Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87786da68bfd89a9c51ca144e2dbe8720d884cc153aa4af97a688dc7a5ec5f43
+oid sha256:6c8e65d798c6d343c5489fd398f690e5be492155e5d996879d9ebde389fcea65
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63c6a2b6fb71565e2a88e78ab5427068150f85fdd018673c516aaacdc0d1f09
+oid sha256:463c4fafe063beaabb61218b2abf18b1ff7986bdaae72519070a82474c3b4bab
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc0069e110610e59528c04803fe0f8f18029279562d95bd0b55b5697d7ca97dd
+oid sha256:57ed317b03bf7861a503e5f81e2fb5a92211e1eb1eca9dba2720cafc83d5ff46
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef83491accae5e9c5c3447eee76089e5ec99e1b1aefde6e4c2bf51aac0c1c2e
+oid sha256:e4d635b9548adbbce23f1775b3d73d0d84c0ba66008f246214003a1d2c207a6f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffbc0955e9a48b707189d482ed198f2ae16da4ea84743c50bdbe5ddf46e2a82
+oid sha256:99e7ef3b0c611dc78a1a65a4d67a49474c796f39fc08ff2fb8575051c2aa8044
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63abb24e7d50c1663315e87847a4330d52b93a2978a52252516beb869fbc0847
+oid sha256:04a0a6f95f88fdc3b489a90a03d5bbaeaa2a9670da5254b73c72e95c6a642f01
 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": 0.7902164459228516,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.37319234955683406,
+  "epoch": 0.4727103094386565,
   "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": 47.321,
       "eval_steps_per_second": 12.304,
       "step": 75
+    },
+    {
+      "epoch": 0.3781682475509252,
+      "grad_norm": 0.1049114391207695,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.9218,
+      "step": 76
+    },
+    {
+      "epoch": 0.3831441455450163,
+      "grad_norm": 0.12478011101484299,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.7758,
+      "step": 77
+    },
+    {
+      "epoch": 0.38812004353910745,
+      "grad_norm": 0.1491149365901947,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.8426,
+      "step": 78
+    },
+    {
+      "epoch": 0.39309594153319855,
+      "grad_norm": 0.1671927273273468,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.8121,
+      "step": 79
+    },
+    {
+      "epoch": 0.3980718395272897,
+      "grad_norm": 0.17548252642154694,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.8689,
+      "step": 80
+    },
+    {
+      "epoch": 0.4030477375213808,
+      "grad_norm": 0.1623646467924118,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.8746,
+      "step": 81
+    },
+    {
+      "epoch": 0.40802363551547194,
+      "grad_norm": 0.17200708389282227,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.907,
+      "step": 82
+    },
+    {
+      "epoch": 0.41299953350956303,
+      "grad_norm": 0.1750720888376236,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.8647,
+      "step": 83
+    },
+    {
+      "epoch": 0.4179754315036542,
+      "grad_norm": 0.16917237639427185,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.8754,
+      "step": 84
+    },
+    {
+      "epoch": 0.4229513294977453,
+      "grad_norm": 0.19028206169605255,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.8705,
+      "step": 85
+    },
+    {
+      "epoch": 0.4279272274918364,
+      "grad_norm": 0.20847304165363312,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.8799,
+      "step": 86
+    },
+    {
+      "epoch": 0.4329031254859275,
+      "grad_norm": 0.2649713456630707,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.7941,
+      "step": 87
+    },
+    {
+      "epoch": 0.43787902348001867,
+      "grad_norm": 0.12713563442230225,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.8887,
+      "step": 88
+    },
+    {
+      "epoch": 0.44285492147410976,
+      "grad_norm": 0.11893071234226227,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.9033,
+      "step": 89
+    },
+    {
+      "epoch": 0.4478308194682009,
+      "grad_norm": 0.12651102244853973,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.782,
+      "step": 90
+    },
+    {
+      "epoch": 0.452806717462292,
+      "grad_norm": 0.12543635070323944,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.781,
+      "step": 91
+    },
+    {
+      "epoch": 0.45778261545638316,
+      "grad_norm": 0.12762346863746643,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.8043,
+      "step": 92
+    },
+    {
+      "epoch": 0.46275851345047425,
+      "grad_norm": 0.1441301554441452,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.8657,
+      "step": 93
+    },
+    {
+      "epoch": 0.4677344114445654,
+      "grad_norm": 0.2067331075668335,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.8734,
+      "step": 94
+    },
+    {
+      "epoch": 0.4727103094386565,
+      "grad_norm": 0.1604580581188202,
+      "learning_rate": 1e-05,
+      "loss": 0.8626,
+      "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": 1.250124588122112e+17,
+  "total_flos": 1.5834911449546752e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null