Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d95f3292d011bfa0f6f200c33ec0fe694b4a3504faa2a05b0745f4b0959cefe
+oid sha256:0a3a6f64c7ac7e82a929a52c365002e58d4dd838dc43817f9f5a2d804b4c8bc1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85610e015c5273f9b34bc3223ff08ffa85f188b61e98e4436f3de18aa9fc119
+oid sha256:2072e6fcb9e1c60254fb9ff7810e449e954472be5040b2217db0238779305b8d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9aad5b8a7ed3399ba42be1b623e0f94bb5b63064670587d5808d6a7b1a5604a
+oid sha256:32f287f4f14c43053ea6c90ee4928b94bcf969f560b9d768af617b83bccfa129
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f85dfacbbcc9678049350859c3eda9f18fb349dd16bb5cbd235b5f14e3c6f7d7
+oid sha256:1b7b18bc745805dbd0f3ea600921aeddef3dbaa46b38d498ff1ebdb7cfecc92a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f9b6a40e7893c555ab93b2a2e1fff1d41c9a6b10cdedbfb5c601f543915721
+oid sha256:ccc688f27d4cb82a1923336099e111b3578302ddf2e09b68bfb4abad407a0626
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d1816811d028604e42d7e52a923daa2d44f7ba661542acb2bd12b01c0cd513
+oid sha256:388a4285d7846c761cc90ad43ef2ab1edb68a8356033a7b4c66754443836f8b9
 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": 0.6152855753898621,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.6065200909780136,
+  "epoch": 0.7682587819054839,
   "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": 14.237,
       "eval_steps_per_second": 3.702,
       "step": 75
+    },
+    {
+      "epoch": 0.6146070255243872,
+      "grad_norm": 0.34593966603279114,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.6562,
+      "step": 76
+    },
+    {
+      "epoch": 0.6226939600707607,
+      "grad_norm": 0.36323046684265137,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.6715,
+      "step": 77
+    },
+    {
+      "epoch": 0.6307808946171342,
+      "grad_norm": 0.39813435077667236,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.7863,
+      "step": 78
+    },
+    {
+      "epoch": 0.6388678291635077,
+      "grad_norm": 0.34668055176734924,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.6792,
+      "step": 79
+    },
+    {
+      "epoch": 0.6469547637098813,
+      "grad_norm": 0.38668936491012573,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.8067,
+      "step": 80
+    },
+    {
+      "epoch": 0.6550416982562547,
+      "grad_norm": 0.38659054040908813,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.7092,
+      "step": 81
+    },
+    {
+      "epoch": 0.6631286328026282,
+      "grad_norm": 0.34319162368774414,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.6067,
+      "step": 82
+    },
+    {
+      "epoch": 0.6712155673490018,
+      "grad_norm": 0.38419049978256226,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.7169,
+      "step": 83
+    },
+    {
+      "epoch": 0.6793025018953753,
+      "grad_norm": 0.3796985149383545,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.7196,
+      "step": 84
+    },
+    {
+      "epoch": 0.6873894364417488,
+      "grad_norm": 0.38364750146865845,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.6701,
+      "step": 85
+    },
+    {
+      "epoch": 0.6954763709881223,
+      "grad_norm": 0.4333467185497284,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.6451,
+      "step": 86
+    },
+    {
+      "epoch": 0.7035633055344959,
+      "grad_norm": 0.38475340604782104,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.6131,
+      "step": 87
+    },
+    {
+      "epoch": 0.7116502400808693,
+      "grad_norm": 0.34996670484542847,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.5663,
+      "step": 88
+    },
+    {
+      "epoch": 0.7197371746272428,
+      "grad_norm": 0.3536860942840576,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.6976,
+      "step": 89
+    },
+    {
+      "epoch": 0.7278241091736164,
+      "grad_norm": 0.36633411049842834,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.6998,
+      "step": 90
+    },
+    {
+      "epoch": 0.7359110437199899,
+      "grad_norm": 0.37283647060394287,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.6256,
+      "step": 91
+    },
+    {
+      "epoch": 0.7439979782663634,
+      "grad_norm": 0.35322660207748413,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.6615,
+      "step": 92
+    },
+    {
+      "epoch": 0.7520849128127369,
+      "grad_norm": 0.41877758502960205,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.7689,
+      "step": 93
+    },
+    {
+      "epoch": 0.7601718473591105,
+      "grad_norm": 0.3584843575954437,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.6636,
+      "step": 94
+    },
+    {
+      "epoch": 0.7682587819054839,
+      "grad_norm": 0.3423212170600891,
+      "learning_rate": 1e-05,
+      "loss": 0.5993,
+      "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