Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267980867f83b369955945e4f7a3df8b790d72041041895e3422ef39fb5178aa
+oid sha256:734b64962d96dde20b023dee1d4f48a32c2f43a89f28c32574feb174c92a94db
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9b926e87a9ba357954c2e70e614eb9ef11c0ba1dc5beeabda1a59a6992f4e8
+oid sha256:8865d259e292f793426f33b44f11c87efee3fe3bc7670e3a87e04270a1cf39a7
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19fea68435333a8abd760de2233319e4139eb46a8c44a8c91d87130ee26c15e5
+oid sha256:041daf5e94442122ad595703364513594bdf36e7713b9c0db490c8994f88c956
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95dbd42a3cf629dfe091885f47118c7e0fcc74a50fa56073a3d6db4a5cc77c9
+oid sha256:8166ac0a77c36bb471492a06a75508aaad02387972da4dcf704b58c21a637cf4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4019cea1c41797a6557beaadd61a4214ce1dd08b82313a0b556105c3b02393
+oid sha256:9f79238a0b6e15db3e74c57a6170e48b32d9f40bc01d1c6824672007b2d33032
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db4d1116a63749ba0702fe7dce447d7cda3fbfe9a281fc69bf48f875babdaff
+oid sha256:5aedaa79240e12d3c592e58fbcc92e6792f76f0ea0a5820fb0526c1014a97280
 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": 2.399653673171997,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 2.314368370298939,
+  "epoch": 2.931533269045323,
   "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": 48.418,
       "eval_steps_per_second": 12.589,
       "step": 75
+    },
+    {
+      "epoch": 2.3452266152362586,
+      "grad_norm": 0.5155852437019348,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 2.3823,
+      "step": 76
+    },
+    {
+      "epoch": 2.376084860173578,
+      "grad_norm": 0.5314053297042847,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 2.3937,
+      "step": 77
+    },
+    {
+      "epoch": 2.406943105110897,
+      "grad_norm": 0.6399489045143127,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 2.4228,
+      "step": 78
+    },
+    {
+      "epoch": 2.437801350048216,
+      "grad_norm": 0.6850634217262268,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 2.4441,
+      "step": 79
+    },
+    {
+      "epoch": 2.468659594985535,
+      "grad_norm": 1.0091044902801514,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 2.3599,
+      "step": 80
+    },
+    {
+      "epoch": 2.4995178399228544,
+      "grad_norm": 1.378424882888794,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 2.1828,
+      "step": 81
+    },
+    {
+      "epoch": 2.5303760848601735,
+      "grad_norm": 0.4469667673110962,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 2.2746,
+      "step": 82
+    },
+    {
+      "epoch": 2.5612343297974927,
+      "grad_norm": 0.48588716983795166,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 2.3452,
+      "step": 83
+    },
+    {
+      "epoch": 2.592092574734812,
+      "grad_norm": 0.5537601709365845,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 2.4595,
+      "step": 84
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 0.5473658442497253,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 2.3284,
+      "step": 85
+    },
+    {
+      "epoch": 2.65380906460945,
+      "grad_norm": 0.6774117946624756,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 2.3467,
+      "step": 86
+    },
+    {
+      "epoch": 2.6846673095467697,
+      "grad_norm": 0.7467882633209229,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 2.4901,
+      "step": 87
+    },
+    {
+      "epoch": 2.715525554484089,
+      "grad_norm": 1.0815759897232056,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 2.3596,
+      "step": 88
+    },
+    {
+      "epoch": 2.746383799421408,
+      "grad_norm": 1.4572314023971558,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 2.1992,
+      "step": 89
+    },
+    {
+      "epoch": 2.777242044358727,
+      "grad_norm": 0.4223305284976959,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 2.2878,
+      "step": 90
+    },
+    {
+      "epoch": 2.8081002892960463,
+      "grad_norm": 0.48473823070526123,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 2.3765,
+      "step": 91
+    },
+    {
+      "epoch": 2.8389585342333654,
+      "grad_norm": 0.5096808075904846,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 2.4602,
+      "step": 92
+    },
+    {
+      "epoch": 2.8698167791706846,
+      "grad_norm": 0.5460689663887024,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 2.3527,
+      "step": 93
+    },
+    {
+      "epoch": 2.9006750241080037,
+      "grad_norm": 0.6414793133735657,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 2.3315,
+      "step": 94
+    },
+    {
+      "epoch": 2.931533269045323,
+      "grad_norm": 0.7416414022445679,
+      "learning_rate": 1e-05,
+      "loss": 2.4737,
+      "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": 1.2510361358748877e+17,
+  "total_flos": 1.584532913431511e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null