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:ebd3d00b878627cd67d075941897596b18c4ea67ff8b5b5095103513562bc08c
+oid sha256:0edb152dd8741b980f7b84fbcac783d3c0d41aaaee058b67388084b64f63c751
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588e72a00c6223e2161c9c240b94cde41ffcbecb12d15e6ca8b034182b6d13b4
+oid sha256:dfd6dd1551eae2b8788ac2c1c755430361ae6c7f55bd61d8010095a978237f02
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c0c9cf0d7c29fd06bfe9ce6aa81667cd6fe7d5b9647245483d9ad449ad51e6f
+oid sha256:44be72edf3d7a0c33c44da04876f8d111e29087823b6bde2dace09e1ff87b7f0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d66a46883f34538dc3a2b24b447886b0f5cd5b52c09c6d43a3b38e8cdb1cd78
+oid sha256:9576e8b2c082ad00ec572a721b0a349184bc79e4c6c4eee7cdeeed643cadd6bd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4dd3734f228ff37ccaa6c66d03a1857352d14e703f6f1513679e097a5fb553
+oid sha256:87bf16491dca8200d7fb710a199fb8452076ba77d6a1aa943bfa4f8b43c87e3b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7b73eeb0eaf69e7c1b40186424e4bc4f68410f4191388d5e88c56413fdccd3
+oid sha256:ac6ed2871d33c7833cc307179f968132237ffef5af5cee18ed6467ff652d5a7b
 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": 10.334551811218262,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.937046004842615,
+  "epoch": 2.453591606133979,
   "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": 351.006,
       "eval_steps_per_second": 91.262,
       "step": 75
+    },
+    {
+      "epoch": 1.9628732849071833,
+      "grad_norm": 0.20866307616233826,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 10.7531,
+      "step": 76
+    },
+    {
+      "epoch": 1.9887005649717513,
+      "grad_norm": 0.20063051581382751,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 10.9387,
+      "step": 77
+    },
+    {
+      "epoch": 2.0145278450363198,
+      "grad_norm": 0.3508239686489105,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 13.3289,
+      "step": 78
+    },
+    {
+      "epoch": 2.040355125100888,
+      "grad_norm": 0.4250504672527313,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 8.3424,
+      "step": 79
+    },
+    {
+      "epoch": 2.066182405165456,
+      "grad_norm": 0.39901620149612427,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 11.4688,
+      "step": 80
+    },
+    {
+      "epoch": 2.0920096852300243,
+      "grad_norm": 0.3271302878856659,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 10.3724,
+      "step": 81
+    },
+    {
+      "epoch": 2.1178369652945923,
+      "grad_norm": 0.336497038602829,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 10.2999,
+      "step": 82
+    },
+    {
+      "epoch": 2.143664245359161,
+      "grad_norm": 0.3253435790538788,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 10.3855,
+      "step": 83
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.29757609963417053,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 10.371,
+      "step": 84
+    },
+    {
+      "epoch": 2.195318805488297,
+      "grad_norm": 0.2762691378593445,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 10.1709,
+      "step": 85
+    },
+    {
+      "epoch": 2.2211460855528653,
+      "grad_norm": 0.19564643502235413,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 10.4328,
+      "step": 86
+    },
+    {
+      "epoch": 2.2469733656174333,
+      "grad_norm": 0.24298599362373352,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 10.5657,
+      "step": 87
+    },
+    {
+      "epoch": 2.272800645682002,
+      "grad_norm": 0.4188690781593323,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 10.8609,
+      "step": 88
+    },
+    {
+      "epoch": 2.29862792574657,
+      "grad_norm": 0.4041149914264679,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 9.6247,
+      "step": 89
+    },
+    {
+      "epoch": 2.324455205811138,
+      "grad_norm": 0.3442460298538208,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 10.1798,
+      "step": 90
+    },
+    {
+      "epoch": 2.3502824858757063,
+      "grad_norm": 0.3444257974624634,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 10.4936,
+      "step": 91
+    },
+    {
+      "epoch": 2.3761097659402743,
+      "grad_norm": 0.31269723176956177,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 10.264,
+      "step": 92
+    },
+    {
+      "epoch": 2.401937046004843,
+      "grad_norm": 0.30598893761634827,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 10.3978,
+      "step": 93
+    },
+    {
+      "epoch": 2.427764326069411,
+      "grad_norm": 0.29670581221580505,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 10.2726,
+      "step": 94
+    },
+    {
+      "epoch": 2.453591606133979,
+      "grad_norm": 0.2217765897512436,
+      "learning_rate": 1e-05,
+      "loss": 10.093,
+      "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": 74957707149312.0,
+  "total_flos": 94858219945984.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null