Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc792381b88afecff4db82a6a1854747f0bc70cadf952b5e23a09223d6f60ce
+oid sha256:6074a7134fffe637083f53a323ca8eaa114ad6c95c71f5395d100a59c92f4d3a
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be48e9ae79e696e3b86ee021982e04506726066bd27f6ad11afd152721876fde
+oid sha256:5f0d060a715c828814c23159a8f73d158f305209b2da2eeffe5941baea6c6299
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4daa89d605df9224f9755a51c77bc749f1af33d82be708fcfc43dffcb47680b
+oid sha256:35d01fb67e619b09f93affdf030b287497d2a112c25a5db0e39833e71da05c2c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670783c39a599a28512baec73bec747492bf0d8860c0c9577f26b810b3bf2b3a
+oid sha256:d07ade0d21ea82489f042696194070462849b225d382937fc1f7960b2c588f6c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e50e44b5144df8259f281366deb9581938758cf3548c7ac17c943ab765061a
+oid sha256:69a6b54a01232873a8d7d79549a3c7b14d01f4733610d5b7445bdb80c477bf4d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4071cc31838fc5ab27eec0e8e172c3c724978db14c7494a6ce2ea70a97a37b37
+oid sha256:0c1004171a66e880dc1d2de1e8bb52b0438bfe777ca90d8e677562953c7d6f2a
 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": 1.0937927961349487,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02839094328909078,
+  "best_metric": 1.0860586166381836,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05678188657818156,
   "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": 138.718,
       "eval_steps_per_second": 17.349,
       "step": 25
+    },
+    {
+      "epoch": 0.029526581020654412,
+      "grad_norm": 0.26916369795799255,
+      "learning_rate": 5e-05,
+      "loss": 0.8223,
+      "step": 26
+    },
+    {
+      "epoch": 0.030662218752218043,
+      "grad_norm": 0.28640347719192505,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9502,
+      "step": 27
+    },
+    {
+      "epoch": 0.031797856483781674,
+      "grad_norm": 0.29415908455848694,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9528,
+      "step": 28
+    },
+    {
+      "epoch": 0.032933494215345305,
+      "grad_norm": 0.300428569316864,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0052,
+      "step": 29
+    },
+    {
+      "epoch": 0.034069131946908936,
+      "grad_norm": 0.3093526065349579,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0124,
+      "step": 30
+    },
+    {
+      "epoch": 0.03520476967847257,
+      "grad_norm": 0.32666245102882385,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.975,
+      "step": 31
+    },
+    {
+      "epoch": 0.0363404074100362,
+      "grad_norm": 0.34878939390182495,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1806,
+      "step": 32
+    },
+    {
+      "epoch": 0.03747604514159983,
+      "grad_norm": 0.37372487783432007,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1176,
+      "step": 33
+    },
+    {
+      "epoch": 0.03861168287316346,
+      "grad_norm": 0.46194377541542053,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1524,
+      "step": 34
+    },
+    {
+      "epoch": 0.03974732060472709,
+      "grad_norm": 0.591774046421051,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1847,
+      "step": 35
+    },
+    {
+      "epoch": 0.04088295833629072,
+      "grad_norm": 0.7484531998634338,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3388,
+      "step": 36
+    },
+    {
+      "epoch": 0.04201859606785435,
+      "grad_norm": 0.8685662746429443,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3402,
+      "step": 37
+    },
+    {
+      "epoch": 0.04315423379941798,
+      "grad_norm": 0.3701391816139221,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8519,
+      "step": 38
+    },
+    {
+      "epoch": 0.044289871530981614,
+      "grad_norm": 0.2335858792066574,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9027,
+      "step": 39
+    },
+    {
+      "epoch": 0.045425509262545245,
+      "grad_norm": 0.24511219561100006,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0077,
+      "step": 40
+    },
+    {
+      "epoch": 0.046561146994108876,
+      "grad_norm": 0.2630201578140259,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9539,
+      "step": 41
+    },
+    {
+      "epoch": 0.04769678472567251,
+      "grad_norm": 0.28861838579177856,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1378,
+      "step": 42
+    },
+    {
+      "epoch": 0.048832422457236145,
+      "grad_norm": 0.3146965801715851,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0489,
+      "step": 43
+    },
+    {
+      "epoch": 0.049968060188799776,
+      "grad_norm": 0.3190613389015198,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0681,
+      "step": 44
+    },
+    {
+      "epoch": 0.05110369792036341,
+      "grad_norm": 0.32654303312301636,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.083,
+      "step": 45
+    },
+    {
+      "epoch": 0.05223933565192704,
+      "grad_norm": 0.39204129576683044,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0401,
+      "step": 46
+    },
+    {
+      "epoch": 0.05337497338349067,
+      "grad_norm": 0.4339013695716858,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0863,
+      "step": 47
+    },
+    {
+      "epoch": 0.0545106111150543,
+      "grad_norm": 0.5439497828483582,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2212,
+      "step": 48
+    },
+    {
+      "epoch": 0.05564624884661793,
+      "grad_norm": 0.7164722084999084,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3335,
+      "step": 49
+    },
+    {
+      "epoch": 0.05678188657818156,
+      "grad_norm": 1.4054168462753296,
+      "learning_rate": 0.0,
+      "loss": 1.5089,
+      "step": 50
+    },
+    {
+      "epoch": 0.05678188657818156,
+      "eval_loss": 1.0860586166381836,
+      "eval_runtime": 42.7723,
+      "eval_samples_per_second": 138.711,
+      "eval_steps_per_second": 17.348,
+      "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": 1.4875783445086208e+16,
+  "total_flos": 2.977002323705856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null