Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d6436c2c56d771b8674c9db67694089a9b6a337b0470555a563a9142ac8bac
+oid sha256:fe0226741b80f39e95afa0e99909dbb847f3aa7f78129643ec93c711c421d64e
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442d6e7728caff0327696a50ccdf8c55b0660853fb6eded3316a1f102a1c9298
+oid sha256:a2408b5bdb9416f8d7e694fa4d6528016a1b26edf8f5c142488525acf3a0767a
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a75cc9e94d518c7b4a4d57f22a4a0b581b98d58f8773bad2c20893b24ab27ef
+oid sha256:51a5d99740e21ef184317ebbe79528b1a6f17f1e319d1a3535dfe26d7ef66664
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac26089c1b0cddeb40974aedf9bae371f0870f676a186f77d3e8c9f8904f930c
+oid sha256:b6ea72a57f3606cb17cea276a3c2b2855dc50505cbc0cfc5c6cd52d9c8bd60ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a2564a61438a0d050a4b7876b27cb7657bf04de36d5d0b1dbd61fd97701e95
+oid sha256:3af9d4fd6a7d8780413f7df417831c8e1881fce56a8ff22185232f5ee39eabd7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19bd9f9a9f4615fe5bc2be83daa03d99725bb3ead43a31393c919e8989d1291
+oid sha256:3d0e930a466d5d9d1c310616540c287fd8eac1ebdd28484b50e4d9ae353c5887
 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": 2.3853487968444824,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009473509698505553,
+  "best_metric": 2.28448224067688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.018947019397011107,
   "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": 11.967,
       "eval_steps_per_second": 1.496,
       "step": 25
+    },
+    {
+      "epoch": 0.009852450086445776,
+      "grad_norm": 41.54273223876953,
+      "learning_rate": 5e-05,
+      "loss": 2.5266,
+      "step": 26
+    },
+    {
+      "epoch": 0.010231390474385997,
+      "grad_norm": 37.918094635009766,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3561,
+      "step": 27
+    },
+    {
+      "epoch": 0.01061033086232622,
+      "grad_norm": 32.39877700805664,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.3502,
+      "step": 28
+    },
+    {
+      "epoch": 0.010989271250266443,
+      "grad_norm": 33.80083465576172,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4292,
+      "step": 29
+    },
+    {
+      "epoch": 0.011368211638206664,
+      "grad_norm": 24.64554786682129,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4089,
+      "step": 30
+    },
+    {
+      "epoch": 0.011747152026146887,
+      "grad_norm": 21.70261573791504,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.3391,
+      "step": 31
+    },
+    {
+      "epoch": 0.012126092414087108,
+      "grad_norm": 20.256654739379883,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.262,
+      "step": 32
+    },
+    {
+      "epoch": 0.012505032802027331,
+      "grad_norm": 15.916815757751465,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.2547,
+      "step": 33
+    },
+    {
+      "epoch": 0.012883973189967554,
+      "grad_norm": 19.03730010986328,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3206,
+      "step": 34
+    },
+    {
+      "epoch": 0.013262913577907775,
+      "grad_norm": 21.43941307067871,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2924,
+      "step": 35
+    },
+    {
+      "epoch": 0.013641853965847998,
+      "grad_norm": 22.336946487426758,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3934,
+      "step": 36
+    },
+    {
+      "epoch": 0.014020794353788219,
+      "grad_norm": 37.155521392822266,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.5508,
+      "step": 37
+    },
+    {
+      "epoch": 0.014399734741728442,
+      "grad_norm": 24.519384384155273,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4562,
+      "step": 38
+    },
+    {
+      "epoch": 0.014778675129668664,
+      "grad_norm": 16.592533111572266,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1991,
+      "step": 39
+    },
+    {
+      "epoch": 0.015157615517608886,
+      "grad_norm": 16.430328369140625,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2824,
+      "step": 40
+    },
+    {
+      "epoch": 0.015536555905549108,
+      "grad_norm": 16.076345443725586,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2632,
+      "step": 41
+    },
+    {
+      "epoch": 0.01591549629348933,
+      "grad_norm": 15.423989295959473,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2627,
+      "step": 42
+    },
+    {
+      "epoch": 0.016294436681429554,
+      "grad_norm": 17.79759979248047,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3937,
+      "step": 43
+    },
+    {
+      "epoch": 0.016673377069369773,
+      "grad_norm": 17.390098571777344,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3232,
+      "step": 44
+    },
+    {
+      "epoch": 0.017052317457309996,
+      "grad_norm": 16.93052864074707,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2348,
+      "step": 45
+    },
+    {
+      "epoch": 0.01743125784525022,
+      "grad_norm": 17.974763870239258,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3418,
+      "step": 46
+    },
+    {
+      "epoch": 0.017810198233190442,
+      "grad_norm": 20.516761779785156,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2928,
+      "step": 47
+    },
+    {
+      "epoch": 0.018189138621130665,
+      "grad_norm": 19.835205078125,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4389,
+      "step": 48
+    },
+    {
+      "epoch": 0.018568079009070884,
+      "grad_norm": 30.226259231567383,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.348,
+      "step": 49
+    },
+    {
+      "epoch": 0.018947019397011107,
+      "grad_norm": 38.83269119262695,
+      "learning_rate": 0.0,
+      "loss": 2.4241,
+      "step": 50
+    },
+    {
+      "epoch": 0.018947019397011107,
+      "eval_loss": 2.28448224067688,
+      "eval_runtime": 1485.3063,
+      "eval_samples_per_second": 11.969,
+      "eval_steps_per_second": 1.497,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null