Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bed8c35653b5058f6d4d0fb2704812f367f37e86c6bc896d2f993ff1470f38
+oid sha256:38a2dcc02febb35ce5c5c212b0d446c40a00e21fa587e32a6323769e0b348010
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd6c4829cc85db423ddaf9ae790dd9e01d407a9e595be1e85fb2076261d7b951
+oid sha256:023e70043eaf4c0f307914aa20a360129fd783623f046db4caf59bf75113b208
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144f14b73cadb1a1e1b12b5f3d0b34c1b073825b85980c8c5df4bec52f3da28f
+oid sha256:75ce695cdbfeb36138c27972719f35eb4a78d8f6b44cacd8496580b241a120c6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5750b671c6410f7b4588858be4d9051c9b1a660d136ca3af1b2f1fff2a46b32f
+oid sha256:4b1264053fb20abee3cc5e9b659e3f2220ac03b2f5be72e43012245eca2c0178
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4c340a91055b7443958d417701993f5045e29fb1b48979385643bf48d1774c
+oid sha256:eb47e8039890bb732c5e3274dc420c0ea1a6b1f8a5668fae9260f97e8ae99340
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e4fefe5205ff0d5f881ef8913363ad672e58d1ad830827b850588ec07c32ec
+oid sha256:1c79922e86753d674408ea73c0893d14b71ec76753bd5967589be11b03a9a441
 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": 0.5292229652404785,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5730659025787965,
+  "best_metric": 0.4871082007884979,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.146131805157593,
   "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": 113.121,
       "eval_steps_per_second": 14.236,
       "step": 25
+    },
+    {
+      "epoch": 0.5959885386819485,
+      "grad_norm": 2.372102975845337,
+      "learning_rate": 5e-05,
+      "loss": 0.5179,
+      "step": 26
+    },
+    {
+      "epoch": 0.6189111747851003,
+      "grad_norm": 1.839175820350647,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.443,
+      "step": 27
+    },
+    {
+      "epoch": 0.6418338108882522,
+      "grad_norm": 2.125877857208252,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5021,
+      "step": 28
+    },
+    {
+      "epoch": 0.664756446991404,
+      "grad_norm": 1.3504488468170166,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4931,
+      "step": 29
+    },
+    {
+      "epoch": 0.6876790830945558,
+      "grad_norm": 2.0473389625549316,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5186,
+      "step": 30
+    },
+    {
+      "epoch": 0.7106017191977078,
+      "grad_norm": 3.015089273452759,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5055,
+      "step": 31
+    },
+    {
+      "epoch": 0.7335243553008596,
+      "grad_norm": 3.7230453491210938,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5307,
+      "step": 32
+    },
+    {
+      "epoch": 0.7564469914040115,
+      "grad_norm": 3.5798141956329346,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9552,
+      "step": 33
+    },
+    {
+      "epoch": 0.7793696275071633,
+      "grad_norm": 3.0358645915985107,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.673,
+      "step": 34
+    },
+    {
+      "epoch": 0.8022922636103151,
+      "grad_norm": 3.3272151947021484,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5957,
+      "step": 35
+    },
+    {
+      "epoch": 0.8252148997134671,
+      "grad_norm": 1.9087271690368652,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4367,
+      "step": 36
+    },
+    {
+      "epoch": 0.8481375358166189,
+      "grad_norm": 1.8877273797988892,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4389,
+      "step": 37
+    },
+    {
+      "epoch": 0.8710601719197708,
+      "grad_norm": 1.7177760601043701,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4901,
+      "step": 38
+    },
+    {
+      "epoch": 0.8939828080229226,
+      "grad_norm": 1.89617121219635,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4447,
+      "step": 39
+    },
+    {
+      "epoch": 0.9169054441260746,
+      "grad_norm": 1.4989944696426392,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5251,
+      "step": 40
+    },
+    {
+      "epoch": 0.9398280802292264,
+      "grad_norm": 1.7579575777053833,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4943,
+      "step": 41
+    },
+    {
+      "epoch": 0.9627507163323782,
+      "grad_norm": 1.385714054107666,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.53,
+      "step": 42
+    },
+    {
+      "epoch": 0.9856733524355301,
+      "grad_norm": 1.1276830434799194,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4551,
+      "step": 43
+    },
+    {
+      "epoch": 1.008595988538682,
+      "grad_norm": 4.495203495025635,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1086,
+      "step": 44
+    },
+    {
+      "epoch": 1.0315186246418337,
+      "grad_norm": 1.7150007486343384,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6485,
+      "step": 45
+    },
+    {
+      "epoch": 1.0544412607449858,
+      "grad_norm": 0.8887443542480469,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4886,
+      "step": 46
+    },
+    {
+      "epoch": 1.0773638968481376,
+      "grad_norm": 1.4859352111816406,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4817,
+      "step": 47
+    },
+    {
+      "epoch": 1.1002865329512894,
+      "grad_norm": 1.5945063829421997,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4495,
+      "step": 48
+    },
+    {
+      "epoch": 1.1232091690544412,
+      "grad_norm": 1.5430727005004883,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4143,
+      "step": 49
+    },
+    {
+      "epoch": 1.146131805157593,
+      "grad_norm": 2.9990031719207764,
+      "learning_rate": 0.0,
+      "loss": 0.3694,
+      "step": 50
+    },
+    {
+      "epoch": 1.146131805157593,
+      "eval_loss": 0.4871082007884979,
+      "eval_runtime": 2.604,
+      "eval_samples_per_second": 112.904,
+      "eval_steps_per_second": 14.209,
+      "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": 3.937237443228467e+16,
+  "total_flos": 7.879368894316544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null