Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9a6e3e4ad5090098f21f47249ef3a7b8e09e7c05702ddcc9662459d9d4e8aa
+oid sha256:62d56da31f466fc206189c66e850346f9c4e5547c58b5775b3e2281fa56f3ce7
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4284a714b8a0dd1f3c01fb21ab89ec704aa18675e5e3e140d6a0b3e762cdcff
+oid sha256:c223aaae009c862bbb488bed6e4b921e58404046047c7c557c863cd531cccb6f
 size 57846868

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea324733835316d7eb5fdc6d5dcc25f511c9b79f4bc5ba941ce777e4d93fdc8
+oid sha256:d4e27d31dea38abf057a4322f1d5da51ce521e5cd659dfcf5a83cb8603030b70
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca38bf555ed0eddd308010dee940e9f09d60d6e9ef341175ebe3cbc1b202bf8
+oid sha256:9c63334c75dda454730d796e2a4bb7670baee13d27d16ea843796d45a2fb0e18
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb264016372de25f148a0a4f222e2649c785e83b280e990d282a2405d2b69f5
+oid sha256:cfa0d0c63bde668f5b67fc96578d094856d25bcb1f4fd34210e7206a07d1bbe2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab25add449e9124160d40492ed6961b93292ee35511d973c12662ef0292f01fe
+oid sha256:2556156160ed09fcac3ae2793b8e151775d4f4145ed77902ba34de7f675ce1aa
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.0032172203063965,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01631787214947171,
+  "best_metric": 3.8318495750427246,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03263574429894342,
   "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": 63.585,
       "eval_steps_per_second": 7.953,
       "step": 25
+    },
+    {
+      "epoch": 0.01697058703545058,
+      "grad_norm": 0.275655061006546,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.0362,
+      "step": 26
+    },
+    {
+      "epoch": 0.017623301921429444,
+      "grad_norm": 0.2766662538051605,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 3.9851,
+      "step": 27
+    },
+    {
+      "epoch": 0.018276016807408313,
+      "grad_norm": 0.28725364804267883,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 3.963,
+      "step": 28
+    },
+    {
+      "epoch": 0.01892873169338718,
+      "grad_norm": 0.29449453949928284,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 3.8857,
+      "step": 29
+    },
+    {
+      "epoch": 0.01958144657936605,
+      "grad_norm": 0.2972124218940735,
+      "learning_rate": 5e-05,
+      "loss": 3.9618,
+      "step": 30
+    },
+    {
+      "epoch": 0.02023416146534492,
+      "grad_norm": 0.28751111030578613,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 3.9089,
+      "step": 31
+    },
+    {
+      "epoch": 0.020886876351323788,
+      "grad_norm": 0.2986813485622406,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.9097,
+      "step": 32
+    },
+    {
+      "epoch": 0.021539591237302657,
+      "grad_norm": 0.29656606912612915,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 3.8916,
+      "step": 33
+    },
+    {
+      "epoch": 0.022192306123281526,
+      "grad_norm": 0.2817177176475525,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.8711,
+      "step": 34
+    },
+    {
+      "epoch": 0.02284502100926039,
+      "grad_norm": 0.26632481813430786,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.8853,
+      "step": 35
+    },
+    {
+      "epoch": 0.02349773589523926,
+      "grad_norm": 0.25886937975883484,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 3.876,
+      "step": 36
+    },
+    {
+      "epoch": 0.02415045078121813,
+      "grad_norm": 0.2591487765312195,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 3.8295,
+      "step": 37
+    },
+    {
+      "epoch": 0.024803165667196998,
+      "grad_norm": 0.2501070201396942,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.8698,
+      "step": 38
+    },
+    {
+      "epoch": 0.025455880553175866,
+      "grad_norm": 0.2335180789232254,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 3.8729,
+      "step": 39
+    },
+    {
+      "epoch": 0.026108595439154735,
+      "grad_norm": 0.23493771255016327,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.8857,
+      "step": 40
+    },
+    {
+      "epoch": 0.026761310325133604,
+      "grad_norm": 0.23735849559307098,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 3.8839,
+      "step": 41
+    },
+    {
+      "epoch": 0.02741402521111247,
+      "grad_norm": 0.2246159315109253,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.8638,
+      "step": 42
+    },
+    {
+      "epoch": 0.028066740097091338,
+      "grad_norm": 0.2345479428768158,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 3.8221,
+      "step": 43
+    },
+    {
+      "epoch": 0.028719454983070207,
+      "grad_norm": 0.22978436946868896,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.8427,
+      "step": 44
+    },
+    {
+      "epoch": 0.029372169869049076,
+      "grad_norm": 0.23703986406326294,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.8245,
+      "step": 45
+    },
+    {
+      "epoch": 0.030024884755027945,
+      "grad_norm": 0.22607843577861786,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.8449,
+      "step": 46
+    },
+    {
+      "epoch": 0.030677599641006813,
+      "grad_norm": 0.23095040023326874,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 3.8575,
+      "step": 47
+    },
+    {
+      "epoch": 0.03133031452698568,
+      "grad_norm": 0.234283447265625,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 3.7832,
+      "step": 48
+    },
+    {
+      "epoch": 0.03198302941296455,
+      "grad_norm": 0.23588110506534576,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 3.816,
+      "step": 49
+    },
+    {
+      "epoch": 0.03263574429894342,
+      "grad_norm": 0.22595348954200745,
+      "learning_rate": 0.0,
+      "loss": 3.8225,
+      "step": 50
+    },
+    {
+      "epoch": 0.03263574429894342,
+      "eval_loss": 3.8318495750427246,
+      "eval_runtime": 162.2542,
+      "eval_samples_per_second": 63.616,
+      "eval_steps_per_second": 7.957,
+      "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": 6.133205889869414e+16,
+  "total_flos": 1.2246627254481715e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null