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:bd8f3a80ed434d19f71ef63b655a0a702eab682599d51d42a64e3d5cb56450b4
+oid sha256:bf94750cd0c0bf408cbe10c46315aab488bb5d471f99cdf3400bb42a7b73087a
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7c46190d07043db20766cfe9ea4d29774cceab12306129af0f92d297271c3a
+oid sha256:7239cba61b01784201c509ca665607d4ea8dda38b0c3f3a69b16981ce0731d9a
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8223a609ae13a12d247f9d667d5d977331c58ceac1a04ae3cd30b71eaecaa059
+oid sha256:0b278a568d8239303c507ea36f8ff6721647c467b319a5ccaae7a50567818b66
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f354e20e26a44e4aa025877cbd881827ab6639b70ca924c96bb6f2fff6ebe1
+oid sha256:d91b9e27828db842f5d056ae40e93a4ff90d1bc71ebab0befb0bf3c054ce6ebf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6301dd26f6858c9fb974c381e5b7e2da53729647d76b776967a8cd6c973718
+oid sha256:2f08f9f572c1b34e58bc9326049cc32db2efba940eb21cff41614653a4c4a71b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7041219e2b47020ff6e8ccc5afddf000f0d8b55e3def58cd6066d8477c9c7214
+oid sha256:0542f885252366f4c06c1323a312f113c293ef8abc778b68be93b60a204fd024
 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": 0.8397419452667236,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7092198581560284,
+  "best_metric": 0.7736261487007141,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4184397163120568,
   "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": 107.2,
       "eval_steps_per_second": 13.513,
       "step": 25
+    },
+    {
+      "epoch": 0.7375886524822695,
+      "grad_norm": 0.6546393036842346,
+      "learning_rate": 5e-05,
+      "loss": 0.6403,
+      "step": 26
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.3804154098033905,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0668,
+      "step": 27
+    },
+    {
+      "epoch": 0.7943262411347518,
+      "grad_norm": 0.3659527599811554,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9944,
+      "step": 28
+    },
+    {
+      "epoch": 0.8226950354609929,
+      "grad_norm": 0.30047330260276794,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9064,
+      "step": 29
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.2907089591026306,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8317,
+      "step": 30
+    },
+    {
+      "epoch": 0.8794326241134752,
+      "grad_norm": 0.2471207082271576,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7746,
+      "step": 31
+    },
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 0.2888796329498291,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6717,
+      "step": 32
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.31053251028060913,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6391,
+      "step": 33
+    },
+    {
+      "epoch": 0.9645390070921985,
+      "grad_norm": 0.3765886425971985,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5467,
+      "step": 34
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 0.8381665349006653,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.514,
+      "step": 35
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.6498362421989441,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7386,
+      "step": 36
+    },
+    {
+      "epoch": 1.049645390070922,
+      "grad_norm": 0.4573185443878174,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9685,
+      "step": 37
+    },
+    {
+      "epoch": 1.0780141843971631,
+      "grad_norm": 0.35154661536216736,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8553,
+      "step": 38
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.33329135179519653,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7982,
+      "step": 39
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 0.3315684199333191,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7198,
+      "step": 40
+    },
+    {
+      "epoch": 1.1631205673758864,
+      "grad_norm": 0.3105354309082031,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6575,
+      "step": 41
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.34584712982177734,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6094,
+      "step": 42
+    },
+    {
+      "epoch": 1.2198581560283688,
+      "grad_norm": 0.43531346321105957,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.55,
+      "step": 43
+    },
+    {
+      "epoch": 1.24822695035461,
+      "grad_norm": 0.38908010721206665,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3067,
+      "step": 44
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.6625954508781433,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4526,
+      "step": 45
+    },
+    {
+      "epoch": 1.3049645390070923,
+      "grad_norm": 0.4183286428451538,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9189,
+      "step": 46
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.34246036410331726,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8448,
+      "step": 47
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.3462507426738739,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7784,
+      "step": 48
+    },
+    {
+      "epoch": 1.3900709219858156,
+      "grad_norm": 0.29618310928344727,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7085,
+      "step": 49
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 0.3255789279937744,
+      "learning_rate": 0.0,
+      "loss": 0.6715,
+      "step": 50
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "eval_loss": 0.7736261487007141,
+      "eval_runtime": 2.2187,
+      "eval_samples_per_second": 107.27,
+      "eval_steps_per_second": 13.521,
+      "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