Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a55fd58b2eb8a98049a7550b4f85a8593b6bfeb7b7003945b2f25a786e44e33
+oid sha256:067f64e15593a2961a4d17f198ff828708744b8af88af13f4a1d9f919a868724
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f95c7e3ac82e785ec8242452e95805a0937b05d13d981706cc0a297abfd5bd6
+oid sha256:5b222e89395a41214dd401fdae535410e4dbdcc575212566de651b068593e82d
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1441b54bbe8ce74c1460442291368305f530b7549e7948458db90e6aac7ae1
+oid sha256:36e273cd7cb614fab1e4ba5cb090395cc97e29a5b211a3c43243d443a4a78fd2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e644235097a5078ccd19fb9c9be55e08f1556894cd6be945676ab3b30c6fccd0
+oid sha256:82f9fea93f02dea3ce6ea7e100947afa7cc80296c5bf01e46b633de369b8a0b1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e37cf7420639b2ad9f632cdfda833522aba64c6684d5eeb899459f193689ca5
+oid sha256:b70fccf0aabcbb7a72ea69b7c066f959922e72e6624b3024f6ea8c47bef2ae16
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc452d168de5511e1ea01cfb2077d204f819498ecb62576b0796cda162f5fef4
+oid sha256:47a7b46e3ba63cc9633af823af842f52129717b5233cc859e251d3e9dfb4a8ad
 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": 11.027515411376953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22573363431151242,
+  "best_metric": 11.009994506835938,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45146726862302483,
   "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": 916.41,
       "eval_steps_per_second": 115.473,
       "step": 25
+    },
+    {
+      "epoch": 0.23476297968397292,
+      "grad_norm": 3.8216607570648193,
+      "learning_rate": 5e-05,
+      "loss": 11.0528,
+      "step": 26
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 4.446141242980957,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.0429,
+      "step": 27
+    },
+    {
+      "epoch": 0.2528216704288939,
+      "grad_norm": 4.9208245277404785,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.0356,
+      "step": 28
+    },
+    {
+      "epoch": 0.2618510158013544,
+      "grad_norm": 4.09058141708374,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.0414,
+      "step": 29
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 4.733359336853027,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.0324,
+      "step": 30
+    },
+    {
+      "epoch": 0.2799097065462754,
+      "grad_norm": 4.318568706512451,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.0351,
+      "step": 31
+    },
+    {
+      "epoch": 0.28893905191873587,
+      "grad_norm": 4.726495742797852,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.0296,
+      "step": 32
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 5.066720962524414,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.0244,
+      "step": 33
+    },
+    {
+      "epoch": 0.30699774266365687,
+      "grad_norm": 5.5661749839782715,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.0142,
+      "step": 34
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 6.597118854522705,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 8.559455871582031,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.9691,
+      "step": 36
+    },
+    {
+      "epoch": 0.3340857787810384,
+      "grad_norm": 9.815827369689941,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.9537,
+      "step": 37
+    },
+    {
+      "epoch": 0.3431151241534989,
+      "grad_norm": 7.0843892097473145,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.9942,
+      "step": 38
+    },
+    {
+      "epoch": 0.35214446952595935,
+      "grad_norm": 3.887183904647827,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.0425,
+      "step": 39
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 4.052178859710693,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.0384,
+      "step": 40
+    },
+    {
+      "epoch": 0.37020316027088035,
+      "grad_norm": 4.703183650970459,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.0254,
+      "step": 41
+    },
+    {
+      "epoch": 0.3792325056433409,
+      "grad_norm": 4.300675868988037,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.0295,
+      "step": 42
+    },
+    {
+      "epoch": 0.38826185101580135,
+      "grad_norm": 4.41107702255249,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.0304,
+      "step": 43
+    },
+    {
+      "epoch": 0.3972911963882618,
+      "grad_norm": 4.380729675292969,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.0285,
+      "step": 44
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 4.796936988830566,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.0226,
+      "step": 45
+    },
+    {
+      "epoch": 0.4153498871331828,
+      "grad_norm": 5.204959392547607,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.0148,
+      "step": 46
+    },
+    {
+      "epoch": 0.42437923250564336,
+      "grad_norm": 6.0904412269592285,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.0041,
+      "step": 47
+    },
+    {
+      "epoch": 0.43340857787810383,
+      "grad_norm": 6.825149059295654,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.9894,
+      "step": 48
+    },
+    {
+      "epoch": 0.44243792325056436,
+      "grad_norm": 8.704109191894531,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.9616,
+      "step": 49
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 10.714920043945312,
+      "learning_rate": 0.0,
+      "loss": 10.9407,
+      "step": 50
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 11.009994506835938,
+      "eval_runtime": 0.8089,
+      "eval_samples_per_second": 922.276,
+      "eval_steps_per_second": 116.212,
+      "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": 2107913011200.0,
+  "total_flos": 4214512680960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null