Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df175e88104020076c33ae821e500674971f41725c8be3ca655eb85639beb82
+oid sha256:be2cdc9b7ce8dcb284902a96981e16dc701c0ffec1ea253c7f1bb5694506721a
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb73644e7c0ffca1ae16b5b2c68de8e37fc17ff530a20f9c14b4f8705a7c2d8d
+oid sha256:100ad461e8d4ad4462240765229d93ff37a6483ba48209835b06e6c036e7a5ff
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba1e94f53ea11b3c061d5464baa3a78fb58bc8a06770a21f1f1d2978c8aa8a1
+oid sha256:86556344de920fe43d329034bb740375cf66aadfaa5e1fd459c34bcf3d2b4c77
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70f2c234472a0c9d4bb243d4395ef7f272e90b616f0f91bd6f8be11d27dd70c
+oid sha256:3be56923d6a9d5cea3456e8f309490172a5ad932fdf15a749e294eb6a809ef7f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02686d7c9c441da9f3d6621000ee6fb90320ecfa596fb2884762ec27074c0ba
+oid sha256:1479f80d61560df7dac391de081439d95b89699f831bcc28065d8345f554ac31
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbbcaf8d7aa7bbb8e3660bcb34138b3acda17b80ed43a1655ce3cb440b0ba3c
+oid sha256:68aa51309bb9546620e0e7ccd79f0563fc0a682244573ba0d1f3c63a101cc612
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.930198669433594,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06284861340246681,
+  "best_metric": 11.927906036376953,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12569722680493361,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 198.062,
       "eval_steps_per_second": 51.496,
       "step": 25
+    },
+    {
+      "epoch": 0.06536255793856548,
+      "grad_norm": 0.02685977704823017,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 11.9309,
+      "step": 26
+    },
+    {
+      "epoch": 0.06787650247466415,
+      "grad_norm": 0.03275511413812637,
+      "learning_rate": 7.75e-05,
+      "loss": 11.9311,
+      "step": 27
+    },
+    {
+      "epoch": 0.07039044701076283,
+      "grad_norm": 0.02926531247794628,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 11.9315,
+      "step": 28
+    },
+    {
+      "epoch": 0.0729043915468615,
+      "grad_norm": 0.028518393635749817,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 11.9315,
+      "step": 29
+    },
+    {
+      "epoch": 0.07541833608296017,
+      "grad_norm": 0.03880656510591507,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 11.9307,
+      "step": 30
+    },
+    {
+      "epoch": 0.07793228061905884,
+      "grad_norm": 0.03654514625668526,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 11.9317,
+      "step": 31
+    },
+    {
+      "epoch": 0.08044622515515751,
+      "grad_norm": 0.044491469860076904,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 11.9293,
+      "step": 32
+    },
+    {
+      "epoch": 0.08296016969125619,
+      "grad_norm": 0.048509083688259125,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 11.9298,
+      "step": 33
+    },
+    {
+      "epoch": 0.08547411422735486,
+      "grad_norm": 0.048801239579916,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 11.9294,
+      "step": 34
+    },
+    {
+      "epoch": 0.08798805876345353,
+      "grad_norm": 0.056390538811683655,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 11.9279,
+      "step": 35
+    },
+    {
+      "epoch": 0.0905020032995522,
+      "grad_norm": 0.08711764216423035,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 11.9253,
+      "step": 36
+    },
+    {
+      "epoch": 0.09301594783565087,
+      "grad_norm": 0.10037648677825928,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 11.9241,
+      "step": 37
+    },
+    {
+      "epoch": 0.09552989237174955,
+      "grad_norm": 0.049203407019376755,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 11.9305,
+      "step": 38
+    },
+    {
+      "epoch": 0.09804383690784822,
+      "grad_norm": 0.04130005091428757,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9299,
+      "step": 39
+    },
+    {
+      "epoch": 0.10055778144394689,
+      "grad_norm": 0.03922172635793686,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 11.9311,
+      "step": 40
+    },
+    {
+      "epoch": 0.10307172598004556,
+      "grad_norm": 0.05184343457221985,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 11.9305,
+      "step": 41
+    },
+    {
+      "epoch": 0.10558567051614423,
+      "grad_norm": 0.051686421036720276,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9302,
+      "step": 42
+    },
+    {
+      "epoch": 0.10809961505224291,
+      "grad_norm": 0.05162731558084488,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 11.9288,
+      "step": 43
+    },
+    {
+      "epoch": 0.11061355958834158,
+      "grad_norm": 0.05084317922592163,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 11.9282,
+      "step": 44
+    },
+    {
+      "epoch": 0.11312750412444025,
+      "grad_norm": 0.058874111622571945,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9284,
+      "step": 45
+    },
+    {
+      "epoch": 0.11564144866053892,
+      "grad_norm": 0.07015693932771683,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 11.9275,
+      "step": 46
+    },
+    {
+      "epoch": 0.11815539319663759,
+      "grad_norm": 0.07656406611204147,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 11.9277,
+      "step": 47
+    },
+    {
+      "epoch": 0.12066933773273628,
+      "grad_norm": 0.10160171240568161,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9253,
+      "step": 48
+    },
+    {
+      "epoch": 0.12318328226883495,
+      "grad_norm": 0.09546644985675812,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 11.9254,
+      "step": 49
+    },
+    {
+      "epoch": 0.12569722680493361,
+      "grad_norm": 0.11191833764314651,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 11.9233,
+      "step": 50
+    },
+    {
+      "epoch": 0.12569722680493361,
+      "eval_loss": 11.927906036376953,
+      "eval_runtime": 0.2529,
+      "eval_samples_per_second": 197.706,
+      "eval_steps_per_second": 51.404,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null