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:cc57595a8bbefe39c4fd7d58f66ddb5d6e9ac21d62fa02085fc062deee4ed5fa
+oid sha256:64b1d0ed768aa5b67742e132f3de6a2b15ae9947ba33f66a54973dc08aad4489
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423af9dbdf46867c566521d47af2f9623d35cae1f70982c4b08775f32d4c9a45
+oid sha256:38f78736a9be7d00e2e8f23da1694a8f250193093af98312f9590207f64b7dd2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39c0e74b807d279589e955892d45b77b0d5724a1fec9c8b2f99c2362d712d54
+oid sha256:d7528e8dc976bd1c3782752382dddac6e40eefa2edbb65e584b74465672c896e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3061a8a95789ebdcd80feb9608794594df99627b54597f9d58af0df174ca2544
+oid sha256:20d4c6811b56c33f905265a86218be679195ca5163aea2a76c10d2a2d8673aac
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0588bf34645d26f6e8c08f4a580782a5d4563cdeb5d1e1b24b44813709cbce7
+oid sha256:0bb77b159130bed29e67872020d9b2233bcd0a96afc481901af09ceb31b32961
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732a48f706fdd94d1435d60e75f2cfafc3dbe48fa457c175d401e569639c114a
+oid sha256:3717e6ace014b0e432d4f891924f914a5c691d659c8e315b5f276089ecbbd07f
 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": 0.617424488067627,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.09239653512993262,
+  "epoch": 0.11703561116458133,
   "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": 14.155,
       "eval_steps_per_second": 3.68,
       "step": 75
+    },
+    {
+      "epoch": 0.09362848893166506,
+      "grad_norm": 0.7286236882209778,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.6132,
+      "step": 76
+    },
+    {
+      "epoch": 0.0948604427333975,
+      "grad_norm": 0.753804624080658,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.572,
+      "step": 77
+    },
+    {
+      "epoch": 0.09609239653512994,
+      "grad_norm": 0.7297849655151367,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.5946,
+      "step": 78
+    },
+    {
+      "epoch": 0.09732435033686236,
+      "grad_norm": 0.7147274017333984,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.5721,
+      "step": 79
+    },
+    {
+      "epoch": 0.0985563041385948,
+      "grad_norm": 0.6752864718437195,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.6103,
+      "step": 80
+    },
+    {
+      "epoch": 0.09978825794032724,
+      "grad_norm": 0.6844044923782349,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.6109,
+      "step": 81
+    },
+    {
+      "epoch": 0.10102021174205968,
+      "grad_norm": 0.6992493867874146,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.6177,
+      "step": 82
+    },
+    {
+      "epoch": 0.10225216554379211,
+      "grad_norm": 0.7029042840003967,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.6083,
+      "step": 83
+    },
+    {
+      "epoch": 0.10348411934552454,
+      "grad_norm": 0.7730789184570312,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.5947,
+      "step": 84
+    },
+    {
+      "epoch": 0.10471607314725698,
+      "grad_norm": 0.7700346112251282,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.6205,
+      "step": 85
+    },
+    {
+      "epoch": 0.10594802694898942,
+      "grad_norm": 0.8437100648880005,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.6452,
+      "step": 86
+    },
+    {
+      "epoch": 0.10717998075072185,
+      "grad_norm": 0.8955070376396179,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.6851,
+      "step": 87
+    },
+    {
+      "epoch": 0.10841193455245428,
+      "grad_norm": 0.6330913305282593,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.6434,
+      "step": 88
+    },
+    {
+      "epoch": 0.10964388835418672,
+      "grad_norm": 0.6137003302574158,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.5866,
+      "step": 89
+    },
+    {
+      "epoch": 0.11087584215591915,
+      "grad_norm": 0.6017877459526062,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.5825,
+      "step": 90
+    },
+    {
+      "epoch": 0.1121077959576516,
+      "grad_norm": 0.6833033561706543,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.5836,
+      "step": 91
+    },
+    {
+      "epoch": 0.11333974975938402,
+      "grad_norm": 0.7089877128601074,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.5883,
+      "step": 92
+    },
+    {
+      "epoch": 0.11457170356111646,
+      "grad_norm": 0.6717115640640259,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.5702,
+      "step": 93
+    },
+    {
+      "epoch": 0.1158036573628489,
+      "grad_norm": 0.6961142420768738,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.5704,
+      "step": 94
+    },
+    {
+      "epoch": 0.11703561116458133,
+      "grad_norm": 0.7490465044975281,
+      "learning_rate": 1e-05,
+      "loss": 0.5949,
+      "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": 8.952125425975296e+17,
+  "total_flos": 1.1339358872902042e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null