Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4772906fdd47eef9a8188e7c501aed4ce8858a37ec144140dd7fac31b7c91b17
+oid sha256:5adecc726ad982295c530974c8172ea2dbc139fe446ca490de69c0052c8829b9
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4ff3988dd76b18accb4798e7124abb57048098fb6c147db6c88a819e484cb3
+oid sha256:de246906d2ab0d49f5c6b0fe5c4f1013a6e1aa53d204bde2b03709bc059c5b13
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5bdb0538eeb7af16e7e2fd592d1bdaec360e48c61de803f1c6f6289edcf24e
+oid sha256:c74fdf79d1d4ea289c2c8f377a8fa80ace643a329b34377699919cc7f48f212c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83eaebb745d5f4911002249f8d6f1d71952f0c54c3a84213d853347b7f842bc0
+oid sha256:65cd0f8daca402cae3497008f42b86eda83058a19f95646477e9278ab54b88d6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea00e5deec6d0f9a55d5cd250f38129133fecbdcaed8f2d6ebb68c9f1fbf38dc
+oid sha256:77dbe0891ca1ca7b893b721da0beb1ad5a3124ffb1147868d766af6a3d32565b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b92e438948eafe24d547c69bb269d99aa3de67b640aff4a2bfa5c5b183dbdcd
+oid sha256:003207565dfd5ad6be4adb61aef1f67d916b06a3b8a54b1c8fcce52ff8be21a0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.698549509048462,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006670891564657617,
+  "best_metric": 2.6588540077209473,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013341783129315233,
   "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": 16.988,
       "eval_steps_per_second": 4.417,
       "step": 25
+    },
+    {
+      "epoch": 0.006937727227243921,
+      "grad_norm": 6.648555755615234,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 42.6766,
+      "step": 26
+    },
+    {
+      "epoch": 0.007204562889830225,
+      "grad_norm": 7.370015621185303,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 43.2309,
+      "step": 27
+    },
+    {
+      "epoch": 0.007471398552416531,
+      "grad_norm": 7.749670028686523,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 43.0116,
+      "step": 28
+    },
+    {
+      "epoch": 0.007738234215002835,
+      "grad_norm": 6.2989397048950195,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 42.8237,
+      "step": 29
+    },
+    {
+      "epoch": 0.00800506987758914,
+      "grad_norm": 4.506712436676025,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 43.307,
+      "step": 30
+    },
+    {
+      "epoch": 0.008271905540175444,
+      "grad_norm": 3.3741683959960938,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 42.2995,
+      "step": 31
+    },
+    {
+      "epoch": 0.008538741202761749,
+      "grad_norm": 5.093672275543213,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 42.7456,
+      "step": 32
+    },
+    {
+      "epoch": 0.008805576865348054,
+      "grad_norm": 6.034478664398193,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 42.0105,
+      "step": 33
+    },
+    {
+      "epoch": 0.009072412527934358,
+      "grad_norm": 8.994264602661133,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 42.6373,
+      "step": 34
+    },
+    {
+      "epoch": 0.009339248190520663,
+      "grad_norm": 9.392966270446777,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 41.8498,
+      "step": 35
+    },
+    {
+      "epoch": 0.009606083853106968,
+      "grad_norm": 13.750999450683594,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 43.4925,
+      "step": 36
+    },
+    {
+      "epoch": 0.009872919515693272,
+      "grad_norm": 24.36878776550293,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 44.5269,
+      "step": 37
+    },
+    {
+      "epoch": 0.010139755178279577,
+      "grad_norm": 25.610509872436523,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 50.1446,
+      "step": 38
+    },
+    {
+      "epoch": 0.010406590840865882,
+      "grad_norm": 3.175342321395874,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 41.6619,
+      "step": 39
+    },
+    {
+      "epoch": 0.010673426503452186,
+      "grad_norm": 3.2958128452301025,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 42.1298,
+      "step": 40
+    },
+    {
+      "epoch": 0.010940262166038491,
+      "grad_norm": 2.820218563079834,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 42.4535,
+      "step": 41
+    },
+    {
+      "epoch": 0.011207097828624796,
+      "grad_norm": 3.14233660697937,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 42.1202,
+      "step": 42
+    },
+    {
+      "epoch": 0.0114739334912111,
+      "grad_norm": 3.2131524085998535,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 42.7891,
+      "step": 43
+    },
+    {
+      "epoch": 0.011740769153797405,
+      "grad_norm": 3.0920655727386475,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 42.275,
+      "step": 44
+    },
+    {
+      "epoch": 0.01200760481638371,
+      "grad_norm": 3.9214160442352295,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 41.5912,
+      "step": 45
+    },
+    {
+      "epoch": 0.012274440478970014,
+      "grad_norm": 3.8326663970947266,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 41.7581,
+      "step": 46
+    },
+    {
+      "epoch": 0.01254127614155632,
+      "grad_norm": 4.249518394470215,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 42.1641,
+      "step": 47
+    },
+    {
+      "epoch": 0.012808111804142625,
+      "grad_norm": 5.223924160003662,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 42.5394,
+      "step": 48
+    },
+    {
+      "epoch": 0.013074947466728928,
+      "grad_norm": 9.145912170410156,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 43.8346,
+      "step": 49
+    },
+    {
+      "epoch": 0.013341783129315233,
+      "grad_norm": 32.097389221191406,
+      "learning_rate": 1e-05,
+      "loss": 49.8327,
+      "step": 50
+    },
+    {
+      "epoch": 0.013341783129315233,
+      "eval_loss": 2.6588540077209473,
+      "eval_runtime": 2.9071,
+      "eval_samples_per_second": 17.2,
+      "eval_steps_per_second": 4.472,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null