Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f30799c929d73c88e5385de347e427be41864f294aabc6b4e7d49a4974d7a18
+oid sha256:f2cc780126a23cfffcb3433f22b11831dbea1b2c545713591696f6f897100a63
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c03e231d64e1758e13007860f6ba535d9e4939b10ff2be2fccd1e772dd543b
+oid sha256:34fdbb832217be145544cd57e43f8bf1275f47821d8e912674c14af27e2b50ba
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc08f0591ebe2c0c34622f1bba2cc3232ee40a64193ba8f13122df2aa99b1f5
+oid sha256:56b7d15204222a7f53f3d9e823a34367ab13d60f2cb777451adafc490fad3ce4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c7046d926629a44b7015663fe1cf1e6deb6f88dad06ecc83a5283f446538de
+oid sha256:d60b1db8a7fb3d9c6e9b63ab565fcdc0e2f1840721f2259321aa2124fab512b7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42e948ebe9ce94ab6a1adfe26f9c1bbf057139b459a51df6399909ae08162c6
+oid sha256:b487b9ec88ea7dd6810873193ca6b06f268f2cf5ec10a536de84ac9f4639af08
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a0cb7604730c96cf6ee5083fac39d62b26b4a8c063e764417788b756746d91
+oid sha256:7aa5699fdd63b420b4a333ecb0b409ff102493d63d0413ea15a5b17cb6f83b2b
 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": 2.641629695892334,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06912044237083118,
+  "best_metric": 2.598724126815796,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13824088474166235,
   "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": 145.46,
       "eval_steps_per_second": 18.205,
       "step": 25
+    },
+    {
+      "epoch": 0.07188526006566442,
+      "grad_norm": 0.5620300769805908,
+      "learning_rate": 5e-05,
+      "loss": 2.5575,
+      "step": 26
+    },
+    {
+      "epoch": 0.07465007776049767,
+      "grad_norm": 0.6803304553031921,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.6463,
+      "step": 27
+    },
+    {
+      "epoch": 0.07741489545533091,
+      "grad_norm": 0.8547685146331787,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.6041,
+      "step": 28
+    },
+    {
+      "epoch": 0.08017971315016416,
+      "grad_norm": 0.718602180480957,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.5597,
+      "step": 29
+    },
+    {
+      "epoch": 0.08294453084499741,
+      "grad_norm": 0.6359795331954956,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.5481,
+      "step": 30
+    },
+    {
+      "epoch": 0.08570934853983066,
+      "grad_norm": 0.7042436599731445,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.5978,
+      "step": 31
+    },
+    {
+      "epoch": 0.0884741662346639,
+      "grad_norm": 0.6024742722511292,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.5476,
+      "step": 32
+    },
+    {
+      "epoch": 0.09123898392949716,
+      "grad_norm": 0.7030935883522034,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.5704,
+      "step": 33
+    },
+    {
+      "epoch": 0.09400380162433039,
+      "grad_norm": 0.7609543800354004,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.6509,
+      "step": 34
+    },
+    {
+      "epoch": 0.09676861931916364,
+      "grad_norm": 1.006309151649475,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.5651,
+      "step": 35
+    },
+    {
+      "epoch": 0.09953343701399689,
+      "grad_norm": 1.313661813735962,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.6464,
+      "step": 36
+    },
+    {
+      "epoch": 0.10229825470883014,
+      "grad_norm": 2.0305123329162598,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.6647,
+      "step": 37
+    },
+    {
+      "epoch": 0.10506307240366339,
+      "grad_norm": 0.48308926820755005,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4811,
+      "step": 38
+    },
+    {
+      "epoch": 0.10782789009849664,
+      "grad_norm": 0.47622811794281006,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.6301,
+      "step": 39
+    },
+    {
+      "epoch": 0.11059270779332987,
+      "grad_norm": 0.5079199075698853,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.6056,
+      "step": 40
+    },
+    {
+      "epoch": 0.11335752548816312,
+      "grad_norm": 0.5400040149688721,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.561,
+      "step": 41
+    },
+    {
+      "epoch": 0.11612234318299637,
+      "grad_norm": 0.5759101510047913,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.5636,
+      "step": 42
+    },
+    {
+      "epoch": 0.11888716087782962,
+      "grad_norm": 0.5764763951301575,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.5641,
+      "step": 43
+    },
+    {
+      "epoch": 0.12165197857266287,
+      "grad_norm": 0.6086241006851196,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.5616,
+      "step": 44
+    },
+    {
+      "epoch": 0.12441679626749612,
+      "grad_norm": 0.6851764917373657,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.5202,
+      "step": 45
+    },
+    {
+      "epoch": 0.12718161396232935,
+      "grad_norm": 0.7342571020126343,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.6312,
+      "step": 46
+    },
+    {
+      "epoch": 0.1299464316571626,
+      "grad_norm": 0.8653113842010498,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.6744,
+      "step": 47
+    },
+    {
+      "epoch": 0.13271124935199585,
+      "grad_norm": 1.0654218196868896,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.5864,
+      "step": 48
+    },
+    {
+      "epoch": 0.1354760670468291,
+      "grad_norm": 1.6293843984603882,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.5471,
+      "step": 49
+    },
+    {
+      "epoch": 0.13824088474166235,
+      "grad_norm": 3.1217777729034424,
+      "learning_rate": 0.0,
+      "loss": 2.6951,
+      "step": 50
+    },
+    {
+      "epoch": 0.13824088474166235,
+      "eval_loss": 2.598724126815796,
+      "eval_runtime": 16.7383,
+      "eval_samples_per_second": 145.594,
+      "eval_steps_per_second": 18.222,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null