epoch": 0.0029668088262562583,
+      "grad_norm": 1.3263107538223267,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.1264,
+      "step": 20
+    },
+    {
+      "epoch": 0.0029668088262562583,
+      "eval_loss": 0.2911243438720703,
+      "eval_runtime": 819.6032,
+      "eval_samples_per_second": 3.464,
+      "eval_steps_per_second": 1.733,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null