Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873968afcbee063f4de5d9a1a1eb0c6ae23680045f6a301307341eb4b7d3f4a3
+oid sha256:7d0538150b7373f620902e207769266e44d4392c4afdb09bfdd656ec4fd7a537
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a609c5e36fe18c030e31cf092372d4d07aea10090f4f1e42768531124c7e45
+oid sha256:654fdcbac7eb5c1bc8de4957e7ecd467e18ee8bc9b60725d44b82ff0a3cc2a1d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5858013b3f4519048df20f56ea7907f316ea8e045826adf5ef0308a0bc1b239
+oid sha256:2302a0e557b2d0f01676f37b50af6d62befbea76aa5c3220e6eada496e417550
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584394df2e3abee26f12de831c09de63efd31e516b429cf763d4e7406a88035c
+oid sha256:c001db7fab6a4560fbf557b264a0cd387de07d0032ea9d82e9867d6cd7f21904
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6edff843be5edf7eb5ad254eb9c0e8f3b8f102600718407a3f5441148bad3c35
+oid sha256:48a40d131b0ea950ddfc6e6c8c8fefce56cfdf2adb0e969c7e149feafab50b83
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9982fe4c7a2112ada18061bd8e05acce3014aebf0142caee8074d48a12b44f0
+oid sha256:d50a65c5076c3485346b1187244057225ba5516f493f3b324608a7a18ec620de
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7302217483520508,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04681647940074907,
+  "best_metric": 1.704688310623169,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09363295880149813,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 37.249,
       "eval_steps_per_second": 4.659,
       "step": 25
+    },
+    {
+      "epoch": 0.04868913857677903,
+      "grad_norm": 2.102870464324951,
+      "learning_rate": 5e-05,
+      "loss": 2.0417,
+      "step": 26
+    },
+    {
+      "epoch": 0.05056179775280899,
+      "grad_norm": 1.305487036705017,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8175,
+      "step": 27
+    },
+    {
+      "epoch": 0.052434456928838954,
+      "grad_norm": 0.9561019539833069,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6949,
+      "step": 28
+    },
+    {
+      "epoch": 0.054307116104868915,
+      "grad_norm": 0.9226228594779968,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.685,
+      "step": 29
+    },
+    {
+      "epoch": 0.056179775280898875,
+      "grad_norm": 0.972161591053009,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6658,
+      "step": 30
+    },
+    {
+      "epoch": 0.05805243445692884,
+      "grad_norm": 0.9487056732177734,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6709,
+      "step": 31
+    },
+    {
+      "epoch": 0.0599250936329588,
+      "grad_norm": 1.209452509880066,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6045,
+      "step": 32
+    },
+    {
+      "epoch": 0.06179775280898876,
+      "grad_norm": 1.2375152111053467,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5892,
+      "step": 33
+    },
+    {
+      "epoch": 0.06367041198501873,
+      "grad_norm": 1.1725419759750366,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.675,
+      "step": 34
+    },
+    {
+      "epoch": 0.06554307116104868,
+      "grad_norm": 1.2376482486724854,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5847,
+      "step": 35
+    },
+    {
+      "epoch": 0.06741573033707865,
+      "grad_norm": 1.0627553462982178,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5509,
+      "step": 36
+    },
+    {
+      "epoch": 0.06928838951310862,
+      "grad_norm": 1.3285757303237915,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5592,
+      "step": 37
+    },
+    {
+      "epoch": 0.07116104868913857,
+      "grad_norm": 1.3554985523223877,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8612,
+      "step": 38
+    },
+    {
+      "epoch": 0.07303370786516854,
+      "grad_norm": 1.2999721765518188,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8108,
+      "step": 39
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 1.1102705001831055,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6896,
+      "step": 40
+    },
+    {
+      "epoch": 0.07677902621722846,
+      "grad_norm": 1.322104811668396,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8057,
+      "step": 41
+    },
+    {
+      "epoch": 0.07865168539325842,
+      "grad_norm": 0.9521006345748901,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.71,
+      "step": 42
+    },
+    {
+      "epoch": 0.08052434456928839,
+      "grad_norm": 0.97364342212677,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6975,
+      "step": 43
+    },
+    {
+      "epoch": 0.08239700374531835,
+      "grad_norm": 0.9265180230140686,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6275,
+      "step": 44
+    },
+    {
+      "epoch": 0.08426966292134831,
+      "grad_norm": 0.9337721467018127,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7701,
+      "step": 45
+    },
+    {
+      "epoch": 0.08614232209737828,
+      "grad_norm": 0.8613065481185913,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6093,
+      "step": 46
+    },
+    {
+      "epoch": 0.08801498127340825,
+      "grad_norm": 0.9239866137504578,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6571,
+      "step": 47
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 0.9398760795593262,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6435,
+      "step": 48
+    },
+    {
+      "epoch": 0.09176029962546817,
+      "grad_norm": 1.0276689529418945,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6551,
+      "step": 49
+    },
+    {
+      "epoch": 0.09363295880149813,
+      "grad_norm": 1.0870341062545776,
+      "learning_rate": 0.0,
+      "loss": 1.5904,
+      "step": 50
+    },
+    {
+      "epoch": 0.09363295880149813,
+      "eval_loss": 1.704688310623169,
+      "eval_runtime": 96.0116,
+      "eval_samples_per_second": 37.475,
+      "eval_steps_per_second": 4.687,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null