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:b4f41337c16bbe084c798d91fe80884b941ad473c29c7a3c2e78387c1c925122
+oid sha256:8e70fdcc478e60da27f3197e8d60a01322dab5ba56ed3aaab7e22acadfd6bf41
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5452cef5d7e0093291198e7194f831fb37ba1f0c57806e5b5f83f0e52897da
+oid sha256:a118f9eeac500c6191769b96b20292bfc2119a1b329e84b310a7c6c66afde3a1
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3b0545016cdad2d62cf5db499381ad30693ddaf4d345902ba2e164e1c35fa8
+oid sha256:9c4ff18d1e3c1fc38137c326c0561b042889bbd0382a5a3a388e3af8c2117c58
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:417c1988987eddde4f77d3ffdba42c9a2ff0d26748cbdfe17718489519eaea46
+oid sha256:5ec1ed7e43cab02929608326c6bcdd67f06ec0bca969c6bebe9a5441efaf60a0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee12974f8c2d6ce98f447f28f9516064d965f704fb182b349bb14faf4e1a345
+oid sha256:03a92398ea1eaf462ada31ae57a370a1e9fb11e68a192bded1c6d7004d4c4883
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902c8c64bdc3048a1f987011cd129962441dc8213f3b0350c8f2231e0dbf883e
+oid sha256:6cd7f23688d8c991346721a32d91cdacf82a7bc62e84484f3eedc7a33075f3f1
 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": 3.767355442047119,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.9639934533551555,
+  "epoch": 2.4877250409165304,
   "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": 172.844,
       "eval_steps_per_second": 44.939,
       "step": 75
+    },
+    {
+      "epoch": 1.9901800327332242,
+      "grad_norm": 0.8656964302062988,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 4.1986,
+      "step": 76
+    },
+    {
+      "epoch": 2.016366612111293,
+      "grad_norm": 0.8424877524375916,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 6.5033,
+      "step": 77
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.6298512816429138,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 3.5305,
+      "step": 78
+    },
+    {
+      "epoch": 2.06873977086743,
+      "grad_norm": 0.577872633934021,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 3.5686,
+      "step": 79
+    },
+    {
+      "epoch": 2.0949263502454993,
+      "grad_norm": 0.4558631479740143,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 3.619,
+      "step": 80
+    },
+    {
+      "epoch": 2.121112929623568,
+      "grad_norm": 0.3921566903591156,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 3.6359,
+      "step": 81
+    },
+    {
+      "epoch": 2.1472995090016367,
+      "grad_norm": 0.3551250398159027,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 3.7263,
+      "step": 82
+    },
+    {
+      "epoch": 2.1734860883797054,
+      "grad_norm": 0.3237386643886566,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 3.7598,
+      "step": 83
+    },
+    {
+      "epoch": 2.199672667757774,
+      "grad_norm": 0.4270864725112915,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 3.8036,
+      "step": 84
+    },
+    {
+      "epoch": 2.2258592471358427,
+      "grad_norm": 0.5806615948677063,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 3.9918,
+      "step": 85
+    },
+    {
+      "epoch": 2.2520458265139114,
+      "grad_norm": 0.4796655774116516,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 2.7358,
+      "step": 86
+    },
+    {
+      "epoch": 2.2782324058919805,
+      "grad_norm": 0.5247834324836731,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 4.1886,
+      "step": 87
+    },
+    {
+      "epoch": 2.304418985270049,
+      "grad_norm": 0.400111585855484,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 3.5208,
+      "step": 88
+    },
+    {
+      "epoch": 2.330605564648118,
+      "grad_norm": 0.35815542936325073,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 3.6359,
+      "step": 89
+    },
+    {
+      "epoch": 2.3567921440261865,
+      "grad_norm": 0.3279394209384918,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 3.6536,
+      "step": 90
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 0.3094680905342102,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 3.7183,
+      "step": 91
+    },
+    {
+      "epoch": 2.409165302782324,
+      "grad_norm": 0.3676002025604248,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 3.7482,
+      "step": 92
+    },
+    {
+      "epoch": 2.4353518821603926,
+      "grad_norm": 0.3828237056732178,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 3.781,
+      "step": 93
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.5239596366882324,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 3.8249,
+      "step": 94
+    },
+    {
+      "epoch": 2.4877250409165304,
+      "grad_norm": 0.8069905638694763,
+      "learning_rate": 1e-05,
+      "loss": 4.1793,
+      "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": 1.70605865336832e+16,
+  "total_flos": 2.161007627599872e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null