Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9624e9a151663ac191cc4fa232c61bd9caaa5f68fc967bf4426ca5df8971d9b9
+oid sha256:4535495114a6129065de48e93703b0614f1b2313336bf6758ce9fde9582a17b6
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7677e032df90eb88721c864579dca479a5b6579e09f8f42cb668edc62cbed8d
+oid sha256:ba761bad8392ff8c1a5b5cc9d912f6064df81328280cf6439a1b6378cf6b267f
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2a5b05f09b8564f5d7ae67ac0484834ab5096f9c2c5416efc0bd11bed918dd
+oid sha256:014e0a77f7974addd051403c6243880eb0ecd104694207ef2f821e79d728a72f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bdd58a7b31c078fa85d00c7c6485823b15270c30aba6855ca78181731d87134
+oid sha256:a0054915793dbfa9bd5581f14262cf63c5e9f72a45d1343ddf99886b1f56cead
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96335fae8d0428a10bf29ce620e4c16471dfc1c7bc18964f4276730c5e3fa77e
+oid sha256:d0bdb0f22d53725d520356da3f2de3e6c5621cfe85930d75894527898f74102e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af91e38f8ee05f8cc00ff1294dd2d779b194430a94ac4b05a2cb8d13aa0041e
+oid sha256:69807e4f25993cc5ca2d70ce593bc3788a7e38e55f06724bb5ead2e736dfc448
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.623828649520874,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.09725655468655023,
+  "epoch": 0.12319163593629695,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 17.036,
       "eval_steps_per_second": 4.429,
       "step": 75
+    },
+    {
+      "epoch": 0.09855330874903756,
+      "grad_norm": 8.681092262268066,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 35.4697,
+      "step": 76
+    },
+    {
+      "epoch": 0.0998500628115249,
+      "grad_norm": 8.077815055847168,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 26.0121,
+      "step": 77
+    },
+    {
+      "epoch": 0.10114681687401224,
+      "grad_norm": 9.344439506530762,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 17.0227,
+      "step": 78
+    },
+    {
+      "epoch": 0.10244357093649957,
+      "grad_norm": 7.068110466003418,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 12.5787,
+      "step": 79
+    },
+    {
+      "epoch": 0.10374032499898692,
+      "grad_norm": 6.340619087219238,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 9.7321,
+      "step": 80
+    },
+    {
+      "epoch": 0.10503707906147425,
+      "grad_norm": 8.806065559387207,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 11.5671,
+      "step": 81
+    },
+    {
+      "epoch": 0.10633383312396158,
+      "grad_norm": 7.022125244140625,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 10.8947,
+      "step": 82
+    },
+    {
+      "epoch": 0.10763058718644893,
+      "grad_norm": 8.060321807861328,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 10.6176,
+      "step": 83
+    },
+    {
+      "epoch": 0.10892734124893626,
+      "grad_norm": 8.609227180480957,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 15.1299,
+      "step": 84
+    },
+    {
+      "epoch": 0.11022409531142359,
+      "grad_norm": 9.17025089263916,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 18.7154,
+      "step": 85
+    },
+    {
+      "epoch": 0.11152084937391094,
+      "grad_norm": 13.300969123840332,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 25.0871,
+      "step": 86
+    },
+    {
+      "epoch": 0.11281760343639827,
+      "grad_norm": 17.63905906677246,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 30.7672,
+      "step": 87
+    },
+    {
+      "epoch": 0.1141143574988856,
+      "grad_norm": 23.852336883544922,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 39.7271,
+      "step": 88
+    },
+    {
+      "epoch": 0.11541111156137294,
+      "grad_norm": 8.638887405395508,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 27.7971,
+      "step": 89
+    },
+    {
+      "epoch": 0.11670786562386028,
+      "grad_norm": 7.553443908691406,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 18.6966,
+      "step": 90
+    },
+    {
+      "epoch": 0.11800461968634761,
+      "grad_norm": 7.639990329742432,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 15.038,
+      "step": 91
+    },
+    {
+      "epoch": 0.11930137374883494,
+      "grad_norm": 6.556589603424072,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 13.3639,
+      "step": 92
+    },
+    {
+      "epoch": 0.12059812781132229,
+      "grad_norm": 7.983014106750488,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 12.7111,
+      "step": 93
+    },
+    {
+      "epoch": 0.12189488187380962,
+      "grad_norm": 6.714142799377441,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 10.5141,
+      "step": 94
+    },
+    {
+      "epoch": 0.12319163593629695,
+      "grad_norm": 8.24644947052002,
+      "learning_rate": 1e-05,
+      "loss": 12.6936,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.889478898365235e+17,
+  "total_flos": 9.993120808697856e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null