Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805a7c245cbe677abcf52a3706f201bbdb5c0fb2889dd0cb91c54249395aa910
+oid sha256:8b61d59e59bc62133f822faa5513560fc2d5bbd1c543fa1686c27149a609b9f3
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a156fd0f95cfcf1a34d5391cab776e48060ea802b2283aa7297c5744eacd13
+oid sha256:b691596eb252848178e3b8455f6713393e686c9712cebe0133335519db945e0c
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a4c447580ebfd9591468c964e77b49c53109afed0ccd29648bbf09505551ef
+oid sha256:4a994b559f61f641809d0b60499fb53ea1af193228c06c3f3d07adcda656dd26
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be2511b5c3018cbc6a89105e88ee118a7f54d9817b81a6778e90c0ecb3d03ca
+oid sha256:8187299c9072fdeee57bcd60816962cb1a9f5da9f21265b0999be75e187143d2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34656ab58f431c24bd936ca23de0ff4db6a3c37a267e9dedb813c91930c1e8f0
+oid sha256:d415388637050d887ce3b09cbc60ea3ef36c3066220f6f129e1e30cab1d6ab96
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffcb35c7b38cfe8a11a2337009b60f91bbadd5f86de99b36c93bc5b5a81aa490
+oid sha256:5f7af5f2c422e57287c87ffd4dfd7d46610b4cb6e30885521ca58a750a2b1887
 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": 2.515045642852783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.022509848058525603,
+  "best_metric": 2.4847590923309326,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04501969611705121,
   "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": 87.701,
       "eval_steps_per_second": 10.97,
       "step": 25
+    },
+    {
+      "epoch": 0.02341024198086663,
+      "grad_norm": 0.23387306928634644,
+      "learning_rate": 5e-05,
+      "loss": 2.3543,
+      "step": 26
+    },
+    {
+      "epoch": 0.024310635903207655,
+      "grad_norm": 0.2605088949203491,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.5719,
+      "step": 27
+    },
+    {
+      "epoch": 0.025211029825548677,
+      "grad_norm": 0.25959137082099915,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.5124,
+      "step": 28
+    },
+    {
+      "epoch": 0.026111423747889703,
+      "grad_norm": 0.277042955160141,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4706,
+      "step": 29
+    },
+    {
+      "epoch": 0.027011817670230726,
+      "grad_norm": 0.33254826068878174,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4795,
+      "step": 30
+    },
+    {
+      "epoch": 0.02791221159257175,
+      "grad_norm": 0.2666430175304413,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.3948,
+      "step": 31
+    },
+    {
+      "epoch": 0.028812605514912774,
+      "grad_norm": 0.2859417498111725,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3231,
+      "step": 32
+    },
+    {
+      "epoch": 0.0297129994372538,
+      "grad_norm": 0.2585482597351074,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.4618,
+      "step": 33
+    },
+    {
+      "epoch": 0.030613393359594822,
+      "grad_norm": 0.27401846647262573,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4809,
+      "step": 34
+    },
+    {
+      "epoch": 0.031513787281935844,
+      "grad_norm": 0.2689136862754822,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.5238,
+      "step": 35
+    },
+    {
+      "epoch": 0.03241418120427687,
+      "grad_norm": 0.28383877873420715,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.5349,
+      "step": 36
+    },
+    {
+      "epoch": 0.033314575126617896,
+      "grad_norm": 0.3058584928512573,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.5093,
+      "step": 37
+    },
+    {
+      "epoch": 0.03421496904895892,
+      "grad_norm": 0.2748225927352905,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4525,
+      "step": 38
+    },
+    {
+      "epoch": 0.03511536297129994,
+      "grad_norm": 0.2352573424577713,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.4571,
+      "step": 39
+    },
+    {
+      "epoch": 0.03601575689364097,
+      "grad_norm": 0.24772126972675323,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.4815,
+      "step": 40
+    },
+    {
+      "epoch": 0.03691615081598199,
+      "grad_norm": 0.2468077391386032,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.3734,
+      "step": 41
+    },
+    {
+      "epoch": 0.037816544738323014,
+      "grad_norm": 0.25353872776031494,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.4168,
+      "step": 42
+    },
+    {
+      "epoch": 0.038716938660664044,
+      "grad_norm": 0.2523353099822998,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.4197,
+      "step": 43
+    },
+    {
+      "epoch": 0.039617332583005066,
+      "grad_norm": 0.2582724988460541,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.492,
+      "step": 44
+    },
+    {
+      "epoch": 0.04051772650534609,
+      "grad_norm": 0.25668585300445557,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.4805,
+      "step": 45
+    },
+    {
+      "epoch": 0.04141812042768711,
+      "grad_norm": 0.2525278329849243,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.4749,
+      "step": 46
+    },
+    {
+      "epoch": 0.04231851435002814,
+      "grad_norm": 0.2551382780075073,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.4707,
+      "step": 47
+    },
+    {
+      "epoch": 0.04321890827236916,
+      "grad_norm": 0.2634233236312866,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4281,
+      "step": 48
+    },
+    {
+      "epoch": 0.044119302194710185,
+      "grad_norm": 0.25443539023399353,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.434,
+      "step": 49
+    },
+    {
+      "epoch": 0.04501969611705121,
+      "grad_norm": 0.37525126338005066,
+      "learning_rate": 0.0,
+      "loss": 2.6176,
+      "step": 50
+    },
+    {
+      "epoch": 0.04501969611705121,
+      "eval_loss": 2.4847590923309326,
+      "eval_runtime": 85.0851,
+      "eval_samples_per_second": 87.947,
+      "eval_steps_per_second": 11.001,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null