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:c59db70e7d31ad4a3f273a4857e92ff0d291810b16465ce505b994282ad88a74
+oid sha256:edab1cc87ae3bfe87bb2462d302c748ecc70ab1fa34d49f716a67d482a44af25
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dabf54961c13e7d87cebea92bf324fdb622d98e7775becf94cefeb5cc2940c
+oid sha256:8b5a7017070ac9d6cde1b5c888e5149db1cf0494441e0f25d71884c892f70086
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335090815d4829a238d0be30e64e2ec72023634f2fbd06a8cef80cf3c299f4fa
+oid sha256:c29b5e38eca2ffaf900af20a4480bc062ccb8a75da68e2ec81e310daeaa94c97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15fa6ed567389d0ac019c0be7fd10b11cb81f1c3a2e79f89480c718a9cdd22c7
+oid sha256:ae24eed42e4bce20b1feaff3628b544beca3dc5aa2a5dab01c9169509ea05b5a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e447de9dca02ccd1ccccb1da9aefaf02ebb21d8b26a3f27d89f289de2f8e5f6f
+oid sha256:f66886fff13874f5f3d0fd0d34895afd440ab6812abe14af9049bc86623333c4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427004771da4a5df9a1cba8439ccc7eece7d1883d7c3d58659b2b82e3e9230fe
+oid sha256:01c27e94f33f7a8002522aafb088fc4228de649e1f6f1f6f79c56d46c539988e
 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": 1.281962513923645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.013481631277384564,
+  "best_metric": 1.2373801469802856,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.026963262554769128,
   "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": 161.224,
       "eval_steps_per_second": 10.079,
       "step": 25
+    },
+    {
+      "epoch": 0.014020896528479945,
+      "grad_norm": 0.6915966272354126,
+      "learning_rate": 5e-05,
+      "loss": 2.7684,
+      "step": 26
+    },
+    {
+      "epoch": 0.014560161779575328,
+      "grad_norm": 1.183508038520813,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0521,
+      "step": 27
+    },
+    {
+      "epoch": 0.015099427030670711,
+      "grad_norm": 1.1337106227874756,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6086,
+      "step": 28
+    },
+    {
+      "epoch": 0.015638692281766092,
+      "grad_norm": 0.9918910264968872,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2684,
+      "step": 29
+    },
+    {
+      "epoch": 0.016177957532861477,
+      "grad_norm": 0.8533536791801453,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2259,
+      "step": 30
+    },
+    {
+      "epoch": 0.016717222783956858,
+      "grad_norm": 0.7464625239372253,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1288,
+      "step": 31
+    },
+    {
+      "epoch": 0.017256488035052243,
+      "grad_norm": 0.7595018148422241,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0143,
+      "step": 32
+    },
+    {
+      "epoch": 0.017795753286147624,
+      "grad_norm": 0.7032437324523926,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0123,
+      "step": 33
+    },
+    {
+      "epoch": 0.018335018537243005,
+      "grad_norm": 0.6670097708702087,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9041,
+      "step": 34
+    },
+    {
+      "epoch": 0.01887428378833839,
+      "grad_norm": 0.611680805683136,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8395,
+      "step": 35
+    },
+    {
+      "epoch": 0.01941354903943377,
+      "grad_norm": 0.6346780061721802,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8197,
+      "step": 36
+    },
+    {
+      "epoch": 0.019952814290529156,
+      "grad_norm": 1.5375241041183472,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0206,
+      "step": 37
+    },
+    {
+      "epoch": 0.020492079541624537,
+      "grad_norm": 0.4851534068584442,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6551,
+      "step": 38
+    },
+    {
+      "epoch": 0.021031344792719918,
+      "grad_norm": 0.7288507223129272,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1959,
+      "step": 39
+    },
+    {
+      "epoch": 0.021570610043815303,
+      "grad_norm": 0.6835736036300659,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7378,
+      "step": 40
+    },
+    {
+      "epoch": 0.022109875294910684,
+      "grad_norm": 0.8178367018699646,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3294,
+      "step": 41
+    },
+    {
+      "epoch": 0.02264914054600607,
+      "grad_norm": 0.8485854864120483,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1328,
+      "step": 42
+    },
+    {
+      "epoch": 0.02318840579710145,
+      "grad_norm": 0.5767989158630371,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1029,
+      "step": 43
+    },
+    {
+      "epoch": 0.02372767104819683,
+      "grad_norm": 0.6219594478607178,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0409,
+      "step": 44
+    },
+    {
+      "epoch": 0.024266936299292215,
+      "grad_norm": 0.37479478120803833,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9684,
+      "step": 45
+    },
+    {
+      "epoch": 0.024806201550387597,
+      "grad_norm": 0.3662634789943695,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9145,
+      "step": 46
+    },
+    {
+      "epoch": 0.025345466801482978,
+      "grad_norm": 0.40091606974601746,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.856,
+      "step": 47
+    },
+    {
+      "epoch": 0.025884732052578362,
+      "grad_norm": 0.4234645664691925,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7905,
+      "step": 48
+    },
+    {
+      "epoch": 0.026423997303673744,
+      "grad_norm": 0.6059905290603638,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8682,
+      "step": 49
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "grad_norm": 1.4071378707885742,
+      "learning_rate": 0.0,
+      "loss": 0.964,
+      "step": 50
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "eval_loss": 1.2373801469802856,
+      "eval_runtime": 155.0212,
+      "eval_samples_per_second": 161.171,
+      "eval_steps_per_second": 10.076,
+      "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": 2.95300912644096e+16,
+  "total_flos": 5.90601825288192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null