Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0372f0a271a0c1c6b63f4da0f685d87dc7fadafb467ea00070d89b791b6fd7
+oid sha256:1be3c275aaa35e9c45d72c36304744caaabe493d7b47092968aaab9794256cb7
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70519e04bea23d31d3eaab0999784f8788896b40e7fb5612e76492665b9e9836
+oid sha256:8fcab19f0506973ede613f2a9a55ad239442abc8275fe751f69d8319535dc634
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e2f53af15dd01177ff62e3adff4c8e72c95a50a77e0cb9152cae995de11053
+oid sha256:3158f4e98074e50fa64f8958ab897746e2f5a450c124a097fd6895043c5b1b0c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767222d2e8f15afc2f99b1609c6c3a2a28c9b75dab8d3eb9a5e78c9836a3c766
+oid sha256:fe247abadfab303ae3a79cd43fe3a69591774557a4a1823118e487756a88d447
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb1643c8e675e8f955fba7bd97a1f86867e6aace30b98c6daf2420f7e0bcf20
+oid sha256:9bb2eec78faea8f011ea08ed234c900851f7f8f5257df2ab372fe1478f228240
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7129f30b1945b5a1f3fb2772ca9cbf49030f7c615b6b394b97194448ebad0c
+oid sha256:12323d662430805ac5be5dd5697d5d076321e6aa726854ab307f1247ef438064
 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": 1.613996982574463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06575702778234424,
+  "best_metric": 1.475806474685669,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13151405556468848,
   "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": 21.452,
       "eval_steps_per_second": 5.577,
       "step": 25
+    },
+    {
+      "epoch": 0.068387308893638,
+      "grad_norm": 2.0202596187591553,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5667,
+      "step": 26
+    },
+    {
+      "epoch": 0.07101759000493178,
+      "grad_norm": 2.1556060314178467,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5961,
+      "step": 27
+    },
+    {
+      "epoch": 0.07364787111622555,
+      "grad_norm": 1.9927035570144653,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5073,
+      "step": 28
+    },
+    {
+      "epoch": 0.07627815222751931,
+      "grad_norm": 1.8589670658111572,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5465,
+      "step": 29
+    },
+    {
+      "epoch": 0.07890843333881309,
+      "grad_norm": 2.149338483810425,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.616,
+      "step": 30
+    },
+    {
+      "epoch": 0.08153871445010685,
+      "grad_norm": 2.1401331424713135,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.511,
+      "step": 31
+    },
+    {
+      "epoch": 0.08416899556140063,
+      "grad_norm": 3.1085312366485596,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.5366,
+      "step": 32
+    },
+    {
+      "epoch": 0.0867992766726944,
+      "grad_norm": 3.0993728637695312,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.53,
+      "step": 33
+    },
+    {
+      "epoch": 0.08942955778398816,
+      "grad_norm": 3.186367988586426,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6375,
+      "step": 34
+    },
+    {
+      "epoch": 0.09205983889528194,
+      "grad_norm": 3.874236583709717,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5334,
+      "step": 35
+    },
+    {
+      "epoch": 0.0946901200065757,
+      "grad_norm": 4.275596618652344,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3862,
+      "step": 36
+    },
+    {
+      "epoch": 0.09732040111786948,
+      "grad_norm": 3.7926650047302246,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2366,
+      "step": 37
+    },
+    {
+      "epoch": 0.09995068222916324,
+      "grad_norm": 3.127962827682495,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.454,
+      "step": 38
+    },
+    {
+      "epoch": 0.10258096334045701,
+      "grad_norm": 2.497931957244873,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3641,
+      "step": 39
+    },
+    {
+      "epoch": 0.10521124445175078,
+      "grad_norm": 2.0440142154693604,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4007,
+      "step": 40
+    },
+    {
+      "epoch": 0.10784152556304455,
+      "grad_norm": 2.033963680267334,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.5559,
+      "step": 41
+    },
+    {
+      "epoch": 0.11047180667433831,
+      "grad_norm": 2.140683889389038,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5221,
+      "step": 42
+    },
+    {
+      "epoch": 0.11310208778563209,
+      "grad_norm": 2.208739757537842,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5577,
+      "step": 43
+    },
+    {
+      "epoch": 0.11573236889692586,
+      "grad_norm": 2.212786912918091,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5415,
+      "step": 44
+    },
+    {
+      "epoch": 0.11836265000821963,
+      "grad_norm": 2.4894113540649414,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5774,
+      "step": 45
+    },
+    {
+      "epoch": 0.1209929311195134,
+      "grad_norm": 2.980783224105835,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.6721,
+      "step": 46
+    },
+    {
+      "epoch": 0.12362321223080716,
+      "grad_norm": 3.151621103286743,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5915,
+      "step": 47
+    },
+    {
+      "epoch": 0.12625349334210093,
+      "grad_norm": 3.5633890628814697,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5143,
+      "step": 48
+    },
+    {
+      "epoch": 0.12888377445339472,
+      "grad_norm": 3.7043654918670654,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.242,
+      "step": 49
+    },
+    {
+      "epoch": 0.13151405556468848,
+      "grad_norm": 4.95023775100708,
+      "learning_rate": 1e-05,
+      "loss": 1.3159,
+      "step": 50
+    },
+    {
+      "epoch": 0.13151405556468848,
+      "eval_loss": 1.475806474685669,
+      "eval_runtime": 2.3073,
+      "eval_samples_per_second": 21.671,
+      "eval_steps_per_second": 5.634,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null