Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5607f10b7aa49be426242494ff8ade88498bfe969ea1d53a28657fe83e2ebc28
+oid sha256:81ca2f310daf53686488a5b674704aaee603070623a3d32d1ef8bc0cd2b40b06
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5182f9e4d81486dc9b8ae4a8771394fdf8417fdae2722dcfc4a75d0650169d5
+oid sha256:0c9e1edb0a1324aad7f0f44bc050bc9ad737ddc2babbec79cccb11d43c5ed791
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d654412881a620991bd2df08e18f5eb4130db68ee859a200e1b33009119e104
+oid sha256:a5ea40a918eac565ade128c038b0e402ba15f51f6770802ad81aae0cd3d19d0b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5693339db387530e78c44f837fcc11ff76c8365248e4343ef8a43e8db4b1441a
+oid sha256:2ae236d31b781d3d91f5e9682618029d5a2267ef24ac8daee8577c2467f7b0c3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0f88a69fc33fb83b73c18c57e825f1c13671701bc60da44c5e784d4bc565c5
+oid sha256:04e17967f0ecdb00885b7adc8959a59b65366e2ed9df3d2b1b250fa154b9abf8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19defe0f64f7d30bdde1353e72a558d7651e1982f13db8b523d537a97edcc0b5
+oid sha256:d374548d55942eeec0434a636dc3b1f0497ee59f85e8fa323881cea13bc1d97d
 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": 11.057889938354492,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09650180940892641,
+  "best_metric": 11.050453186035156,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.19300361881785283,
   "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": 963.753,
       "eval_steps_per_second": 120.952,
       "step": 25
+    },
+    {
+      "epoch": 0.10036188178528348,
+      "grad_norm": 3.5759146213531494,
+      "learning_rate": 5e-05,
+      "loss": 11.0631,
+      "step": 26
+    },
+    {
+      "epoch": 0.10422195416164053,
+      "grad_norm": 3.4713640213012695,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.0568,
+      "step": 27
+    },
+    {
+      "epoch": 0.10808202653799759,
+      "grad_norm": 3.517700672149658,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.0592,
+      "step": 28
+    },
+    {
+      "epoch": 0.11194209891435464,
+      "grad_norm": 3.803478479385376,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.0491,
+      "step": 29
+    },
+    {
+      "epoch": 0.1158021712907117,
+      "grad_norm": 3.692575216293335,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.0552,
+      "step": 30
+    },
+    {
+      "epoch": 0.11966224366706876,
+      "grad_norm": 3.297511577606201,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.0584,
+      "step": 31
+    },
+    {
+      "epoch": 0.12352231604342581,
+      "grad_norm": 3.4056272506713867,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.055,
+      "step": 32
+    },
+    {
+      "epoch": 0.12738238841978286,
+      "grad_norm": 3.3810365200042725,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.0535,
+      "step": 33
+    },
+    {
+      "epoch": 0.13124246079613994,
+      "grad_norm": 3.5185937881469727,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.0526,
+      "step": 34
+    },
+    {
+      "epoch": 0.13510253317249699,
+      "grad_norm": 3.627316951751709,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.0508,
+      "step": 35
+    },
+    {
+      "epoch": 0.13896260554885403,
+      "grad_norm": 3.6404926776885986,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.0464,
+      "step": 36
+    },
+    {
+      "epoch": 0.1428226779252111,
+      "grad_norm": 3.660294532775879,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.04,
+      "step": 37
+    },
+    {
+      "epoch": 0.14668275030156816,
+      "grad_norm": 3.650830030441284,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.0468,
+      "step": 38
+    },
+    {
+      "epoch": 0.1505428226779252,
+      "grad_norm": 3.3983261585235596,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.0528,
+      "step": 39
+    },
+    {
+      "epoch": 0.15440289505428226,
+      "grad_norm": 3.4742696285247803,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.0479,
+      "step": 40
+    },
+    {
+      "epoch": 0.15826296743063933,
+      "grad_norm": 3.557180166244507,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.0481,
+      "step": 41
+    },
+    {
+      "epoch": 0.16212303980699638,
+      "grad_norm": 3.4408743381500244,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.0475,
+      "step": 42
+    },
+    {
+      "epoch": 0.16598311218335343,
+      "grad_norm": 3.4046168327331543,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.0487,
+      "step": 43
+    },
+    {
+      "epoch": 0.1698431845597105,
+      "grad_norm": 2.9810149669647217,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.0557,
+      "step": 44
+    },
+    {
+      "epoch": 0.17370325693606756,
+      "grad_norm": 3.1998450756073,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.0516,
+      "step": 45
+    },
+    {
+      "epoch": 0.1775633293124246,
+      "grad_norm": 3.363704204559326,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.0471,
+      "step": 46
+    },
+    {
+      "epoch": 0.18142340168878165,
+      "grad_norm": 3.268141746520996,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.0491,
+      "step": 47
+    },
+    {
+      "epoch": 0.18528347406513873,
+      "grad_norm": 3.6082420349121094,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.0462,
+      "step": 48
+    },
+    {
+      "epoch": 0.18914354644149578,
+      "grad_norm": 3.4948015213012695,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.0508,
+      "step": 49
+    },
+    {
+      "epoch": 0.19300361881785283,
+      "grad_norm": 3.8561291694641113,
+      "learning_rate": 0.0,
+      "loss": 11.042,
+      "step": 50
+    },
+    {
+      "epoch": 0.19300361881785283,
+      "eval_loss": 11.050453186035156,
+      "eval_runtime": 1.8118,
+      "eval_samples_per_second": 963.139,
+      "eval_steps_per_second": 120.875,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null