Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114982e7520322b7e1259410c48f5a0dc26b96fbbee64930a6aacae1651b0d15
+oid sha256:6faf0c4d2867fb9a719bd6119966085db4b016faae22a8605e7b5848b4b92826
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864fb9dd2b1841992103a4720925807d1de0cc2b2eb152ce9c06356b40367d7b
+oid sha256:d9f417267bc11a109941fda17aa901c349aad0533e3a60ef0b866f08f8e92c17
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9887d5f313c6bd272f9a22b9f203748564a20018b24bc5c48bf2d9187eb287
+oid sha256:309e709ef95b25c4917d454183c06c50d4ae69835cbb1456a83e1c729ec68e3f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870df2f09aa919070a4de9f39c1091709cc0b3867705a6799636d8e177af4a02
+oid sha256:363601c848b3f31e7392d6b609380b70aca43b4400ede713120201efa4b029dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f21d198e8bd2513acc896275679a7780df210029e566ce8b357a34dbba14612
+oid sha256:e36c2957e69dfa1489185501bc4aaad93e50bb29c0417ff605705b27ac747c7f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04cc759f40e0ad37bec37e9651cd7055ddbaec892a5025b2a540f6f77e0b1eb3
+oid sha256:f7911f2f1027a1119a778ee38c06ea276bc5e2aca4d65425e11b08ba0e2967a7
 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": 0.927205502986908,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.35842293906810035,
+  "best_metric": 0.905018150806427,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7168458781362007,
   "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": 83.772,
       "eval_steps_per_second": 10.516,
       "step": 25
+    },
+    {
+      "epoch": 0.3727598566308244,
+      "grad_norm": 0.306890606880188,
+      "learning_rate": 5e-05,
+      "loss": 0.9556,
+      "step": 26
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.32755231857299805,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8453,
+      "step": 27
+    },
+    {
+      "epoch": 0.4014336917562724,
+      "grad_norm": 0.327320396900177,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8859,
+      "step": 28
+    },
+    {
+      "epoch": 0.4157706093189964,
+      "grad_norm": 0.26873916387557983,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8621,
+      "step": 29
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.2484484165906906,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8585,
+      "step": 30
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.2556518614292145,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8101,
+      "step": 31
+    },
+    {
+      "epoch": 0.45878136200716846,
+      "grad_norm": 0.2587701082229614,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8591,
+      "step": 32
+    },
+    {
+      "epoch": 0.4731182795698925,
+      "grad_norm": 0.2929799258708954,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8938,
+      "step": 33
+    },
+    {
+      "epoch": 0.4874551971326165,
+      "grad_norm": 0.32331496477127075,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9321,
+      "step": 34
+    },
+    {
+      "epoch": 0.5017921146953405,
+      "grad_norm": 0.3812984526157379,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9969,
+      "step": 35
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.48057031631469727,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0929,
+      "step": 36
+    },
+    {
+      "epoch": 0.5304659498207885,
+      "grad_norm": 0.5055277943611145,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0387,
+      "step": 37
+    },
+    {
+      "epoch": 0.5448028673835126,
+      "grad_norm": 0.2941000759601593,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9023,
+      "step": 38
+    },
+    {
+      "epoch": 0.5591397849462365,
+      "grad_norm": 0.22578291594982147,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8705,
+      "step": 39
+    },
+    {
+      "epoch": 0.5734767025089605,
+      "grad_norm": 0.2067464292049408,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.82,
+      "step": 40
+    },
+    {
+      "epoch": 0.5878136200716846,
+      "grad_norm": 0.2110137641429901,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8518,
+      "step": 41
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.21045488119125366,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8105,
+      "step": 42
+    },
+    {
+      "epoch": 0.6164874551971327,
+      "grad_norm": 0.2219025194644928,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8502,
+      "step": 43
+    },
+    {
+      "epoch": 0.6308243727598566,
+      "grad_norm": 0.24328501522541046,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8586,
+      "step": 44
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.23979176580905914,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8313,
+      "step": 45
+    },
+    {
+      "epoch": 0.6594982078853047,
+      "grad_norm": 0.27109646797180176,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.902,
+      "step": 46
+    },
+    {
+      "epoch": 0.6738351254480287,
+      "grad_norm": 0.29217034578323364,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9383,
+      "step": 47
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.3429727554321289,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.034,
+      "step": 48
+    },
+    {
+      "epoch": 0.7025089605734767,
+      "grad_norm": 0.4209645688533783,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0656,
+      "step": 49
+    },
+    {
+      "epoch": 0.7168458781362007,
+      "grad_norm": 0.6673789620399475,
+      "learning_rate": 0.0,
+      "loss": 1.2387,
+      "step": 50
+    },
+    {
+      "epoch": 0.7168458781362007,
+      "eval_loss": 0.905018150806427,
+      "eval_runtime": 5.6113,
+      "eval_samples_per_second": 83.76,
+      "eval_steps_per_second": 10.515,
+      "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": 5.337414377668608e+16,
+  "total_flos": 1.067482872849367e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null