Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5bfc425d628aeedeaba3b1f246609ada1d667fe2ff39440f1689bb0b8dcf39
+oid sha256:3d32d29412725114f71ae5218e85b4a8ff9c9b5a2ac8fbb50873886397b59116
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7079e9fdd614c34a3e440287d71b3227b2efbbde85a6963290395ca1d434496
+oid sha256:2c63c2b7e48dd6aab23855d48a52f4bd7b969e8b1c330a8c2519c1ea9963f236
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6fb20f8ce76c8c9a94814400d5f9e694543bf7a8ba9dc49c9bbde7faf619d00
+oid sha256:a02d9bd7f81ea31cb8875d6be0aa7b128fd0963ff9683f63dabd7dfeb0faa6cf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3541dfa4721441482c1f4689d12581e75bd97bd8e906fef1480711dcbecf4d
+oid sha256:6c641e3de29cf6ef35a644df4f9a8504df99ebaa6ec0efd391aaff19451c768b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b24722e2287706be32cec1dd805c280b9230ed765f8ebfbdb02a3459fe4d01
+oid sha256:8e9d0628bfc69c962337ed4054fb70e066c6602d9d1a7db5fa395d9a32c7d3a6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5423eef95874d9199c04b853cd7b6313b826a681fcfb0fc9938550d6adbab1e
+oid sha256:35f25f640291efb9c3bf4ba84081ac877e79da10ba255daa77628f9652969335
 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": 0.9326862692832947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.021015025743406537,
+  "best_metric": 0.8844071626663208,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.042030051486813075,
   "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": 24.404,
       "eval_steps_per_second": 3.051,
       "step": 25
+    },
+    {
+      "epoch": 0.021855626773142796,
+      "grad_norm": 21.628856658935547,
+      "learning_rate": 5e-05,
+      "loss": 0.9625,
+      "step": 26
+    },
+    {
+      "epoch": 0.022696227802879058,
+      "grad_norm": 19.372676849365234,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9493,
+      "step": 27
+    },
+    {
+      "epoch": 0.02353682883261532,
+      "grad_norm": 15.937079429626465,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9098,
+      "step": 28
+    },
+    {
+      "epoch": 0.02437742986235158,
+      "grad_norm": 14.250678062438965,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8953,
+      "step": 29
+    },
+    {
+      "epoch": 0.025218030892087843,
+      "grad_norm": 12.575410842895508,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8521,
+      "step": 30
+    },
+    {
+      "epoch": 0.026058631921824105,
+      "grad_norm": 12.10473918914795,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8513,
+      "step": 31
+    },
+    {
+      "epoch": 0.026899232951560367,
+      "grad_norm": 12.294198989868164,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8321,
+      "step": 32
+    },
+    {
+      "epoch": 0.027739833981296626,
+      "grad_norm": 14.769253730773926,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8647,
+      "step": 33
+    },
+    {
+      "epoch": 0.028580435011032888,
+      "grad_norm": 14.944522857666016,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8401,
+      "step": 34
+    },
+    {
+      "epoch": 0.02942103604076915,
+      "grad_norm": 17.539342880249023,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8871,
+      "step": 35
+    },
+    {
+      "epoch": 0.03026163707050541,
+      "grad_norm": 24.73512840270996,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9443,
+      "step": 36
+    },
+    {
+      "epoch": 0.031102238100241673,
+      "grad_norm": 38.59557342529297,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0182,
+      "step": 37
+    },
+    {
+      "epoch": 0.03194283912997793,
+      "grad_norm": 41.428646087646484,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0888,
+      "step": 38
+    },
+    {
+      "epoch": 0.0327834401597142,
+      "grad_norm": 12.97634506225586,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.871,
+      "step": 39
+    },
+    {
+      "epoch": 0.033624041189450456,
+      "grad_norm": 12.2452392578125,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8759,
+      "step": 40
+    },
+    {
+      "epoch": 0.03446464221918672,
+      "grad_norm": 12.03636360168457,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8499,
+      "step": 41
+    },
+    {
+      "epoch": 0.03530524324892298,
+      "grad_norm": 11.152754783630371,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.795,
+      "step": 42
+    },
+    {
+      "epoch": 0.03614584427865924,
+      "grad_norm": 11.173242568969727,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8306,
+      "step": 43
+    },
+    {
+      "epoch": 0.0369864453083955,
+      "grad_norm": 11.396944046020508,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8435,
+      "step": 44
+    },
+    {
+      "epoch": 0.03782704633813176,
+      "grad_norm": 11.597098350524902,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8474,
+      "step": 45
+    },
+    {
+      "epoch": 0.03866764736786803,
+      "grad_norm": 12.91210651397705,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8523,
+      "step": 46
+    },
+    {
+      "epoch": 0.039508248397604286,
+      "grad_norm": 14.450052261352539,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8953,
+      "step": 47
+    },
+    {
+      "epoch": 0.04034884942734055,
+      "grad_norm": 19.216999053955078,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9383,
+      "step": 48
+    },
+    {
+      "epoch": 0.04118945045707681,
+      "grad_norm": 28.695844650268555,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8173,
+      "step": 49
+    },
+    {
+      "epoch": 0.042030051486813075,
+      "grad_norm": 49.96198654174805,
+      "learning_rate": 0.0,
+      "loss": 1.1398,
+      "step": 50
+    },
+    {
+      "epoch": 0.042030051486813075,
+      "eval_loss": 0.8844071626663208,
+      "eval_runtime": 328.3779,
+      "eval_samples_per_second": 24.408,
+      "eval_steps_per_second": 3.051,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null