Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9cdfef3079ea0ba4a23a121dab1e1a0985c940635cc9eb6043f3b499f5e34a
+oid sha256:e0deb531068307a393819252fdb58b1f90ab24f605bd1b1193a79c4c3249f62e
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccecfbc4e52d86139b7b3cb507b32ab369280b0f49c58ba464b3075746b5991
+oid sha256:46f3a2f4415b3e6ca3bc4642e6c05a2f6e764ad1c2dc86c689bf5754812fefe7
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2405dbb6e675eb899b5d7e95731efd9bc615a481e967e46def4ce21f5cfc45
+oid sha256:cba95f40bd1260ce16815e8a09df2c11320213c3bf350b743b1600080448675e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575cb40db917dc995933edcb3bae4a328b285a7c4690e796c98f269cc6f32e7b
+oid sha256:251be627239cc1232cccb83feceda02bebbd3e1b238381ee68c5e903af258d59
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23771d891219296fa6f0941ada22cb899e63d576b8a2ba409e40e2042058d07
+oid sha256:800375b07d149e87a004ed6c88c73a4e8b691b19830b36ee60daa99935d4e6a2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6916732684e1bc022cace20be8f8b625d657fc4786cf6f176fa51062a22045e
+oid sha256:dfa235ec737731a3331d2ef8a5e7a3fe3d83b87b2981544782b26f30d9d32201
 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": 1.027244210243225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.025547678354729514,
+  "best_metric": 1.0231027603149414,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05109535670945903,
   "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": 50.414,
       "eval_steps_per_second": 13.108,
       "step": 25
+    },
+    {
+      "epoch": 0.026569585488918693,
+      "grad_norm": 0.10399110615253448,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9921,
+      "step": 26
+    },
+    {
+      "epoch": 0.027591492623107877,
+      "grad_norm": 0.11868777126073837,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.953,
+      "step": 27
+    },
+    {
+      "epoch": 0.028613399757297056,
+      "grad_norm": 0.08569394052028656,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0039,
+      "step": 28
+    },
+    {
+      "epoch": 0.029635306891486236,
+      "grad_norm": 0.08266085386276245,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9993,
+      "step": 29
+    },
+    {
+      "epoch": 0.030657214025675415,
+      "grad_norm": 0.08436281234025955,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9719,
+      "step": 30
+    },
+    {
+      "epoch": 0.0316791211598646,
+      "grad_norm": 0.07534889131784439,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9922,
+      "step": 31
+    },
+    {
+      "epoch": 0.032701028294053774,
+      "grad_norm": 0.0886206105351448,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9549,
+      "step": 32
+    },
+    {
+      "epoch": 0.03372293542824296,
+      "grad_norm": 0.12971074879169464,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0573,
+      "step": 33
+    },
+    {
+      "epoch": 0.03474484256243214,
+      "grad_norm": 0.10268256813287735,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0629,
+      "step": 34
+    },
+    {
+      "epoch": 0.03576674969662132,
+      "grad_norm": 0.13337336480617523,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0963,
+      "step": 35
+    },
+    {
+      "epoch": 0.0367886568308105,
+      "grad_norm": 0.16662007570266724,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0929,
+      "step": 36
+    },
+    {
+      "epoch": 0.03781056396499968,
+      "grad_norm": 0.1939576119184494,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1368,
+      "step": 37
+    },
+    {
+      "epoch": 0.03883247109918886,
+      "grad_norm": 0.10542629659175873,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9937,
+      "step": 38
+    },
+    {
+      "epoch": 0.03985437823337804,
+      "grad_norm": 0.07947812229394913,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9395,
+      "step": 39
+    },
+    {
+      "epoch": 0.040876285367567225,
+      "grad_norm": 0.07600011676549911,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.0418981925017564,
+      "grad_norm": 0.08075827360153198,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0617,
+      "step": 41
+    },
+    {
+      "epoch": 0.042920099635945584,
+      "grad_norm": 0.08019677549600601,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0343,
+      "step": 42
+    },
+    {
+      "epoch": 0.04394200677013477,
+      "grad_norm": 0.0765736997127533,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9314,
+      "step": 43
+    },
+    {
+      "epoch": 0.04496391390432394,
+      "grad_norm": 0.083722323179245,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0294,
+      "step": 44
+    },
+    {
+      "epoch": 0.045985821038513126,
+      "grad_norm": 0.08264289796352386,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9393,
+      "step": 45
+    },
+    {
+      "epoch": 0.0470077281727023,
+      "grad_norm": 0.09311388432979584,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0048,
+      "step": 46
+    },
+    {
+      "epoch": 0.048029635306891486,
+      "grad_norm": 0.11415554583072662,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0739,
+      "step": 47
+    },
+    {
+      "epoch": 0.04905154244108067,
+      "grad_norm": 0.1320764273405075,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0266,
+      "step": 48
+    },
+    {
+      "epoch": 0.050073449575269845,
+      "grad_norm": 0.16924385726451874,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.1562,
+      "step": 49
+    },
+    {
+      "epoch": 0.05109535670945903,
+      "grad_norm": 0.23526246845722198,
+      "learning_rate": 1e-05,
+      "loss": 1.2363,
+      "step": 50
+    },
+    {
+      "epoch": 0.05109535670945903,
+      "eval_loss": 1.0231027603149414,
+      "eval_runtime": 0.9849,
+      "eval_samples_per_second": 50.766,
+      "eval_steps_per_second": 13.199,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null