Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ede76dd6c5ce7ff536c098f0c597bfba85fc7571efd1b0f2b17e051ff09c32
+oid sha256:a493f52b15db78d5a09860d75ab830096e6020fb9cea3a72952549b6c4176e98
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f42e50c15b2073501f636385d4621819680aceb3f220b67e5e69091d44d01d
+oid sha256:f2e0583c8fcd79c373cc3a99213c4bef758c7e647dca5c740365c7ec07287b18
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3065832dcec5b27b274ec267c9f0485277a970b0f4120413e2375960fd71e4ad
+oid sha256:6a0049135492969efa3391bb6c19672e22fc12fb1eecfb0a61325eea7e52a184
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9cb00e25309f8b5f2bba7c816a4792cd3a07cdb5b6857726a637dd1444bb90
+oid sha256:bb03ea725d2475db705a6936f93b696dbd20a50ebcb1c91f397789daa6166b80
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82aec8b9c6a0a8a116efb799cbbe1b18e52190f74975f2f8ee1645c898d54cc
+oid sha256:6e45f03344446f17e24db5715860a5e137628e565f442b7b9c2f8aa278c456b7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864b274905d187681934d1a88f9ec6768d678bbac8e90579e0c2d60bca4bc21a
+oid sha256:e4934237ad0adddc7fd61e8135cd16989f88c8bdaf0ef027384317ec0ee6d1b7
 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": 1.4860926866531372,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3325020781379884,
+  "best_metric": 1.467692255973816,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6650041562759768,
   "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": 114.363,
       "eval_steps_per_second": 14.436,
       "step": 25
+    },
+    {
+      "epoch": 0.3458021612635079,
+      "grad_norm": 0.18647287786006927,
+      "learning_rate": 5e-05,
+      "loss": 1.4277,
+      "step": 26
+    },
+    {
+      "epoch": 0.35910224438902744,
+      "grad_norm": 0.20698946714401245,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4413,
+      "step": 27
+    },
+    {
+      "epoch": 0.372402327514547,
+      "grad_norm": 0.20511312782764435,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4307,
+      "step": 28
+    },
+    {
+      "epoch": 0.3857024106400665,
+      "grad_norm": 0.2180362045764923,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4408,
+      "step": 29
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.21642690896987915,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4654,
+      "step": 30
+    },
+    {
+      "epoch": 0.41230257689110555,
+      "grad_norm": 0.21712642908096313,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4509,
+      "step": 31
+    },
+    {
+      "epoch": 0.4256026600166251,
+      "grad_norm": 0.22278568148612976,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4888,
+      "step": 32
+    },
+    {
+      "epoch": 0.4389027431421446,
+      "grad_norm": 0.2208184450864792,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3575,
+      "step": 33
+    },
+    {
+      "epoch": 0.45220282626766417,
+      "grad_norm": 0.23661835491657257,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4795,
+      "step": 34
+    },
+    {
+      "epoch": 0.46550290939318373,
+      "grad_norm": 0.25014418363571167,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.48,
+      "step": 35
+    },
+    {
+      "epoch": 0.47880299251870323,
+      "grad_norm": 0.26492103934288025,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4518,
+      "step": 36
+    },
+    {
+      "epoch": 0.4921030756442228,
+      "grad_norm": 0.33129605650901794,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5776,
+      "step": 37
+    },
+    {
+      "epoch": 0.5054031587697423,
+      "grad_norm": 0.22219394147396088,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5443,
+      "step": 38
+    },
+    {
+      "epoch": 0.5187032418952618,
+      "grad_norm": 0.21399854123592377,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4885,
+      "step": 39
+    },
+    {
+      "epoch": 0.5320033250207814,
+      "grad_norm": 0.20631512999534607,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3427,
+      "step": 40
+    },
+    {
+      "epoch": 0.545303408146301,
+      "grad_norm": 0.21566346287727356,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.459,
+      "step": 41
+    },
+    {
+      "epoch": 0.5586034912718204,
+      "grad_norm": 0.20011813938617706,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4605,
+      "step": 42
+    },
+    {
+      "epoch": 0.57190357439734,
+      "grad_norm": 0.21354447305202484,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.4537,
+      "step": 43
+    },
+    {
+      "epoch": 0.5852036575228595,
+      "grad_norm": 0.20864373445510864,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3382,
+      "step": 44
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 0.20621033012866974,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3996,
+      "step": 45
+    },
+    {
+      "epoch": 0.6118038237738986,
+      "grad_norm": 0.24815712869167328,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4625,
+      "step": 46
+    },
+    {
+      "epoch": 0.6251039068994181,
+      "grad_norm": 0.2448890209197998,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4835,
+      "step": 47
+    },
+    {
+      "epoch": 0.6384039900249376,
+      "grad_norm": 0.26246240735054016,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4203,
+      "step": 48
+    },
+    {
+      "epoch": 0.6517040731504572,
+      "grad_norm": 0.30303773283958435,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5443,
+      "step": 49
+    },
+    {
+      "epoch": 0.6650041562759768,
+      "grad_norm": 0.4216666519641876,
+      "learning_rate": 0.0,
+      "loss": 1.5894,
+      "step": 50
+    },
+    {
+      "epoch": 0.6650041562759768,
+      "eval_loss": 1.467692255973816,
+      "eval_runtime": 4.4285,
+      "eval_samples_per_second": 114.486,
+      "eval_steps_per_second": 14.452,
+      "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