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:b2cc154dc4600c55e64b99069e14bf7728045a748dac64fdbf8cdf425a705b47
+oid sha256:8a062851d53f2d31767fbf73e9b0c6146074deaa4251fd1c8eb57e427d21889e
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d1562281073861538c6c99aaffc17e724f2bb4cde5d1d34d1f162ce53fafae
+oid sha256:f2f828b3622da425b28d69d363ae94c3dee935544f2097770305eac2ac8b6c7d
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b7a3ffab6f1c374295de3b8aab90d6f20bcc52ab4822a7fa32871bd40eb10e
+oid sha256:ae5de7b756d94bd60acb5aba97204c630f35e3809d10c3907ea9d696458a1b1c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77ae99de28953145460ddd977eed9bb5d7b3b422cdb6f12cfd722b0bf21762e
+oid sha256:cad40508a083295737642dab2a4a614c84381a4656a4ef5780ee0a0784051305
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1c6fc9236e11bb8a243adc5b4b882061d96d7428f454a12ed6de8cce3bb62a
+oid sha256:ac53b34122a93d5eb5eca0f8a8c6a994e2ac8c33972b0ffb24b994e48b5a8e91
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33a9faa8f66d5c059282d0c453155769a0716d0c741cb7d2024d124502efd6f
+oid sha256:90c3a694e089a57dcfd073ac250c20b80f9e58c18cd364ac2cc63e1c79298d25
 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": 7.096124172210693,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07780587434351294,
+  "best_metric": 5.745617389678955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15561174868702587,
   "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": 43.488,
       "eval_steps_per_second": 5.444,
       "step": 25
+    },
+    {
+      "epoch": 0.08091810931725345,
+      "grad_norm": 36.23772048950195,
+      "learning_rate": 5e-05,
+      "loss": 10.1879,
+      "step": 26
+    },
+    {
+      "epoch": 0.08403034429099397,
+      "grad_norm": 28.252685546875,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 8.9334,
+      "step": 27
+    },
+    {
+      "epoch": 0.08714257926473448,
+      "grad_norm": 21.92393684387207,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 7.6344,
+      "step": 28
+    },
+    {
+      "epoch": 0.090254814238475,
+      "grad_norm": 19.237417221069336,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 7.2,
+      "step": 29
+    },
+    {
+      "epoch": 0.09336704921221552,
+      "grad_norm": 19.00653839111328,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.7892,
+      "step": 30
+    },
+    {
+      "epoch": 0.09647928418595604,
+      "grad_norm": 9.482794761657715,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.8281,
+      "step": 31
+    },
+    {
+      "epoch": 0.09959151915969655,
+      "grad_norm": 7.041558742523193,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.985,
+      "step": 32
+    },
+    {
+      "epoch": 0.10270375413343708,
+      "grad_norm": 7.1093878746032715,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.0649,
+      "step": 33
+    },
+    {
+      "epoch": 0.10581598910717759,
+      "grad_norm": 7.380600929260254,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.0434,
+      "step": 34
+    },
+    {
+      "epoch": 0.10892822408091811,
+      "grad_norm": 11.326904296875,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.7365,
+      "step": 35
+    },
+    {
+      "epoch": 0.11204045905465862,
+      "grad_norm": 67.85647583007812,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 9.864,
+      "step": 36
+    },
+    {
+      "epoch": 0.11515269402839914,
+      "grad_norm": 68.0254135131836,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 9.6725,
+      "step": 37
+    },
+    {
+      "epoch": 0.11826492900213967,
+      "grad_norm": 13.48176383972168,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.5964,
+      "step": 38
+    },
+    {
+      "epoch": 0.12137716397588018,
+      "grad_norm": 14.436902046203613,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.5174,
+      "step": 39
+    },
+    {
+      "epoch": 0.1244893989496207,
+      "grad_norm": 11.990131378173828,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.0007,
+      "step": 40
+    },
+    {
+      "epoch": 0.1276016339233612,
+      "grad_norm": 7.9069085121154785,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 5.5727,
+      "step": 41
+    },
+    {
+      "epoch": 0.13071386889710174,
+      "grad_norm": 7.264441013336182,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.4522,
+      "step": 42
+    },
+    {
+      "epoch": 0.13382610387084226,
+      "grad_norm": 6.674943923950195,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.0556,
+      "step": 43
+    },
+    {
+      "epoch": 0.13693833884458276,
+      "grad_norm": 9.692429542541504,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.0145,
+      "step": 44
+    },
+    {
+      "epoch": 0.14005057381832328,
+      "grad_norm": 9.313735961914062,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.9252,
+      "step": 45
+    },
+    {
+      "epoch": 0.1431628087920638,
+      "grad_norm": 9.679069519042969,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.9762,
+      "step": 46
+    },
+    {
+      "epoch": 0.14627504376580433,
+      "grad_norm": 9.562905311584473,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.1521,
+      "step": 47
+    },
+    {
+      "epoch": 0.14938727873954483,
+      "grad_norm": 15.053668022155762,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.0278,
+      "step": 48
+    },
+    {
+      "epoch": 0.15249951371328535,
+      "grad_norm": 66.99755859375,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 9.3966,
+      "step": 49
+    },
+    {
+      "epoch": 0.15561174868702587,
+      "grad_norm": 68.58241271972656,
+      "learning_rate": 0.0,
+      "loss": 9.256,
+      "step": 50
+    },
+    {
+      "epoch": 0.15561174868702587,
+      "eval_loss": 5.745617389678955,
+      "eval_runtime": 51.0026,
+      "eval_samples_per_second": 42.449,
+      "eval_steps_per_second": 5.313,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null