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:fe55e6db57b1772f13ea0a227c7a5ac8b90940305a1140ed299ffe957970cb22
+oid sha256:3d61c51322e8814635541bf4552430b589066610c73be6fbc77dc9cd49006079
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f9b7da5fc862ebc5ef30b551f2747bbeba5d13dc23c263ebc0d10209790a52
+oid sha256:d25f4360a0627a2534107fcd11474cae9c7f751838cfe57e0ba52de333c29bc4
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3242fa10e9b53b3c8b1644622c1086870916b71a850dbc256c721f58dc10909
+oid sha256:f022338a26936dc941d4fb3f4beadbac7c386256583f7c0b5be3d217fdc6a5ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da4dd1e5db98d1739a37500cab1ba0374bfbcce21c3d331eacab6831f9856b5
+oid sha256:525ac02daa0f154d555c34f20bfaecea654ccea22e1fbc09065d98801f93b381
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cca8bf65f5ac0a00a96fa44d38d2025f077629c201c6239b5423efd6bfad31
+oid sha256:b1b3a8eb00a85b3f08b48a5c301677c0e57cebf2f691a9359b84a007dbd106d1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f88f929e89d1bda332fbad1138c45d598fc4f01cff903e10037e98a1feb618f
+oid sha256:3b52a8a37394f83d217f00abe5e3dba5b1efda5d4c775ade666aa6942e1193bf
 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": 1.6852511167526245,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.0265183917878529,
+  "epoch": 1.300256629597947,
   "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": 34.051,
       "eval_steps_per_second": 8.853,
       "step": 75
+    },
+    {
+      "epoch": 1.0402053036783576,
+      "grad_norm": 0.6126305460929871,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 1.7548,
+      "step": 76
+    },
+    {
+      "epoch": 1.0538922155688624,
+      "grad_norm": 0.6389468312263489,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 1.8156,
+      "step": 77
+    },
+    {
+      "epoch": 1.067579127459367,
+      "grad_norm": 0.6474320888519287,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 1.7414,
+      "step": 78
+    },
+    {
+      "epoch": 1.0812660393498716,
+      "grad_norm": 0.6839907169342041,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 1.6932,
+      "step": 79
+    },
+    {
+      "epoch": 1.0949529512403764,
+      "grad_norm": 0.6910409331321716,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 1.6342,
+      "step": 80
+    },
+    {
+      "epoch": 1.1086398631308811,
+      "grad_norm": 0.736857533454895,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.6396,
+      "step": 81
+    },
+    {
+      "epoch": 1.122326775021386,
+      "grad_norm": 0.7820208072662354,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 1.6122,
+      "step": 82
+    },
+    {
+      "epoch": 1.1360136869118904,
+      "grad_norm": 0.8468031287193298,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 1.5167,
+      "step": 83
+    },
+    {
+      "epoch": 1.1497005988023952,
+      "grad_norm": 0.8978099822998047,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 1.4598,
+      "step": 84
+    },
+    {
+      "epoch": 1.1633875106929,
+      "grad_norm": 1.1949200630187988,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 1.3726,
+      "step": 85
+    },
+    {
+      "epoch": 1.1770744225834047,
+      "grad_norm": 0.7065590023994446,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 1.7266,
+      "step": 86
+    },
+    {
+      "epoch": 1.1907613344739094,
+      "grad_norm": 0.6318903565406799,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 1.9521,
+      "step": 87
+    },
+    {
+      "epoch": 1.204448246364414,
+      "grad_norm": 0.6263776421546936,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 1.78,
+      "step": 88
+    },
+    {
+      "epoch": 1.2181351582549187,
+      "grad_norm": 0.6598425507545471,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 1.7473,
+      "step": 89
+    },
+    {
+      "epoch": 1.2318220701454234,
+      "grad_norm": 0.6533094644546509,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 1.7707,
+      "step": 90
+    },
+    {
+      "epoch": 1.2455089820359282,
+      "grad_norm": 0.6790942549705505,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 1.6519,
+      "step": 91
+    },
+    {
+      "epoch": 1.259195893926433,
+      "grad_norm": 0.7855159640312195,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 1.6926,
+      "step": 92
+    },
+    {
+      "epoch": 1.2728828058169377,
+      "grad_norm": 0.8199930787086487,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 1.703,
+      "step": 93
+    },
+    {
+      "epoch": 1.2865697177074422,
+      "grad_norm": 0.8154268860816956,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 1.5764,
+      "step": 94
+    },
+    {
+      "epoch": 1.300256629597947,
+      "grad_norm": 0.8530352711677551,
+      "learning_rate": 1e-05,
+      "loss": 1.5592,
+      "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": 2.384195670245376e+17,
+  "total_flos": 3.0199811823108096e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null