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:a5e4611fbcaa59e1d4b0c57eaa46e82e45f409da9cad93a2ecd6de36e3bf7865
+oid sha256:565bec2cbe21b8ffe16d5d07aefe0dba7bf23047d34c84abe7d7e0f1cda65c0c
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f1aada1e60e3137606e938711c4b2305ab70a77d39b7aca07c2c36239b53dc
+oid sha256:61d96277711dd9d59563b9f0a47cbac1eec894a59bf34afecad1f01447512a7b
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922e0eed4c91934f10def57a4c2c5209f95b814881947cf3ef7804f7c838e5cb
+oid sha256:53c68ebad2287c24457dce6f0d69cfaa02d55f8d42014d882e544976090337ac
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1116bb9cd2c1c2b90ab3df015195c2757f366b1b8450e260cc28dd51d0e6ccb6
+oid sha256:74d234cbb08233df61784b41f10cece7b427a5d9d25c6f9c72df693a22becbe2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8551f9255ddbac227acbaab131c3ecfedfa3177310c69e9382328330fc83e8
+oid sha256:d8f0340a1c8d0725e2f253e456c9aebecd0ad2e07f45912306b7f48aaccddd84
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3c6308469473b0b1a227782c89a429e0cce06ed160171ee67b7e107f263bc7
+oid sha256:62cecca05ee62f12b80d7106e619c0c78ab7cb4863ebbca7b7225ebe577f63a8
 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": 1.830102801322937,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02959893443836022,
+  "best_metric": 1.6445624828338623,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05919786887672044,
   "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": 108.094,
       "eval_steps_per_second": 13.526,
       "step": 25
+    },
+    {
+      "epoch": 0.03078289181589463,
+      "grad_norm": 6.333754539489746,
+      "learning_rate": 5e-05,
+      "loss": 1.4631,
+      "step": 26
+    },
+    {
+      "epoch": 0.031966849193429035,
+      "grad_norm": 5.988046646118164,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5457,
+      "step": 27
+    },
+    {
+      "epoch": 0.03315080657096345,
+      "grad_norm": 4.666529178619385,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6051,
+      "step": 28
+    },
+    {
+      "epoch": 0.034334763948497854,
+      "grad_norm": 3.764298915863037,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.5352,
+      "step": 29
+    },
+    {
+      "epoch": 0.03551872132603226,
+      "grad_norm": 2.0698702335357666,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.62,
+      "step": 30
+    },
+    {
+      "epoch": 0.03670267870356667,
+      "grad_norm": 2.650376796722412,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6256,
+      "step": 31
+    },
+    {
+      "epoch": 0.03788663608110108,
+      "grad_norm": 2.5088350772857666,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6179,
+      "step": 32
+    },
+    {
+      "epoch": 0.03907059345863549,
+      "grad_norm": 3.2323107719421387,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.7883,
+      "step": 33
+    },
+    {
+      "epoch": 0.0402545508361699,
+      "grad_norm": 3.3702969551086426,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7842,
+      "step": 34
+    },
+    {
+      "epoch": 0.04143850821370431,
+      "grad_norm": 4.248794078826904,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9471,
+      "step": 35
+    },
+    {
+      "epoch": 0.042622465591238716,
+      "grad_norm": 3.2208549976348877,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8535,
+      "step": 36
+    },
+    {
+      "epoch": 0.04380642296877312,
+      "grad_norm": 5.214898109436035,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0621,
+      "step": 37
+    },
+    {
+      "epoch": 0.044990380346307535,
+      "grad_norm": 3.3143386840820312,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4488,
+      "step": 38
+    },
+    {
+      "epoch": 0.04617433772384194,
+      "grad_norm": 2.913778066635132,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2645,
+      "step": 39
+    },
+    {
+      "epoch": 0.04735829510137635,
+      "grad_norm": 2.4461803436279297,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3157,
+      "step": 40
+    },
+    {
+      "epoch": 0.04854225247891076,
+      "grad_norm": 2.449554681777954,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3519,
+      "step": 41
+    },
+    {
+      "epoch": 0.049726209856445165,
+      "grad_norm": 2.1570582389831543,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4461,
+      "step": 42
+    },
+    {
+      "epoch": 0.05091016723397958,
+      "grad_norm": 2.617800235748291,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.501,
+      "step": 43
+    },
+    {
+      "epoch": 0.052094124611513984,
+      "grad_norm": 2.0715324878692627,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5023,
+      "step": 44
+    },
+    {
+      "epoch": 0.0532780819890484,
+      "grad_norm": 2.4961233139038086,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6375,
+      "step": 45
+    },
+    {
+      "epoch": 0.0544620393665828,
+      "grad_norm": 2.1479310989379883,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6086,
+      "step": 46
+    },
+    {
+      "epoch": 0.05564599674411721,
+      "grad_norm": 2.451838970184326,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7377,
+      "step": 47
+    },
+    {
+      "epoch": 0.05682995412165162,
+      "grad_norm": 3.4158780574798584,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9478,
+      "step": 48
+    },
+    {
+      "epoch": 0.05801391149918603,
+      "grad_norm": 3.3791892528533936,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9543,
+      "step": 49
+    },
+    {
+      "epoch": 0.05919786887672044,
+      "grad_norm": 4.547910213470459,
+      "learning_rate": 0.0,
+      "loss": 2.1126,
+      "step": 50
+    },
+    {
+      "epoch": 0.05919786887672044,
+      "eval_loss": 1.6445624828338623,
+      "eval_runtime": 51.8608,
+      "eval_samples_per_second": 109.717,
+      "eval_steps_per_second": 13.729,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null