Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c5bbcbe962be6364ead93bedbc8aec1dd6cd91fa75d6e02eb9a1fc906b1cb5
+oid sha256:00334b825ce1f70d905871eea7d2394da71547ecfa1991ac620f201038a0443b
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d689b93a4d4fbaeea093ab7b9312c21148fa7733b949cc729068f595b454551b
+oid sha256:02cba43b3d8135f6f6d509f073fcfa566291bdbb08f617fe5a055d5945a10d25
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a0470b363d8422747a96da897373ba7aa5d79daf96f38002a7b2dad736b962
+oid sha256:82ded4faecb709177fbd8b3df1e2adb705ad0c3872bbbe302840720507867e19
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e172c9bcfe170b63a0ac9246a7bf38cd3766c6c944899add8840e3351e00e6
+oid sha256:919feaf85d3268ed19355efda2811e6e0f0f2f0e8f09dea90c33546b39823cc1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc92bbf2db7fde38602b913142994e5c57faa26060ccc744d18c12d8d6da3e7
+oid sha256:50e7870e6492c3bef476326993a4c3e5383a351dd34b507ff89d57080a224884
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef6c1cf2288ba4cecf80d0decb558393223fd461f0407406ec05102721a51b25
+oid sha256:1217b6487d5951b3432237a1ea350f0648993d903cc56a9692c16a263dac5e90
 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": 0.6766892075538635,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.17985611510791366,
+  "epoch": 0.2278177458033573,
   "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": 66.606,
       "eval_steps_per_second": 17.318,
       "step": 75
+    },
+    {
+      "epoch": 0.18225419664268586,
+      "grad_norm": 0.16568902134895325,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.8217,
+      "step": 76
+    },
+    {
+      "epoch": 0.18465227817745802,
+      "grad_norm": 0.17887593805789948,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.7957,
+      "step": 77
+    },
+    {
+      "epoch": 0.18705035971223022,
+      "grad_norm": 0.1890738606452942,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.8071,
+      "step": 78
+    },
+    {
+      "epoch": 0.18944844124700239,
+      "grad_norm": 0.19821521639823914,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.8074,
+      "step": 79
+    },
+    {
+      "epoch": 0.19184652278177458,
+      "grad_norm": 0.2057449370622635,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.7791,
+      "step": 80
+    },
+    {
+      "epoch": 0.19424460431654678,
+      "grad_norm": 0.2022455483675003,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.7405,
+      "step": 81
+    },
+    {
+      "epoch": 0.19664268585131894,
+      "grad_norm": 0.21495573222637177,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.7107,
+      "step": 82
+    },
+    {
+      "epoch": 0.19904076738609114,
+      "grad_norm": 0.2219359427690506,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.7123,
+      "step": 83
+    },
+    {
+      "epoch": 0.2014388489208633,
+      "grad_norm": 0.22916068136692047,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.7013,
+      "step": 84
+    },
+    {
+      "epoch": 0.2038369304556355,
+      "grad_norm": 0.23410719633102417,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.718,
+      "step": 85
+    },
+    {
+      "epoch": 0.20623501199040767,
+      "grad_norm": 0.2526921033859253,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.6883,
+      "step": 86
+    },
+    {
+      "epoch": 0.20863309352517986,
+      "grad_norm": 0.2825489044189453,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.6675,
+      "step": 87
+    },
+    {
+      "epoch": 0.21103117505995203,
+      "grad_norm": 0.18947294354438782,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.7122,
+      "step": 88
+    },
+    {
+      "epoch": 0.21342925659472423,
+      "grad_norm": 0.17600999772548676,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.8282,
+      "step": 89
+    },
+    {
+      "epoch": 0.2158273381294964,
+      "grad_norm": 0.19144967198371887,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.7966,
+      "step": 90
+    },
+    {
+      "epoch": 0.2182254196642686,
+      "grad_norm": 0.19476370513439178,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.7913,
+      "step": 91
+    },
+    {
+      "epoch": 0.22062350119904076,
+      "grad_norm": 0.20564761757850647,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.7938,
+      "step": 92
+    },
+    {
+      "epoch": 0.22302158273381295,
+      "grad_norm": 0.20608943700790405,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.771,
+      "step": 93
+    },
+    {
+      "epoch": 0.22541966426858512,
+      "grad_norm": 0.2185487449169159,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.7525,
+      "step": 94
+    },
+    {
+      "epoch": 0.2278177458033573,
+      "grad_norm": 0.21544459462165833,
+      "learning_rate": 1e-05,
+      "loss": 0.7168,
+      "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": 4.431359317639168e+16,
+  "total_flos": 5.61440859619328e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null