Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5c5835e15687c093c3f1fb158323d680b4f1c4a25ea75f04a80a5b904e9a7b
+oid sha256:247c345cb2ec56e54ca272b38afc51936898922ff572b1b22cec400d59e5d457
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a589b61ce658d7c34b9254b5683ed0003278b49e52772c109ef7e592554fab73
+oid sha256:52df92aaeb5b81407ed2b9f8681f07d22a69700b9a31338cf90294fc5643aaa9
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34c47eb333704b3847869f21df7b73675d47415b83f3a5c0a7346fde67ac586
+oid sha256:a02bce9736e66f5d30bbf3e76627fa9d1df027ded14eebf6738594a6efd8379b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37c8b3174e20f81cf03ee7a64d3223df39e58383e28f02e7d27684982ccd76c
+oid sha256:7e14d6b6e7f248a6f1185d1bb0aceab636abf269559a04cd62d616ec8f5df7dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba971a1814bd31bf5d580c2f0e4035ae01cb4a2940c1774b3535173e39affa9
+oid sha256:27613f7985ca15bedf09522283eb35c2e2191533dcbeb80901e3aa5e43690bc3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee7932315201a0c23ac7580f4372d0042d34d6e65e0c974f259dcf76d1ed2d3
+oid sha256:40cfb1d738b734633790aa6258c4931bbe4ab9b3313e5dfdd712e4aeced04979
 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": 0.1435670405626297,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02914602156805596,
+  "best_metric": 0.12280955910682678,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05829204313611192,
   "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": 33.032,
       "eval_steps_per_second": 4.133,
       "step": 25
+    },
+    {
+      "epoch": 0.0303118624307782,
+      "grad_norm": 2.517028331756592,
+      "learning_rate": 5e-05,
+      "loss": 0.1762,
+      "step": 26
+    },
+    {
+      "epoch": 0.031477703293500435,
+      "grad_norm": 1.4719444513320923,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1734,
+      "step": 27
+    },
+    {
+      "epoch": 0.03264354415622268,
+      "grad_norm": 4.189019680023193,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1852,
+      "step": 28
+    },
+    {
+      "epoch": 0.03380938501894491,
+      "grad_norm": 2.236452102661133,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1602,
+      "step": 29
+    },
+    {
+      "epoch": 0.034975225881667155,
+      "grad_norm": 1.3396327495574951,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1157,
+      "step": 30
+    },
+    {
+      "epoch": 0.03614106674438939,
+      "grad_norm": 1.026810646057129,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1083,
+      "step": 31
+    },
+    {
+      "epoch": 0.03730690760711163,
+      "grad_norm": 0.5179802775382996,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1017,
+      "step": 32
+    },
+    {
+      "epoch": 0.03847274846983387,
+      "grad_norm": 1.053564429283142,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.12,
+      "step": 33
+    },
+    {
+      "epoch": 0.03963858933255611,
+      "grad_norm": 0.9238091111183167,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1108,
+      "step": 34
+    },
+    {
+      "epoch": 0.040804430195278345,
+      "grad_norm": 0.655486524105072,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1086,
+      "step": 35
+    },
+    {
+      "epoch": 0.04197027105800058,
+      "grad_norm": 1.3844945430755615,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1304,
+      "step": 36
+    },
+    {
+      "epoch": 0.04313611192072282,
+      "grad_norm": 2.077029228210449,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1312,
+      "step": 37
+    },
+    {
+      "epoch": 0.04430195278344506,
+      "grad_norm": 0.49116334319114685,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.114,
+      "step": 38
+    },
+    {
+      "epoch": 0.0454677936461673,
+      "grad_norm": 1.8224717378616333,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1352,
+      "step": 39
+    },
+    {
+      "epoch": 0.046633634508889535,
+      "grad_norm": 0.638178288936615,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1262,
+      "step": 40
+    },
+    {
+      "epoch": 0.04779947537161178,
+      "grad_norm": 0.6785788536071777,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1205,
+      "step": 41
+    },
+    {
+      "epoch": 0.04896531623433401,
+      "grad_norm": 0.6223834753036499,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1145,
+      "step": 42
+    },
+    {
+      "epoch": 0.050131157097056255,
+      "grad_norm": 1.2081153392791748,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1274,
+      "step": 43
+    },
+    {
+      "epoch": 0.05129699795977849,
+      "grad_norm": 1.6178852319717407,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1332,
+      "step": 44
+    },
+    {
+      "epoch": 0.05246283882250073,
+      "grad_norm": 0.6872188448905945,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1384,
+      "step": 45
+    },
+    {
+      "epoch": 0.05362867968522297,
+      "grad_norm": 0.9840008020401001,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1038,
+      "step": 46
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "grad_norm": 1.2670667171478271,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1206,
+      "step": 47
+    },
+    {
+      "epoch": 0.055960361410667445,
+      "grad_norm": 0.6150506734848022,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1007,
+      "step": 48
+    },
+    {
+      "epoch": 0.05712620227338968,
+      "grad_norm": 0.7032421827316284,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1494,
+      "step": 49
+    },
+    {
+      "epoch": 0.05829204313611192,
+      "grad_norm": 0.9980733394622803,
+      "learning_rate": 0.0,
+      "loss": 0.127,
+      "step": 50
+    },
+    {
+      "epoch": 0.05829204313611192,
+      "eval_loss": 0.12280955910682678,
+      "eval_runtime": 175.0073,
+      "eval_samples_per_second": 33.021,
+      "eval_steps_per_second": 4.131,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null