Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5156d70457364bf1de0774f94ce7be68573e1c5f73785730c81a104b9a5915
+oid sha256:ad4c351095efc763de5a21747bf62cbe0fd10f36e21ad5f239238a488b9485fe
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9270d8f96ecfbda7ced91a746c93552ee2376c5f66bbf92da3f869c234db9248
+oid sha256:0302fac5fb3b1855ffedfc679675174c9c3ba5169158ac94da5f9292affc7781
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1706cc5ec3016c3b9b68410fb652316f2824e559c4a65895b660d1a2a38ee538
+oid sha256:1257fc545b76da164fb4de636e5bbb6d32dc80325123d56ba7681738bf8f417e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf4bd185507b7543363c1969c0065f55690822a416eb4f15640e2843930b900
+oid sha256:49a2711f9e2cf2677c3f885ac8614d8dbdfa0e386d7573cfe99c2b86a3ddb411
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ecd66fefcd73b531c5078c727bb5161827076d3a44b8e78dc30e4b7a83708a
+oid sha256:236b6dade338c1f8a0fff860025ac8a471e3b1309d26cb2a6bd7107bbc250f9a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf1f23342b8930edbc880aab08b08c9f8a66125cc3cbe4de3a33330d0c62ebf
+oid sha256:b6af79a72f09ec9c98ab2904386d686432e87b993071ce4f3d07ccaee2581725
 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": 2.317429780960083,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06586530545035403,
+  "best_metric": 2.279601573944092,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13173061090070806,
   "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": 30.341,
       "eval_steps_per_second": 3.797,
       "step": 25
+    },
+    {
+      "epoch": 0.06849991766836819,
+      "grad_norm": 1.438060998916626,
+      "learning_rate": 5e-05,
+      "loss": 2.4561,
+      "step": 26
+    },
+    {
+      "epoch": 0.07113452988638234,
+      "grad_norm": 1.4393006563186646,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.4412,
+      "step": 27
+    },
+    {
+      "epoch": 0.07376914210439652,
+      "grad_norm": 1.3842298984527588,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.4253,
+      "step": 28
+    },
+    {
+      "epoch": 0.07640375432241067,
+      "grad_norm": 1.2816487550735474,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3898,
+      "step": 29
+    },
+    {
+      "epoch": 0.07903836654042483,
+      "grad_norm": 1.2254124879837036,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.3172,
+      "step": 30
+    },
+    {
+      "epoch": 0.08167297875843899,
+      "grad_norm": 1.1389992237091064,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.2249,
+      "step": 31
+    },
+    {
+      "epoch": 0.08430759097645316,
+      "grad_norm": 1.2742527723312378,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.2767,
+      "step": 32
+    },
+    {
+      "epoch": 0.08694220319446731,
+      "grad_norm": 1.1469522714614868,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.341,
+      "step": 33
+    },
+    {
+      "epoch": 0.08957681541248147,
+      "grad_norm": 1.3233062028884888,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3118,
+      "step": 34
+    },
+    {
+      "epoch": 0.09221142763049564,
+      "grad_norm": 1.3203026056289673,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2315,
+      "step": 35
+    },
+    {
+      "epoch": 0.0948460398485098,
+      "grad_norm": 1.3014671802520752,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.2017,
+      "step": 36
+    },
+    {
+      "epoch": 0.09748065206652395,
+      "grad_norm": 1.498002529144287,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.1095,
+      "step": 37
+    },
+    {
+      "epoch": 0.10011526428453812,
+      "grad_norm": 1.0392613410949707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4473,
+      "step": 38
+    },
+    {
+      "epoch": 0.10274987650255228,
+      "grad_norm": 0.9770948886871338,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.3847,
+      "step": 39
+    },
+    {
+      "epoch": 0.10538448872056644,
+      "grad_norm": 1.0258359909057617,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.4703,
+      "step": 40
+    },
+    {
+      "epoch": 0.10801910093858061,
+      "grad_norm": 1.0511903762817383,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.399,
+      "step": 41
+    },
+    {
+      "epoch": 0.11065371315659477,
+      "grad_norm": 1.0126500129699707,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3849,
+      "step": 42
+    },
+    {
+      "epoch": 0.11328832537460892,
+      "grad_norm": 1.061611294746399,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3324,
+      "step": 43
+    },
+    {
+      "epoch": 0.11592293759262308,
+      "grad_norm": 1.1187413930892944,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3951,
+      "step": 44
+    },
+    {
+      "epoch": 0.11855754981063725,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.1854,
+      "step": 45
+    },
+    {
+      "epoch": 0.1211921620286514,
+      "grad_norm": 1.1284306049346924,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.2851,
+      "step": 46
+    },
+    {
+      "epoch": 0.12382677424666556,
+      "grad_norm": 1.0848690271377563,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1642,
+      "step": 47
+    },
+    {
+      "epoch": 0.12646138646467972,
+      "grad_norm": 1.2179816961288452,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.2824,
+      "step": 48
+    },
+    {
+      "epoch": 0.1290959986826939,
+      "grad_norm": 1.3205076456069946,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1305,
+      "step": 49
+    },
+    {
+      "epoch": 0.13173061090070806,
+      "grad_norm": 1.5582979917526245,
+      "learning_rate": 0.0,
+      "loss": 2.0369,
+      "step": 50
+    },
+    {
+      "epoch": 0.13173061090070806,
+      "eval_loss": 2.279601573944092,
+      "eval_runtime": 84.3886,
+      "eval_samples_per_second": 30.3,
+      "eval_steps_per_second": 3.792,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null