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:b5ca21a89a10c91632c6679bfe2332a7dbb06e75fa0d1706420c9e06fc2e2fce
+oid sha256:84d57282c8aaeb8d90648346452fc4b469375347135f2c44b313b0216d3d3bda
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c772de918757e1c9f42dcc980606915b66a141a2215b7d51350dc8c2d049261f
+oid sha256:83d5e6a6632ca495b832e91b6a42f6f5500843cd557fb685615ec3cfba40a160
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0abe8d3ca60aa55fef38412bb27afffa877782c0f0a3bc816e1268a38f49350e
+oid sha256:587b8885ea1e475fa6549dd648fd3c2b3415d55cb03b987d0a558bb1bfe45da0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f37d339241944c8127596a30855bbf1e6bdbbe9bf5d391bac85d710df37b06c
+oid sha256:19669ed83ea06d40370e8133e5cabaf29139583e92ad8b94902ef94003c33f14
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b61d6b1a33347c4e31e16a99966994b8610e66f9ef180203a700e9e8e8387c
+oid sha256:b5cbb8924d1c5a879016ecd04f1e3776bbf9947976190c3baf3a5eba3f8dd0ce
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34172be24ad8dadb2c66994c8143aadd22b7c21805946e38372bd7559a85291b
+oid sha256:fff163f147f8c4ddaedbf3dbc7b1dbdd541a1616e68267a1afc4bb43a522cc77
 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": 10.047934532165527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4483985765124556,
+  "best_metric": 9.844544410705566,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8967971530249113,
   "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": 967.694,
       "eval_steps_per_second": 123.012,
       "step": 25
+    },
+    {
+      "epoch": 1.5053380782918149,
+      "grad_norm": 38.16707229614258,
+      "learning_rate": 5e-05,
+      "loss": 10.0674,
+      "step": 26
+    },
+    {
+      "epoch": 1.5622775800711743,
+      "grad_norm": 39.47360610961914,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.0273,
+      "step": 27
+    },
+    {
+      "epoch": 1.6192170818505338,
+      "grad_norm": 41.1451530456543,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.0354,
+      "step": 28
+    },
+    {
+      "epoch": 1.6761565836298933,
+      "grad_norm": 37.08360290527344,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 9.9929,
+      "step": 29
+    },
+    {
+      "epoch": 1.7330960854092528,
+      "grad_norm": 42.404457092285156,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 9.9641,
+      "step": 30
+    },
+    {
+      "epoch": 1.790035587188612,
+      "grad_norm": 38.849552154541016,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 9.9485,
+      "step": 31
+    },
+    {
+      "epoch": 1.8469750889679717,
+      "grad_norm": 35.90088653564453,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 9.9368,
+      "step": 32
+    },
+    {
+      "epoch": 1.903914590747331,
+      "grad_norm": 39.651119232177734,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 9.9373,
+      "step": 33
+    },
+    {
+      "epoch": 1.9608540925266904,
+      "grad_norm": 39.915504455566406,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 9.9233,
+      "step": 34
+    },
+    {
+      "epoch": 2.0427046263345194,
+      "grad_norm": 35.5047492980957,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 9.8757,
+      "step": 35
+    },
+    {
+      "epoch": 2.099644128113879,
+      "grad_norm": 36.85204315185547,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 9.9016,
+      "step": 36
+    },
+    {
+      "epoch": 2.1565836298932384,
+      "grad_norm": 36.31344985961914,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 9.8718,
+      "step": 37
+    },
+    {
+      "epoch": 2.213523131672598,
+      "grad_norm": 36.17488098144531,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 9.8591,
+      "step": 38
+    },
+    {
+      "epoch": 2.2704626334519573,
+      "grad_norm": 36.54132080078125,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 9.884,
+      "step": 39
+    },
+    {
+      "epoch": 2.3274021352313166,
+      "grad_norm": 36.260841369628906,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 9.8633,
+      "step": 40
+    },
+    {
+      "epoch": 2.3843416370106763,
+      "grad_norm": 33.74192428588867,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 9.8713,
+      "step": 41
+    },
+    {
+      "epoch": 2.4412811387900355,
+      "grad_norm": 34.44586944580078,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 9.864,
+      "step": 42
+    },
+    {
+      "epoch": 2.498220640569395,
+      "grad_norm": 33.68125915527344,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 9.8672,
+      "step": 43
+    },
+    {
+      "epoch": 2.5551601423487544,
+      "grad_norm": 34.21220397949219,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 9.8374,
+      "step": 44
+    },
+    {
+      "epoch": 2.612099644128114,
+      "grad_norm": 36.1893424987793,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 9.8433,
+      "step": 45
+    },
+    {
+      "epoch": 2.6690391459074734,
+      "grad_norm": 36.4090690612793,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 9.8464,
+      "step": 46
+    },
+    {
+      "epoch": 2.7259786476868326,
+      "grad_norm": 32.83701705932617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 9.8167,
+      "step": 47
+    },
+    {
+      "epoch": 2.7829181494661923,
+      "grad_norm": 33.877655029296875,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 9.8623,
+      "step": 48
+    },
+    {
+      "epoch": 2.8398576512455516,
+      "grad_norm": 36.13532257080078,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 9.8472,
+      "step": 49
+    },
+    {
+      "epoch": 2.8967971530249113,
+      "grad_norm": 33.10332489013672,
+      "learning_rate": 0.0,
+      "loss": 9.8337,
+      "step": 50
+    },
+    {
+      "epoch": 2.8967971530249113,
+      "eval_loss": 9.844544410705566,
+      "eval_runtime": 0.1222,
+      "eval_samples_per_second": 965.317,
+      "eval_steps_per_second": 122.71,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null