Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d95207f4199ec933d4dc84045b713ecb89351f95a5b2ab41a905c6675a08c33
+oid sha256:cbbb0f571df349fc61dee927c0052770d2d032595da7b3fdab6e53a15cb6cdaf
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed575f9be619ee1095d0b5374d47cf204c217fac8cbf9843105adc7faefed95c
+oid sha256:ce1e1f8cb334b7558a972d246bb805021bb85ee103a9931c2d375ab8d96bde33
 size 100824826

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4d5c9f2506eab878ef08f9a16b3999473f9b66e38d63aae874a04f181132a8
+oid sha256:784d9bb5d4ef29d85358d22836584ecc8fd73df1a95f218e6a1ceb483c0b2c51
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47befb163ac8b7ae6621190db1c6877178465751028e72a042b52a5972a0b19b
+oid sha256:0ef59799ab01cffc7bad8a129ee7829a36e8f5ba7b0a7933cdb443cc11b9fcd8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43d744a809d5e310b7c2b446addbf9d474338c0fd7b327d727ae9dcc12326bf
+oid sha256:8997ca967edb7b22e2d546c700b4f6884a9f1940a242bf1ae323820dbe1ccbd1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6229c18ca7c49f77e0640910fe2dc60e1e39ea7c3835ab450b6bc8b535490d78
+oid sha256:0dcda2ab2a3b181ddeed1ea7d55ba77d71529a404f66a6236153487ee80e806a
 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": 1.7169548273086548,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22573363431151242,
+  "best_metric": 1.6892688274383545,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45146726862302483,
   "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": 34.583,
       "eval_steps_per_second": 4.358,
       "step": 25
+    },
+    {
+      "epoch": 0.23476297968397292,
+      "grad_norm": 10.446999549865723,
+      "learning_rate": 5e-05,
+      "loss": 1.9507,
+      "step": 26
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 14.517119407653809,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7608,
+      "step": 27
+    },
+    {
+      "epoch": 0.2528216704288939,
+      "grad_norm": 13.12651538848877,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.855,
+      "step": 28
+    },
+    {
+      "epoch": 0.2618510158013544,
+      "grad_norm": 14.233924865722656,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0465,
+      "step": 29
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 7.151965618133545,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.972,
+      "step": 30
+    },
+    {
+      "epoch": 0.2799097065462754,
+      "grad_norm": 16.563194274902344,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.9879,
+      "step": 31
+    },
+    {
+      "epoch": 0.28893905191873587,
+      "grad_norm": 6.9923882484436035,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1213,
+      "step": 32
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 8.007791519165039,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9241,
+      "step": 33
+    },
+    {
+      "epoch": 0.30699774266365687,
+      "grad_norm": 7.834492206573486,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7401,
+      "step": 34
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 7.595086097717285,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6902,
+      "step": 35
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 10.489594459533691,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1672,
+      "step": 36
+    },
+    {
+      "epoch": 0.3340857787810384,
+      "grad_norm": 12.582670211791992,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9709,
+      "step": 37
+    },
+    {
+      "epoch": 0.3431151241534989,
+      "grad_norm": 14.302665710449219,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.383,
+      "step": 38
+    },
+    {
+      "epoch": 0.35214446952595935,
+      "grad_norm": 8.146827697753906,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7108,
+      "step": 39
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 7.049624919891357,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0271,
+      "step": 40
+    },
+    {
+      "epoch": 0.37020316027088035,
+      "grad_norm": 6.904928207397461,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6862,
+      "step": 41
+    },
+    {
+      "epoch": 0.3792325056433409,
+      "grad_norm": 6.063751220703125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9426,
+      "step": 42
+    },
+    {
+      "epoch": 0.38826185101580135,
+      "grad_norm": 6.246118545532227,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0365,
+      "step": 43
+    },
+    {
+      "epoch": 0.3972911963882618,
+      "grad_norm": 5.754870414733887,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0996,
+      "step": 44
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 6.7023515701293945,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9791,
+      "step": 45
+    },
+    {
+      "epoch": 0.4153498871331828,
+      "grad_norm": 6.462357997894287,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9522,
+      "step": 46
+    },
+    {
+      "epoch": 0.42437923250564336,
+      "grad_norm": 6.6611409187316895,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6469,
+      "step": 47
+    },
+    {
+      "epoch": 0.43340857787810383,
+      "grad_norm": 7.755826950073242,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6362,
+      "step": 48
+    },
+    {
+      "epoch": 0.44243792325056436,
+      "grad_norm": 9.511348724365234,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0692,
+      "step": 49
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 17.744104385375977,
+      "learning_rate": 0.0,
+      "loss": 0.7786,
+      "step": 50
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 1.6892688274383545,
+      "eval_runtime": 21.5484,
+      "eval_samples_per_second": 34.62,
+      "eval_steps_per_second": 4.362,
+      "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": 1.2413185227227136e+16,
+  "total_flos": 2.480315377385472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null