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:d2873318cfb3056aa7767a345b83f1a021cae9e7527b2e4224b18ea7f66c8529
+oid sha256:5ec49397f4699f4cae2117aa0de0d07d62129b209ce8946b247255d8af90339b
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f400b071e71cf3412d4daa13e3dc34cff0c7216f23ad1d040567b588e8aa21d
+oid sha256:72cb4224e32c8bcc9c67944d41a6b1b590dd6ab461b3a7ae067627f2a4481556
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d03ea1ba9655e3af0f5fc501bb50e6e557d45d6a0d702214bad807baf262ac4f
+oid sha256:fec3ebf0df17813137a3e1fd0aeb97317ae63afb15304a1ef50f68b0e99a6e38
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92dc9970c0b21b4cc02c6fce70026b912250813a4656843b4a8dbd11ea34b61e
+oid sha256:4633c43673fd9c6e7ec71212403add79d993625eaf17a546912eed4d65edde46
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487171c01d9ee4b2b0fd181bd8f0f9c43a4e7f783809ee3f23889282bea0de4a
+oid sha256:193284a8c0571073ab7e090c6975ef4f7a633e37c39190214b729c913694d3a3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11c3e30a3a590329eaaa67bea03db05401850d4081f08b92efa190d8443f209d
+oid sha256:6a6aa702a9befbb816bdc40442a3c855d153879ab592d89dfd900090199bd45b
 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": 0.2354392111301422,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0641025641025641,
+  "best_metric": 0.2184295952320099,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1282051282051282,
   "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": 37.852,
       "eval_steps_per_second": 4.739,
       "step": 25
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.34883347153663635,
+      "learning_rate": 5e-05,
+      "loss": 0.1933,
+      "step": 26
+    },
+    {
+      "epoch": 0.06923076923076923,
+      "grad_norm": 0.43962642550468445,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1936,
+      "step": 27
+    },
+    {
+      "epoch": 0.07179487179487179,
+      "grad_norm": 0.3392525613307953,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2484,
+      "step": 28
+    },
+    {
+      "epoch": 0.07435897435897436,
+      "grad_norm": 0.268801748752594,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2169,
+      "step": 29
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.2719249725341797,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1971,
+      "step": 30
+    },
+    {
+      "epoch": 0.07948717948717948,
+      "grad_norm": 0.3328043818473816,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2637,
+      "step": 31
+    },
+    {
+      "epoch": 0.08205128205128205,
+      "grad_norm": 0.2753499448299408,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2259,
+      "step": 32
+    },
+    {
+      "epoch": 0.08461538461538462,
+      "grad_norm": 0.3301796019077301,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2266,
+      "step": 33
+    },
+    {
+      "epoch": 0.08717948717948718,
+      "grad_norm": 0.3097302317619324,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.224,
+      "step": 34
+    },
+    {
+      "epoch": 0.08974358974358974,
+      "grad_norm": 0.34540295600891113,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2636,
+      "step": 35
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.4204685688018799,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.253,
+      "step": 36
+    },
+    {
+      "epoch": 0.09487179487179487,
+      "grad_norm": 0.45146670937538147,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2145,
+      "step": 37
+    },
+    {
+      "epoch": 0.09743589743589744,
+      "grad_norm": 0.28045856952667236,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2233,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2076382040977478,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1671,
+      "step": 39
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 0.211055725812912,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1827,
+      "step": 40
+    },
+    {
+      "epoch": 0.10512820512820513,
+      "grad_norm": 0.23544220626354218,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1951,
+      "step": 41
+    },
+    {
+      "epoch": 0.1076923076923077,
+      "grad_norm": 0.22622856497764587,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.178,
+      "step": 42
+    },
+    {
+      "epoch": 0.11025641025641025,
+      "grad_norm": 0.24078531563282013,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.195,
+      "step": 43
+    },
+    {
+      "epoch": 0.11282051282051282,
+      "grad_norm": 0.25304022431373596,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2121,
+      "step": 44
+    },
+    {
+      "epoch": 0.11538461538461539,
+      "grad_norm": 0.25861841440200806,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1862,
+      "step": 45
+    },
+    {
+      "epoch": 0.11794871794871795,
+      "grad_norm": 0.3511195480823517,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2426,
+      "step": 46
+    },
+    {
+      "epoch": 0.12051282051282051,
+      "grad_norm": 0.3163631558418274,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2127,
+      "step": 47
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 0.4123046100139618,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2465,
+      "step": 48
+    },
+    {
+      "epoch": 0.12564102564102564,
+      "grad_norm": 0.4300198256969452,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2869,
+      "step": 49
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 0.4179116189479828,
+      "learning_rate": 0.0,
+      "loss": 0.2097,
+      "step": 50
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "eval_loss": 0.2184295952320099,
+      "eval_runtime": 69.5641,
+      "eval_samples_per_second": 37.778,
+      "eval_steps_per_second": 4.729,
+      "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": 2.822877455843328e+17,
+  "total_flos": 5.645754911686656e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null