Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a11fe295d80c6e2032ae1e67296f0381e3b2ea1d9c51f1c705db34f57e5a62
+oid sha256:2b08d90c0469efc3bb72090b5ae3f8de95481e89df0f0bb945cbe4ae3cb4b100
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9810f38002dc756dd68aa40c3f7800de9771ce64e9d05b13f8d7c79b41426b3b
+oid sha256:37cd209f9c105bb9fcadc91f3135fbb9d2022b3b06247280bb924741f36bf81c
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b53ecd244b9bf8cbd0af1aff959cdda167a6b0bb0867ed3598e335f00a5d579
+oid sha256:3c10641458f0de6e5dc3e858706bf8acb89de8dc3542487a11c55f4fc67ce7f9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d12cb8718b4cc23973c53937c65387c0ee97846968458bc9ba5e38aa9589aefb
+oid sha256:d90b23a53b14e67778f53cc20150cf46eb42a4557f7d8a88f0b12b6a9b3b5066
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fce1a2a09557e484d187b28888d551d5400fc6ab2e2ee35bc703101dddd34b
+oid sha256:36b7f53d31aef85f97263d71f01877b7658548676fdb7a23d6765bdb91a5e237
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44b6ac7df032040ccfc42d6adb84d52c61186529294f2267df9449fb88fbfb6
+oid sha256:71f2876858b326e4ad9f98d2eec47b438aee7a84e9f4fc9cb2ca2ea523ea3157
 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": 4.178318977355957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0733810310034856,
+  "best_metric": 4.028105735778809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1467620620069712,
   "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": 164.711,
       "eval_steps_per_second": 20.589,
       "step": 25
+    },
+    {
+      "epoch": 0.07631627224362503,
+      "grad_norm": 1.2970190048217773,
+      "learning_rate": 5e-05,
+      "loss": 3.3026,
+      "step": 26
+    },
+    {
+      "epoch": 0.07925151348376444,
+      "grad_norm": 2.200300931930542,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.5441,
+      "step": 27
+    },
+    {
+      "epoch": 0.08218675472390387,
+      "grad_norm": 1.8640614748001099,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.6378,
+      "step": 28
+    },
+    {
+      "epoch": 0.0851219959640433,
+      "grad_norm": 1.2264716625213623,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.555,
+      "step": 29
+    },
+    {
+      "epoch": 0.08805723720418272,
+      "grad_norm": 1.5774284601211548,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.8577,
+      "step": 30
+    },
+    {
+      "epoch": 0.09099247844432214,
+      "grad_norm": 1.717018485069275,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.7962,
+      "step": 31
+    },
+    {
+      "epoch": 0.09392771968446156,
+      "grad_norm": 1.5714224576950073,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.9705,
+      "step": 32
+    },
+    {
+      "epoch": 0.09686296092460099,
+      "grad_norm": 1.3049858808517456,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.9805,
+      "step": 33
+    },
+    {
+      "epoch": 0.09979820216474042,
+      "grad_norm": 1.8364142179489136,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.1243,
+      "step": 34
+    },
+    {
+      "epoch": 0.10273344340487983,
+      "grad_norm": 1.8525341749191284,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.049,
+      "step": 35
+    },
+    {
+      "epoch": 0.10566868464501926,
+      "grad_norm": 2.7360332012176514,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.3234,
+      "step": 36
+    },
+    {
+      "epoch": 0.10860392588515869,
+      "grad_norm": 1.7006713151931763,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.5007,
+      "step": 37
+    },
+    {
+      "epoch": 0.11153916712529811,
+      "grad_norm": 3.3105547428131104,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.5437,
+      "step": 38
+    },
+    {
+      "epoch": 0.11447440836543754,
+      "grad_norm": 2.7863497734069824,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.422,
+      "step": 39
+    },
+    {
+      "epoch": 0.11740964960557695,
+      "grad_norm": 3.747509002685547,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.4732,
+      "step": 40
+    },
+    {
+      "epoch": 0.12034489084571638,
+      "grad_norm": 3.606635332107544,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.5158,
+      "step": 41
+    },
+    {
+      "epoch": 0.12328013208585581,
+      "grad_norm": 2.7214155197143555,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.6458,
+      "step": 42
+    },
+    {
+      "epoch": 0.12621537332599522,
+      "grad_norm": 1.4316763877868652,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.667,
+      "step": 43
+    },
+    {
+      "epoch": 0.12915061456613466,
+      "grad_norm": 1.5033129453659058,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.9072,
+      "step": 44
+    },
+    {
+      "epoch": 0.13208585580627408,
+      "grad_norm": 3.340280294418335,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.91,
+      "step": 45
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 1.2967872619628906,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.838,
+      "step": 46
+    },
+    {
+      "epoch": 0.13795633828655293,
+      "grad_norm": 1.9000120162963867,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.0708,
+      "step": 47
+    },
+    {
+      "epoch": 0.14089157952669235,
+      "grad_norm": 1.6708569526672363,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.1453,
+      "step": 48
+    },
+    {
+      "epoch": 0.1438268207668318,
+      "grad_norm": 1.74222993850708,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.2787,
+      "step": 49
+    },
+    {
+      "epoch": 0.1467620620069712,
+      "grad_norm": 2.433371067047119,
+      "learning_rate": 0.0,
+      "loss": 4.2654,
+      "step": 50
+    },
+    {
+      "epoch": 0.1467620620069712,
+      "eval_loss": 4.028105735778809,
+      "eval_runtime": 13.8349,
+      "eval_samples_per_second": 165.957,
+      "eval_steps_per_second": 20.745,
+      "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": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null