Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789802eba1416c3d9f72c1e5814ce15a38a6ecad0c6dc6300a9556572c92fed3
+oid sha256:f6aaed359345c6649203220da9e1ebc386741a4677b52f8e444edcbc311423fe
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10aca25c468d495bfc87a3ae2e651ac715e62af19eb7ccf46a1c0bed07c03d4a
+oid sha256:eb9e75b740920df5f4586b27ac5ddac1733f8b2e0588ad1e87fdd3c96fdaf546
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b7767334f0c1085143bb89840f779d1835a57078016d418c1d3b5677d3b144
+oid sha256:ec67d432652fbab0e8aa9372c876453dc1d545373fa4c40337123860b00bc980
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572b8c49f23908be2c7054bf9e2d2122e1b80740de8f042ba9bc666597d74d96
+oid sha256:36e7150b0bee10c27bc0e3f6980108a425af2d0719595fa22f6d3f0700abad33
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3452efb1f6f6baa93aaa3e753a62dd7206d57342126d4903c36bd7b7954e8b8
+oid sha256:b2e77f8580a8dc7375a7905a92cbb5318f277372be5d6c38862c8d74afbb41f6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb3a46778d47ba9153997bde4ba6c26f35b73f21edbc574fddd2920e53a6fe1
+oid sha256:0c1aa5570b1d0fc680dab15bd29e0b641c5cf2523df266792023162582c61b26
 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": 11.845855712890625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09334889148191365,
+  "best_metric": 11.816559791564941,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1866977829638273,
   "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": 231.756,
       "eval_steps_per_second": 29.018,
       "step": 25
+    },
+    {
+      "epoch": 0.0970828471411902,
+      "grad_norm": 2.9534995555877686,
+      "learning_rate": 5e-05,
+      "loss": 11.8459,
+      "step": 26
+    },
+    {
+      "epoch": 0.10081680280046675,
+      "grad_norm": 2.955491781234741,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.8433,
+      "step": 27
+    },
+    {
+      "epoch": 0.10455075845974329,
+      "grad_norm": 2.891913890838623,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.841,
+      "step": 28
+    },
+    {
+      "epoch": 0.10828471411901984,
+      "grad_norm": 2.914942502975464,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.8363,
+      "step": 29
+    },
+    {
+      "epoch": 0.11201866977829639,
+      "grad_norm": 2.8910973072052,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.8331,
+      "step": 30
+    },
+    {
+      "epoch": 0.11575262543757293,
+      "grad_norm": 2.835066318511963,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.8321,
+      "step": 31
+    },
+    {
+      "epoch": 0.11948658109684948,
+      "grad_norm": 2.7818522453308105,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.8309,
+      "step": 32
+    },
+    {
+      "epoch": 0.12322053675612601,
+      "grad_norm": 2.7701222896575928,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.8288,
+      "step": 33
+    },
+    {
+      "epoch": 0.12695449241540258,
+      "grad_norm": 2.7583718299865723,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.8265,
+      "step": 34
+    },
+    {
+      "epoch": 0.1306884480746791,
+      "grad_norm": 2.7240748405456543,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.8255,
+      "step": 35
+    },
+    {
+      "epoch": 0.13442240373395567,
+      "grad_norm": 2.7345070838928223,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.8233,
+      "step": 36
+    },
+    {
+      "epoch": 0.1381563593932322,
+      "grad_norm": 2.70548152923584,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.823,
+      "step": 37
+    },
+    {
+      "epoch": 0.14189031505250876,
+      "grad_norm": 2.6903340816497803,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.8199,
+      "step": 38
+    },
+    {
+      "epoch": 0.1456242707117853,
+      "grad_norm": 2.6467480659484863,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.821,
+      "step": 39
+    },
+    {
+      "epoch": 0.14935822637106183,
+      "grad_norm": 2.666109085083008,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.8185,
+      "step": 40
+    },
+    {
+      "epoch": 0.1530921820303384,
+      "grad_norm": 2.642460584640503,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.8179,
+      "step": 41
+    },
+    {
+      "epoch": 0.15682613768961493,
+      "grad_norm": 2.6411454677581787,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.818,
+      "step": 42
+    },
+    {
+      "epoch": 0.16056009334889149,
+      "grad_norm": 2.620548725128174,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.8159,
+      "step": 43
+    },
+    {
+      "epoch": 0.16429404900816802,
+      "grad_norm": 2.590919017791748,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.8172,
+      "step": 44
+    },
+    {
+      "epoch": 0.16802800466744458,
+      "grad_norm": 2.6139168739318848,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.8185,
+      "step": 45
+    },
+    {
+      "epoch": 0.1717619603267211,
+      "grad_norm": 2.604081153869629,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.8167,
+      "step": 46
+    },
+    {
+      "epoch": 0.17549591598599767,
+      "grad_norm": 2.6263182163238525,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.8167,
+      "step": 47
+    },
+    {
+      "epoch": 0.1792298716452742,
+      "grad_norm": 2.586052656173706,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.819,
+      "step": 48
+    },
+    {
+      "epoch": 0.18296382730455077,
+      "grad_norm": 2.631632089614868,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.8153,
+      "step": 49
+    },
+    {
+      "epoch": 0.1866977829638273,
+      "grad_norm": 2.6062960624694824,
+      "learning_rate": 0.0,
+      "loss": 11.8145,
+      "step": 50
+    },
+    {
+      "epoch": 0.1866977829638273,
+      "eval_loss": 11.816559791564941,
+      "eval_runtime": 7.6632,
+      "eval_samples_per_second": 235.54,
+      "eval_steps_per_second": 29.491,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null