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:f3596ff8b83be1817070c1e2890909ff8591dc13ac0888ce62e442966829fa17
+oid sha256:f21eee4821a403794287932a576b35589216626ce20fbdc60c8ca2f5900681e5
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8454a1dbf07e4b6e8f3bf4dd79bf5f5d8f490f9c160af84c7d4c0d5dc3aa1a1
+oid sha256:e6d34d9f594c28241f7156c857398dbfa2b80ac5d1ff5633bd4f37833b332436
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e5de6ee5e70e6f6379f43adf200babb0b1740bf307978daf655b80c90a7e44
+oid sha256:62c46a6e9a5ad0c4b301aadc541fbf3145737aaa039d9758b4f16c1e7d0c7a30
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6787e67f0c248addce6c903dbc12800b1a196976e1e71b5a4ca273ee0ae34697
+oid sha256:15b72285361f97cff93ce50c34e5a15f8e536984207cc7015d750ea94013be98
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e54237d52508e13492ed2b8a5820590205615d4b466c8b9c6f65479a8d52fe
+oid sha256:23e05d71188a40eafb6dd5967ea0e32343b87c40b158a26cc738f6276d1dd22e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d48fb384625da57c27df708bb460af85484eddbfb2fb4116d0f4df3fd50171
+oid sha256:75afbd67eaad78a59612136e33a0e2f1d8a17379e76d69a96737d5c34db3fea4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.9562482833862305,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12095554883580284,
+  "best_metric": 4.756171226501465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.24191109767160568,
   "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": 79.549,
       "eval_steps_per_second": 20.683,
       "step": 25
+    },
+    {
+      "epoch": 0.12579377078923495,
+      "grad_norm": 4.755553245544434,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.5379,
+      "step": 26
+    },
+    {
+      "epoch": 0.13063199274266707,
+      "grad_norm": 5.11820650100708,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.7219,
+      "step": 27
+    },
+    {
+      "epoch": 0.13547021469609918,
+      "grad_norm": 5.073906898498535,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.8242,
+      "step": 28
+    },
+    {
+      "epoch": 0.1403084366495313,
+      "grad_norm": 3.844876766204834,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.6271,
+      "step": 29
+    },
+    {
+      "epoch": 0.1451466586029634,
+      "grad_norm": 3.936986207962036,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.6216,
+      "step": 30
+    },
+    {
+      "epoch": 0.14998488055639553,
+      "grad_norm": 3.3851535320281982,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.9915,
+      "step": 31
+    },
+    {
+      "epoch": 0.15482310250982764,
+      "grad_norm": 3.053683280944824,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.6988,
+      "step": 32
+    },
+    {
+      "epoch": 0.15966132446325976,
+      "grad_norm": 2.712008476257324,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.6162,
+      "step": 33
+    },
+    {
+      "epoch": 0.16449954641669187,
+      "grad_norm": 2.528663158416748,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.817,
+      "step": 34
+    },
+    {
+      "epoch": 0.169337768370124,
+      "grad_norm": 2.811427593231201,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.7751,
+      "step": 35
+    },
+    {
+      "epoch": 0.1741759903235561,
+      "grad_norm": 3.468078374862671,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.095,
+      "step": 36
+    },
+    {
+      "epoch": 0.17901421227698822,
+      "grad_norm": 4.003626823425293,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 5.0665,
+      "step": 37
+    },
+    {
+      "epoch": 0.18385243423042033,
+      "grad_norm": 3.149742841720581,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.9927,
+      "step": 38
+    },
+    {
+      "epoch": 0.18869065618385245,
+      "grad_norm": 3.245288610458374,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.8175,
+      "step": 39
+    },
+    {
+      "epoch": 0.19352887813728456,
+      "grad_norm": 2.557149887084961,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.2874,
+      "step": 40
+    },
+    {
+      "epoch": 0.19836710009071667,
+      "grad_norm": 5.485939979553223,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.4249,
+      "step": 41
+    },
+    {
+      "epoch": 0.20320532204414876,
+      "grad_norm": 2.7812869548797607,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.6258,
+      "step": 42
+    },
+    {
+      "epoch": 0.20804354399758088,
+      "grad_norm": 2.9063451290130615,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.719,
+      "step": 43
+    },
+    {
+      "epoch": 0.212881765951013,
+      "grad_norm": 3.1801960468292236,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.9229,
+      "step": 44
+    },
+    {
+      "epoch": 0.2177199879044451,
+      "grad_norm": 2.8547780513763428,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.8585,
+      "step": 45
+    },
+    {
+      "epoch": 0.22255820985787722,
+      "grad_norm": 4.2867560386657715,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.6341,
+      "step": 46
+    },
+    {
+      "epoch": 0.22739643181130934,
+      "grad_norm": 3.4731550216674805,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.9739,
+      "step": 47
+    },
+    {
+      "epoch": 0.23223465376474145,
+      "grad_norm": 2.86755108833313,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 5.0205,
+      "step": 48
+    },
+    {
+      "epoch": 0.23707287571817356,
+      "grad_norm": 3.26322865486145,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.8262,
+      "step": 49
+    },
+    {
+      "epoch": 0.24191109767160568,
+      "grad_norm": 4.35727596282959,
+      "learning_rate": 1e-05,
+      "loss": 5.265,
+      "step": 50
+    },
+    {
+      "epoch": 0.24191109767160568,
+      "eval_loss": 4.756171226501465,
+      "eval_runtime": 0.6223,
+      "eval_samples_per_second": 80.348,
+      "eval_steps_per_second": 20.89,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null