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:b4802e2812903a6f8a7bed676400f9ab90f0070bcf03c84b119c4c18da1f68d1
+oid sha256:24dacefcd1509c7e09085c629261302ce5ac5a83aa19da86a6b4b83f77078caa
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8503b0141d0efaffbeace58e4e83b94412d08a1cc2aa1b2b7c50f4d50816d89b
+oid sha256:9bdc954abead67ffa8c65181f6f08f10a2de9a8dc68c6e72a595b691bc127944
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7235b9eff26a80fec06c92de884f29fdb29ab31cd4f18474dc08d2a9ca7dc6
+oid sha256:740844ee5a0e0ed3593c65fc876a246e048c02d8327eeccb88c47770911d14c3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd73bd379c55539201a5529aecf33be20fc980c84fe6fe44711d3d1a7354d25
+oid sha256:1c9b2bd6050cd01403f4eee1d1d850ea041b3563faef8061f25e17ce0ef2aa07
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcbc9ab6aa63a4a260cf0e1421ff9b3502f14864951bf64fadb0d65f051d497
+oid sha256:42945a51494e7c0df67bfa5c598d8fce889228bb9a1fe95dd1504b43220a02fd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eca94f44a411ce73d139a2e2ddf87fb7a6efdb318feee0d06069a6ba42936cc
+oid sha256:2e5bbf666c50afa1e507631358ab8a6f2ff30340b8d5128f76972be56c804a44
 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": 2.43084979057312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.045966444495518274,
+  "best_metric": 2.2995645999908447,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09193288899103655,
   "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": 40.166,
       "eval_steps_per_second": 5.021,
       "step": 25
+    },
+    {
+      "epoch": 0.047805102275339004,
+      "grad_norm": 0.6615458130836487,
+      "learning_rate": 5e-05,
+      "loss": 2.457,
+      "step": 26
+    },
+    {
+      "epoch": 0.04964376005515973,
+      "grad_norm": 0.495445191860199,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.4575,
+      "step": 27
+    },
+    {
+      "epoch": 0.05148241783498046,
+      "grad_norm": 0.4795641601085663,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.4228,
+      "step": 28
+    },
+    {
+      "epoch": 0.0533210756148012,
+      "grad_norm": 0.4803744852542877,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4151,
+      "step": 29
+    },
+    {
+      "epoch": 0.05515973339462193,
+      "grad_norm": 0.5404251217842102,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4128,
+      "step": 30
+    },
+    {
+      "epoch": 0.05699839117444266,
+      "grad_norm": 0.5260909795761108,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.4072,
+      "step": 31
+    },
+    {
+      "epoch": 0.058837048954263386,
+      "grad_norm": 0.5466575622558594,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.428,
+      "step": 32
+    },
+    {
+      "epoch": 0.060675706734084116,
+      "grad_norm": 0.47617822885513306,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.4066,
+      "step": 33
+    },
+    {
+      "epoch": 0.06251436451390485,
+      "grad_norm": 0.5196675658226013,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3135,
+      "step": 34
+    },
+    {
+      "epoch": 0.06435302229372558,
+      "grad_norm": 0.6534458994865417,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.3918,
+      "step": 35
+    },
+    {
+      "epoch": 0.06619168007354631,
+      "grad_norm": 0.5190359950065613,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3302,
+      "step": 36
+    },
+    {
+      "epoch": 0.06803033785336704,
+      "grad_norm": 0.5105009078979492,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2812,
+      "step": 37
+    },
+    {
+      "epoch": 0.06986899563318777,
+      "grad_norm": 0.622005045413971,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3611,
+      "step": 38
+    },
+    {
+      "epoch": 0.0717076534130085,
+      "grad_norm": 0.6437798738479614,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.3768,
+      "step": 39
+    },
+    {
+      "epoch": 0.07354631119282923,
+      "grad_norm": 0.6086359024047852,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3218,
+      "step": 40
+    },
+    {
+      "epoch": 0.07538496897264997,
+      "grad_norm": 0.4965401887893677,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.3161,
+      "step": 41
+    },
+    {
+      "epoch": 0.0772236267524707,
+      "grad_norm": 0.4839130640029907,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.319,
+      "step": 42
+    },
+    {
+      "epoch": 0.07906228453229143,
+      "grad_norm": 0.4947792589664459,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.305,
+      "step": 43
+    },
+    {
+      "epoch": 0.08090094231211216,
+      "grad_norm": 0.5204262137413025,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3355,
+      "step": 44
+    },
+    {
+      "epoch": 0.08273960009193289,
+      "grad_norm": 0.6242971420288086,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.3654,
+      "step": 45
+    },
+    {
+      "epoch": 0.08457825787175362,
+      "grad_norm": 0.5766761302947998,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3287,
+      "step": 46
+    },
+    {
+      "epoch": 0.08641691565157435,
+      "grad_norm": 0.5085965991020203,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.3468,
+      "step": 47
+    },
+    {
+      "epoch": 0.08825557343139508,
+      "grad_norm": 0.5474885106086731,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.3602,
+      "step": 48
+    },
+    {
+      "epoch": 0.0900942312112158,
+      "grad_norm": 0.677193820476532,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.2757,
+      "step": 49
+    },
+    {
+      "epoch": 0.09193288899103655,
+      "grad_norm": 0.827997088432312,
+      "learning_rate": 0.0,
+      "loss": 2.2033,
+      "step": 50
+    },
+    {
+      "epoch": 0.09193288899103655,
+      "eval_loss": 2.2995645999908447,
+      "eval_runtime": 91.2388,
+      "eval_samples_per_second": 40.158,
+      "eval_steps_per_second": 5.02,
+      "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": 2.652642132099072e+17,
+  "total_flos": 5.305284264198144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null