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:bf6e2f34a437cc812d80116db6b3f6e3dc9249735fccac25dbd833e0efd52047
+oid sha256:edbcbcd6bdcbb722b562683c0982b06ac97a9893f548ced09abdab5b1a6a044f
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9563cf1303015f1e47633400eae256015b83d96252d08ebcc19ef3cda9b40f61
+oid sha256:cc54eadd32637345b869c379ecc69fd97251c355b30359ffa8da436fc1ed0273
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de426bbc15c4be72c228cb80b9966550032ee81fc5c4e878ea4f3eb899834a5
+oid sha256:2742a0f633e24acceb85204e414da2819aeeac19effd2c70e2aff1627b756a14
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d8e68d636d47c3f5773c1481f02bce82a8857eb226987ac68f9c7a6f67f325
+oid sha256:df3b9cc8d58da34d4e97cabc826d63c534ac7aaae0451e31b586459841c4c6e5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee9c227f27343b1cf7e8f5f80fa67616152e754a3450fbcc9e0304b2966329c
+oid sha256:c97f0b5db7c2f38a611c26dad843acd5211c74f2a59cb8ff33ed37bd35f5afd3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff30627bbe4a5a58431dc59129643ab4793b7f03955eaf533bbb2f129b58445
+oid sha256:5365e09c5a31ca5ec1459e0bd616191f34140149fc218a32c04343b693dea842
 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": 0.7020787596702576,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.11885895404120443,
+  "epoch": 0.15055467511885895,
   "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": 15.101,
       "eval_steps_per_second": 3.926,
       "step": 75
+    },
+    {
+      "epoch": 0.12044374009508717,
+      "grad_norm": 0.557953953742981,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.7917,
+      "step": 76
+    },
+    {
+      "epoch": 0.12202852614896989,
+      "grad_norm": 0.5222028493881226,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.7734,
+      "step": 77
+    },
+    {
+      "epoch": 0.12361331220285261,
+      "grad_norm": 0.5229513645172119,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.7783,
+      "step": 78
+    },
+    {
+      "epoch": 0.12519809825673534,
+      "grad_norm": 0.5746840238571167,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.7599,
+      "step": 79
+    },
+    {
+      "epoch": 0.12678288431061807,
+      "grad_norm": 0.523705244064331,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.6275,
+      "step": 80
+    },
+    {
+      "epoch": 0.12836767036450078,
+      "grad_norm": 0.5565693974494934,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.701,
+      "step": 81
+    },
+    {
+      "epoch": 0.12995245641838352,
+      "grad_norm": 0.5287532210350037,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.5081,
+      "step": 82
+    },
+    {
+      "epoch": 0.13153724247226625,
+      "grad_norm": 0.594470739364624,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.5422,
+      "step": 83
+    },
+    {
+      "epoch": 0.13312202852614896,
+      "grad_norm": 0.6673708558082581,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.5362,
+      "step": 84
+    },
+    {
+      "epoch": 0.1347068145800317,
+      "grad_norm": 0.9278484582901001,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.6325,
+      "step": 85
+    },
+    {
+      "epoch": 0.13629160063391443,
+      "grad_norm": 0.8525876998901367,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.5122,
+      "step": 86
+    },
+    {
+      "epoch": 0.13787638668779714,
+      "grad_norm": 1.6866328716278076,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.6012,
+      "step": 87
+    },
+    {
+      "epoch": 0.13946117274167988,
+      "grad_norm": 0.9566619992256165,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.7856,
+      "step": 88
+    },
+    {
+      "epoch": 0.1410459587955626,
+      "grad_norm": 0.5302878618240356,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.8218,
+      "step": 89
+    },
+    {
+      "epoch": 0.14263074484944532,
+      "grad_norm": 0.4923751950263977,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.7623,
+      "step": 90
+    },
+    {
+      "epoch": 0.14421553090332806,
+      "grad_norm": 0.5600050091743469,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.6418,
+      "step": 91
+    },
+    {
+      "epoch": 0.14580031695721077,
+      "grad_norm": 0.528347373008728,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.6164,
+      "step": 92
+    },
+    {
+      "epoch": 0.1473851030110935,
+      "grad_norm": 0.571899950504303,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.723,
+      "step": 93
+    },
+    {
+      "epoch": 0.14896988906497624,
+      "grad_norm": 0.5378746390342712,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.509,
+      "step": 94
+    },
+    {
+      "epoch": 0.15055467511885895,
+      "grad_norm": 0.6092713475227356,
+      "learning_rate": 1e-05,
+      "loss": 0.5414,
+      "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": 7.98028814352384e+17,
+  "total_flos": 1.0108364981796864e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null