Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0961d537eb7427c8f1e417e5175ee4dc11d05467f723fd9086578082016d0793
+oid sha256:39a4fb2d99f9f8b7a48d48cde1d89402e2a602eb8750284110faf0d7477c4ca8
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8751958d42652c5aa30b5e841e93eba367e400e8682183ef378862deb3b01ea2
+oid sha256:decf5028c95496a6f400685b9e6165621fd1a09ef45bb8658680395fe847effe
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d147a55961380853aafd19601e813425bf2511a50d53eecf241b887530a1f2c
+oid sha256:8ee0ce113dadec09fc3179b257c6cb7ddc4ecf431f50b98e9c283c5f1ff1913f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afbc72c40aaf9ef284ad4a81e970ad13a2b527843a849c7a2979124a739077c
+oid sha256:2100dcac1ecb45cda8fa8795f72d75270620377af9b686c0a476815995552e83
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15a3f418d8e5025ed16a3a38ccdf429ca578c50860821317466567f1cfac1d4
+oid sha256:4adc45e4832b6e6f6474e1197683d1bc5b64a019560ffd321afed9597e6b7f2d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1773b40f8f356310bc60ff5fc488ada75539aa74658ff06d5061c2ed9c0a53b
+oid sha256:76dcb6dce755a1fcf037eb02ec8ed3112a7dbfe486338edc07e216a8fbb0bba0
 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": 2.0682475566864014,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2840909090909091,
+  "best_metric": 2.032545328140259,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5681818181818182,
   "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": 35.332,
       "eval_steps_per_second": 4.469,
       "step": 25
+    },
+    {
+      "epoch": 0.29545454545454547,
+      "grad_norm": 0.7505583167076111,
+      "learning_rate": 5e-05,
+      "loss": 1.6557,
+      "step": 26
+    },
+    {
+      "epoch": 0.3068181818181818,
+      "grad_norm": 0.8248937129974365,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7955,
+      "step": 27
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 0.7818592190742493,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7143,
+      "step": 28
+    },
+    {
+      "epoch": 0.32954545454545453,
+      "grad_norm": 0.9162489771842957,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8803,
+      "step": 29
+    },
+    {
+      "epoch": 0.3409090909090909,
+      "grad_norm": 0.8971193432807922,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8417,
+      "step": 30
+    },
+    {
+      "epoch": 0.3522727272727273,
+      "grad_norm": 0.942955732345581,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0823,
+      "step": 31
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.8796543478965759,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8845,
+      "step": 32
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.9612118601799011,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0512,
+      "step": 33
+    },
+    {
+      "epoch": 0.38636363636363635,
+      "grad_norm": 1.0305103063583374,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1146,
+      "step": 34
+    },
+    {
+      "epoch": 0.3977272727272727,
+      "grad_norm": 1.1519629955291748,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1694,
+      "step": 35
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 1.2092336416244507,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.2877,
+      "step": 36
+    },
+    {
+      "epoch": 0.42045454545454547,
+      "grad_norm": 1.228949785232544,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.4408,
+      "step": 37
+    },
+    {
+      "epoch": 0.4318181818181818,
+      "grad_norm": 0.9068592190742493,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8291,
+      "step": 38
+    },
+    {
+      "epoch": 0.4431818181818182,
+      "grad_norm": 0.9036156535148621,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5543,
+      "step": 39
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.8183141946792603,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6965,
+      "step": 40
+    },
+    {
+      "epoch": 0.4659090909090909,
+      "grad_norm": 0.7449139952659607,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5929,
+      "step": 41
+    },
+    {
+      "epoch": 0.4772727272727273,
+      "grad_norm": 0.9520010948181152,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.0831,
+      "step": 42
+    },
+    {
+      "epoch": 0.48863636363636365,
+      "grad_norm": 0.9523089528083801,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0609,
+      "step": 43
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8622874021530151,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8157,
+      "step": 44
+    },
+    {
+      "epoch": 0.5113636363636364,
+      "grad_norm": 0.9605145454406738,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0216,
+      "step": 45
+    },
+    {
+      "epoch": 0.5227272727272727,
+      "grad_norm": 0.9834564328193665,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0998,
+      "step": 46
+    },
+    {
+      "epoch": 0.5340909090909091,
+      "grad_norm": 0.9851539731025696,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2128,
+      "step": 47
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.0516159534454346,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1404,
+      "step": 48
+    },
+    {
+      "epoch": 0.5568181818181818,
+      "grad_norm": 1.004589319229126,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.2279,
+      "step": 49
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 1.3169046640396118,
+      "learning_rate": 0.0,
+      "loss": 2.3239,
+      "step": 50
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "eval_loss": 2.032545328140259,
+      "eval_runtime": 16.7126,
+      "eval_samples_per_second": 35.482,
+      "eval_steps_per_second": 4.488,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null