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:e1f5d07f9e496e2422654818e4c6f21e6bdd3fc13b3a299d40991ada27f65ae3
+oid sha256:8e0795827e089ce578a567e3826a70714070a631858351f998f9f952a04c43d2
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c21a4ef661adbd6ca37f114541599133be7f22a915a887b43ccfc7cf8b891d
+oid sha256:1846499e178efb094036fff89b4d4bcf4297c2bbbf0a7a099b767df8291b4afb
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87d0182d980ec067ba3388cfe29f42594782dc9b5bf7a5de850d5eb8826895d
+oid sha256:bff3a912909663822fd88c11a1d1ba016856f24e2019765743fa3176a8a89825
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc33a80293ecf896d891104ee67dc8532dc6d24773cfa26342a94867a953d47
+oid sha256:db665512d782f103c0ab3824d7e81a380b2331e8f704a774ed5b375876e295a3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b07a9fbf91ef36ba8318a0d18de6989f692396b4d4cff596ce6462a525ffe8
+oid sha256:a1513fbc82c2958444787d0d286ecebc5bbbf946d9955471b2bab85aaedf6824
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5e1e6282b09d1860efc94cae0c5f892e7cc5bf1ae5740fc02359aad199315f
+oid sha256:81057b28db50f1aab47684b4696ae452edc34e4e76c2137e7e1581d12ce0b55e
 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": 1.6399972438812256,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.6681514476614699,
+  "epoch": 0.8463251670378619,
   "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": 36.852,
       "eval_steps_per_second": 9.582,
       "step": 75
+    },
+    {
+      "epoch": 0.6770601336302895,
+      "grad_norm": 0.16422314941883087,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 1.5677,
+      "step": 76
+    },
+    {
+      "epoch": 0.6859688195991092,
+      "grad_norm": 0.21063150465488434,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 1.7556,
+      "step": 77
+    },
+    {
+      "epoch": 0.6948775055679287,
+      "grad_norm": 0.2691607177257538,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 1.8171,
+      "step": 78
+    },
+    {
+      "epoch": 0.7037861915367484,
+      "grad_norm": 0.29943981766700745,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 1.8864,
+      "step": 79
+    },
+    {
+      "epoch": 0.7126948775055679,
+      "grad_norm": 0.3224969804286957,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 1.8952,
+      "step": 80
+    },
+    {
+      "epoch": 0.7216035634743875,
+      "grad_norm": 0.35002103447914124,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.9489,
+      "step": 81
+    },
+    {
+      "epoch": 0.7305122494432071,
+      "grad_norm": 0.3734034597873688,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 1.7525,
+      "step": 82
+    },
+    {
+      "epoch": 0.7394209354120267,
+      "grad_norm": 0.4094945788383484,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 1.911,
+      "step": 83
+    },
+    {
+      "epoch": 0.7483296213808464,
+      "grad_norm": 0.4211490750312805,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 1.6963,
+      "step": 84
+    },
+    {
+      "epoch": 0.7572383073496659,
+      "grad_norm": 0.5119789242744446,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 1.7085,
+      "step": 85
+    },
+    {
+      "epoch": 0.7661469933184856,
+      "grad_norm": 0.638528048992157,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 1.4974,
+      "step": 86
+    },
+    {
+      "epoch": 0.7750556792873051,
+      "grad_norm": 1.150501012802124,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 1.3799,
+      "step": 87
+    },
+    {
+      "epoch": 0.7839643652561247,
+      "grad_norm": 0.244547039270401,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 1.5573,
+      "step": 88
+    },
+    {
+      "epoch": 0.7928730512249443,
+      "grad_norm": 0.22487600147724152,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 1.4302,
+      "step": 89
+    },
+    {
+      "epoch": 0.8017817371937639,
+      "grad_norm": 0.21676325798034668,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 1.7492,
+      "step": 90
+    },
+    {
+      "epoch": 0.8106904231625836,
+      "grad_norm": 0.2692321538925171,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 1.7248,
+      "step": 91
+    },
+    {
+      "epoch": 0.8195991091314031,
+      "grad_norm": 0.3116702735424042,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 1.7725,
+      "step": 92
+    },
+    {
+      "epoch": 0.8285077951002228,
+      "grad_norm": 0.2740122675895691,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 1.913,
+      "step": 93
+    },
+    {
+      "epoch": 0.8374164810690423,
+      "grad_norm": 0.298614501953125,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 2.0478,
+      "step": 94
+    },
+    {
+      "epoch": 0.8463251670378619,
+      "grad_norm": 0.35496339201927185,
+      "learning_rate": 1e-05,
+      "loss": 1.8879,
+      "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": 1.592781135056732e+17,
+  "total_flos": 2.01808564908458e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null