Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863ccf752d78c4b04c5fa28388d86357f3b53122006963229cd9128cccbc4fe4
+oid sha256:e6850da0ab33ef52d5fcda6527bc8996c871bb61edb0d74d52908a274f8e18f6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e284daf5d11240e2604ba05d73e2e5a324ba445fc1137a417a39b0ac73d3ca2
+oid sha256:c8ea5c1819ae9e21d764bf4f187a0225f85457c7f9e2ea3e4e89de9a94c946fe
 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": 1.7174628973007202,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04681647940074907,
+  "best_metric": 1.6797080039978027,
+  "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": 14.809,
       "eval_steps_per_second": 1.852,
       "step": 25
+    },
+    {
+      "epoch": 0.04868913857677903,
+      "grad_norm": 2.2478160858154297,
+      "learning_rate": 5e-05,
+      "loss": 2.0625,
+      "step": 26
+    },
+    {
+      "epoch": 0.05056179775280899,
+      "grad_norm": 1.5112407207489014,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8351,
+      "step": 27
+    },
+    {
+      "epoch": 0.052434456928838954,
+      "grad_norm": 1.1244219541549683,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7192,
+      "step": 28
+    },
+    {
+      "epoch": 0.054307116104868915,
+      "grad_norm": 1.005778431892395,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.685,
+      "step": 29
+    },
+    {
+      "epoch": 0.056179775280898875,
+      "grad_norm": 0.9678806662559509,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6409,
+      "step": 30
+    },
+    {
+      "epoch": 0.05805243445692884,
+      "grad_norm": 1.0039587020874023,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6625,
+      "step": 31
+    },
+    {
+      "epoch": 0.0599250936329588,
+      "grad_norm": 1.1212393045425415,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5962,
+      "step": 32
+    },
+    {
+      "epoch": 0.06179775280898876,
+      "grad_norm": 1.1912685632705688,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5737,
+      "step": 33
+    },
+    {
+      "epoch": 0.06367041198501873,
+      "grad_norm": 1.0543924570083618,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6632,
+      "step": 34
+    },
+    {
+      "epoch": 0.06554307116104868,
+      "grad_norm": 1.2754708528518677,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5752,
+      "step": 35
+    },
+    {
+      "epoch": 0.06741573033707865,
+      "grad_norm": 1.1570887565612793,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5309,
+      "step": 36
+    },
+    {
+      "epoch": 0.06928838951310862,
+      "grad_norm": 1.335957646369934,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5368,
+      "step": 37
+    },
+    {
+      "epoch": 0.07116104868913857,
+      "grad_norm": 1.1365514993667603,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8507,
+      "step": 38
+    },
+    {
+      "epoch": 0.07303370786516854,
+      "grad_norm": 1.1642248630523682,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7966,
+      "step": 39
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 1.0239207744598389,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6646,
+      "step": 40
+    },
+    {
+      "epoch": 0.07677902621722846,
+      "grad_norm": 1.0390326976776123,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.7976,
+      "step": 41
+    },
+    {
+      "epoch": 0.07865168539325842,
+      "grad_norm": 0.9292603731155396,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6664,
+      "step": 42
+    },
+    {
+      "epoch": 0.08052434456928839,
+      "grad_norm": 0.9708360433578491,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6991,
+      "step": 43
+    },
+    {
+      "epoch": 0.08239700374531835,
+      "grad_norm": 0.917884349822998,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6031,
+      "step": 44
+    },
+    {
+      "epoch": 0.08426966292134831,
+      "grad_norm": 0.955154538154602,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7643,
+      "step": 45
+    },
+    {
+      "epoch": 0.08614232209737828,
+      "grad_norm": 0.9974094033241272,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.597,
+      "step": 46
+    },
+    {
+      "epoch": 0.08801498127340825,
+      "grad_norm": 0.9787687063217163,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.618,
+      "step": 47
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 0.9520777463912964,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6154,
+      "step": 48
+    },
+    {
+      "epoch": 0.09176029962546817,
+      "grad_norm": 1.1157002449035645,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6452,
+      "step": 49
+    },
+    {
+      "epoch": 0.09363295880149813,
+      "grad_norm": 1.192071557044983,
+      "learning_rate": 0.0,
+      "loss": 1.5853,
+      "step": 50
+    },
+    {
+      "epoch": 0.09363295880149813,
+      "eval_loss": 1.6797080039978027,
+      "eval_runtime": 243.0062,
+      "eval_samples_per_second": 14.806,
+      "eval_steps_per_second": 1.852,
+      "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