Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5535c203806977e4c7f31345ccc58cfe0f491997ef0e1efa59872b6d86cb3f2f
+oid sha256:3fe055da256526c516e9d474fe1d98509769c1542f5a0d5e8a16ea2a4cebd02e
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02092188762c0de3d34f52f4db0911dd56ef112fbcf78ff3d78e0d4578f8b4ac
+oid sha256:d77ec5b98e4406fa0afc1dc2e7da70fe1824c8ac4334e3cb1d9b54fa1f242a14
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5122bd5ad6bb27b382cbba3c1991b6562ef24913204fdbeb618fac7864a86a
+oid sha256:e66b33a9b9a5ad5cb3e9249eb6f9b7d06afdf4892e6cddb78ec271679205abe2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f215d238d906e1f7cebf173cde14901e8c8962aa3f7e8924f4578d22222d7e
+oid sha256:d4405e3dc45dc733a398d394660b0db1c0a7ab482d4f5628957bcfa0877727da
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d415fd7c45b3f916ad628332f044fd96634312576975632ddf2ee8176ef665ad
+oid sha256:0089c8507340620ce579b17c2e9e48f12a8ab91e620d5d1e32b18e151463b485
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43faa1097897e6e64499ff7350cd9605962e8d374ecccc42f4aa511752f8d2b6
+oid sha256:06098d5a32a07c07e2fade0c5863aa3057148c4b439be8454b8812e1bdde3893
 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": 0.9570152163505554,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14947683109118087,
+  "best_metric": 0.8159454464912415,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.29895366218236175,
   "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": 122.044,
       "eval_steps_per_second": 15.269,
       "step": 25
+    },
+    {
+      "epoch": 0.1554559043348281,
+      "grad_norm": 0.6872985363006592,
+      "learning_rate": 5e-05,
+      "loss": 1.029,
+      "step": 26
+    },
+    {
+      "epoch": 0.16143497757847533,
+      "grad_norm": 0.632942259311676,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9259,
+      "step": 27
+    },
+    {
+      "epoch": 0.16741405082212257,
+      "grad_norm": 0.5986387133598328,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8612,
+      "step": 28
+    },
+    {
+      "epoch": 0.17339312406576982,
+      "grad_norm": 0.6099429130554199,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8646,
+      "step": 29
+    },
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 0.5303110480308533,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8294,
+      "step": 30
+    },
+    {
+      "epoch": 0.18535127055306427,
+      "grad_norm": 0.5066549777984619,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8879,
+      "step": 31
+    },
+    {
+      "epoch": 0.19133034379671152,
+      "grad_norm": 0.530630350112915,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8317,
+      "step": 32
+    },
+    {
+      "epoch": 0.19730941704035873,
+      "grad_norm": 0.3913431465625763,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8476,
+      "step": 33
+    },
+    {
+      "epoch": 0.20328849028400597,
+      "grad_norm": 0.38945111632347107,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8998,
+      "step": 34
+    },
+    {
+      "epoch": 0.20926756352765322,
+      "grad_norm": 0.36714988946914673,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7483,
+      "step": 35
+    },
+    {
+      "epoch": 0.21524663677130046,
+      "grad_norm": 0.41465187072753906,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8728,
+      "step": 36
+    },
+    {
+      "epoch": 0.22122571001494767,
+      "grad_norm": 0.5536110401153564,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9151,
+      "step": 37
+    },
+    {
+      "epoch": 0.22720478325859492,
+      "grad_norm": 0.6803256869316101,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0324,
+      "step": 38
+    },
+    {
+      "epoch": 0.23318385650224216,
+      "grad_norm": 0.38136497139930725,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7947,
+      "step": 39
+    },
+    {
+      "epoch": 0.23916292974588937,
+      "grad_norm": 0.39119410514831543,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7218,
+      "step": 40
+    },
+    {
+      "epoch": 0.24514200298953662,
+      "grad_norm": 0.3474106192588806,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.762,
+      "step": 41
+    },
+    {
+      "epoch": 0.25112107623318386,
+      "grad_norm": 0.3799263834953308,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7763,
+      "step": 42
+    },
+    {
+      "epoch": 0.2571001494768311,
+      "grad_norm": 0.34402114152908325,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7772,
+      "step": 43
+    },
+    {
+      "epoch": 0.26307922272047835,
+      "grad_norm": 0.31651434302330017,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7316,
+      "step": 44
+    },
+    {
+      "epoch": 0.26905829596412556,
+      "grad_norm": 0.33870384097099304,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8084,
+      "step": 45
+    },
+    {
+      "epoch": 0.2750373692077728,
+      "grad_norm": 0.32227766513824463,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8132,
+      "step": 46
+    },
+    {
+      "epoch": 0.28101644245142005,
+      "grad_norm": 0.31585749983787537,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7976,
+      "step": 47
+    },
+    {
+      "epoch": 0.28699551569506726,
+      "grad_norm": 0.32487156987190247,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8213,
+      "step": 48
+    },
+    {
+      "epoch": 0.2929745889387145,
+      "grad_norm": 0.40243586897850037,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8709,
+      "step": 49
+    },
+    {
+      "epoch": 0.29895366218236175,
+      "grad_norm": 0.5789146423339844,
+      "learning_rate": 0.0,
+      "loss": 0.9765,
+      "step": 50
+    },
+    {
+      "epoch": 0.29895366218236175,
+      "eval_loss": 0.8159454464912415,
+      "eval_runtime": 9.2521,
+      "eval_samples_per_second": 121.81,
+      "eval_steps_per_second": 15.24,
+      "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": 4.200939509723955e+16,
+  "total_flos": 8.396670163641958e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null