Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e70a1ab09eafeac53adfdac0ce37faec32fa3fcdeb5c9574fc18887ec37c9ad
+oid sha256:9504ecae5f8b13512f3c3b309a6c8f43ec3d312393840f8c7274f17ba2f26b4e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08a5db648a99b2a39c0da5d2be9d219522c4ad11f2a2b55f86823c0e0f2d147
+oid sha256:ad3c6b96b731b97571ecfde602659b4212d05970771cc8d4f954614685112213
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74132bf0139d3e5b481fb29b3a85a584240164d592e50763a22e6c2b3a5dbbce
+oid sha256:e8563d054598c7466a892db4bd998a020db56a361014f4e363a1eb9a06268883
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b9101ba0cbcd853dd8eed444121e7a47b8114b5a4ff4103330049e8a22a651
+oid sha256:99317a4914824202abd1e0aed2608c4375f5054fa89c279a824a669482ad9ece
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b016a48c5eb7ef9d2087cf52f71edd50116978c75a6fe55271bf32d6a4c994dd
+oid sha256:271510b906facb6d3207512c40c2a600a375095ea28b9f83b14efad29ff27eba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288cb1f4fdcb08b7226c88c3b3671c1e073a122d22c17562c1a1ada3ef936630
+oid sha256:3c1ccc0d6df59cd5b409c57081c5d5aba71850ff87096eee3081481bd2906ce1
 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": 0.5778371691703796,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11299435028248588,
+  "best_metric": 0.4722478687763214,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22598870056497175,
   "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": 32.924,
       "eval_steps_per_second": 4.129,
       "step": 25
+    },
+    {
+      "epoch": 0.11751412429378531,
+      "grad_norm": 1.7103195190429688,
+      "learning_rate": 5e-05,
+      "loss": 0.3885,
+      "step": 26
+    },
+    {
+      "epoch": 0.12203389830508475,
+      "grad_norm": 2.540452480316162,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3325,
+      "step": 27
+    },
+    {
+      "epoch": 0.12655367231638417,
+      "grad_norm": 2.0381650924682617,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2664,
+      "step": 28
+    },
+    {
+      "epoch": 0.1310734463276836,
+      "grad_norm": 1.8808456659317017,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3471,
+      "step": 29
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 1.5149118900299072,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3276,
+      "step": 30
+    },
+    {
+      "epoch": 0.1401129943502825,
+      "grad_norm": 1.6971021890640259,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3439,
+      "step": 31
+    },
+    {
+      "epoch": 0.14463276836158193,
+      "grad_norm": 1.2903318405151367,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.39,
+      "step": 32
+    },
+    {
+      "epoch": 0.14915254237288136,
+      "grad_norm": 1.122199296951294,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3097,
+      "step": 33
+    },
+    {
+      "epoch": 0.1536723163841808,
+      "grad_norm": 1.0199609994888306,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3251,
+      "step": 34
+    },
+    {
+      "epoch": 0.15819209039548024,
+      "grad_norm": 1.3618215322494507,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.476,
+      "step": 35
+    },
+    {
+      "epoch": 0.16271186440677965,
+      "grad_norm": 1.6055341958999634,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6691,
+      "step": 36
+    },
+    {
+      "epoch": 0.1672316384180791,
+      "grad_norm": 2.307286024093628,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9103,
+      "step": 37
+    },
+    {
+      "epoch": 0.17175141242937852,
+      "grad_norm": 1.8381061553955078,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6667,
+      "step": 38
+    },
+    {
+      "epoch": 0.17627118644067796,
+      "grad_norm": 2.2784359455108643,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3198,
+      "step": 39
+    },
+    {
+      "epoch": 0.1807909604519774,
+      "grad_norm": 1.9385861158370972,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2847,
+      "step": 40
+    },
+    {
+      "epoch": 0.18531073446327684,
+      "grad_norm": 1.723340630531311,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2729,
+      "step": 41
+    },
+    {
+      "epoch": 0.18983050847457628,
+      "grad_norm": 1.352947473526001,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3033,
+      "step": 42
+    },
+    {
+      "epoch": 0.1943502824858757,
+      "grad_norm": 1.3377389907836914,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2928,
+      "step": 43
+    },
+    {
+      "epoch": 0.19887005649717515,
+      "grad_norm": 1.2967225313186646,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2915,
+      "step": 44
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 1.1458157300949097,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2949,
+      "step": 45
+    },
+    {
+      "epoch": 0.207909604519774,
+      "grad_norm": 1.1767059564590454,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3244,
+      "step": 46
+    },
+    {
+      "epoch": 0.21242937853107344,
+      "grad_norm": 0.8545200824737549,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3141,
+      "step": 47
+    },
+    {
+      "epoch": 0.21694915254237288,
+      "grad_norm": 1.389214038848877,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6378,
+      "step": 48
+    },
+    {
+      "epoch": 0.2214689265536723,
+      "grad_norm": 1.9914606809616089,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7584,
+      "step": 49
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "grad_norm": 2.9483211040496826,
+      "learning_rate": 0.0,
+      "loss": 1.1446,
+      "step": 50
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "eval_loss": 0.4722478687763214,
+      "eval_runtime": 45.2655,
+      "eval_samples_per_second": 32.939,
+      "eval_steps_per_second": 4.131,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.9736786926882e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null