Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1e353bca2b8387e262dbc27bb9a6524d50289204ea6b0dd668e0905d7d3669
+oid sha256:3184e47ebdf7f6df1fbbe5941383575ce9b2e226651885435c5c9594e02c3f24
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19170c82f3e7ac0d2c41ace6aaaedd96ea3678d3812a35f2c158a7b5320f3817
+oid sha256:e083124038fc4c4368122a761ee428494360151c093885bdfca71a83f7891f16
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88b2c4e0834c3d93e23c085db66d87e6bd15c20b85fb79ae0998c5b611e72c7
+oid sha256:f496780c46ab842515a3aeda87bd305936758cefe5aa77fcc911c4930ea4cce7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb3f156c8c7f38175c7cd93d60b75542442a531c337c196cf86b6a001601a09
+oid sha256:19108c4f90ec367ae7310f82e44698d25b1cf2740ff6a317b79d4054b4dc4779
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b4c88195c8e20a912d84e31a5880afa654b4c688392179759ec2309043d36c
+oid sha256:4227bc8c93c42458b1ddd177e935432a6e31689570e1ed6f9d296ff6a2f378ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9093f3c6d8e62cb073ae76a0e8a5ef2a4cfe911aee2d96d0efc3f481da1f90e
+oid sha256:7793cbdb4a0a3dcbac3719f0109fe0cfb8de9fcf85d2aa23cd961c0b5679804e
 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": 2.2520217895507812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010366722819748608,
+  "best_metric": 2.1690759658813477,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020733445639497215,
   "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": 14.794,
       "eval_steps_per_second": 1.849,
       "step": 25
+    },
+    {
+      "epoch": 0.010781391732538552,
+      "grad_norm": 1.0906449556350708,
+      "learning_rate": 5e-05,
+      "loss": 2.43,
+      "step": 26
+    },
+    {
+      "epoch": 0.011196060645328496,
+      "grad_norm": 1.1582051515579224,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.4405,
+      "step": 27
+    },
+    {
+      "epoch": 0.01161072955811844,
+      "grad_norm": 1.1142066717147827,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.354,
+      "step": 28
+    },
+    {
+      "epoch": 0.012025398470908385,
+      "grad_norm": 1.0841790437698364,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3621,
+      "step": 29
+    },
+    {
+      "epoch": 0.01244006738369833,
+      "grad_norm": 0.9841034412384033,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.3249,
+      "step": 30
+    },
+    {
+      "epoch": 0.012854736296488273,
+      "grad_norm": 1.0224250555038452,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.2604,
+      "step": 31
+    },
+    {
+      "epoch": 0.013269405209278218,
+      "grad_norm": 0.8767861723899841,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1979,
+      "step": 32
+    },
+    {
+      "epoch": 0.013684074122068162,
+      "grad_norm": 0.8886589407920837,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.2309,
+      "step": 33
+    },
+    {
+      "epoch": 0.014098743034858105,
+      "grad_norm": 1.1102007627487183,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0605,
+      "step": 34
+    },
+    {
+      "epoch": 0.014513411947648049,
+      "grad_norm": 1.4647661447525024,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1955,
+      "step": 35
+    },
+    {
+      "epoch": 0.014928080860437993,
+      "grad_norm": 1.925478458404541,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1027,
+      "step": 36
+    },
+    {
+      "epoch": 0.015342749773227938,
+      "grad_norm": 2.8022842407226562,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0967,
+      "step": 37
+    },
+    {
+      "epoch": 0.015757418686017884,
+      "grad_norm": 0.7166653871536255,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3004,
+      "step": 38
+    },
+    {
+      "epoch": 0.016172087598807828,
+      "grad_norm": 0.7799428701400757,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.318,
+      "step": 39
+    },
+    {
+      "epoch": 0.016586756511597772,
+      "grad_norm": 0.7969001531600952,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2889,
+      "step": 40
+    },
+    {
+      "epoch": 0.017001425424387717,
+      "grad_norm": 0.7274399399757385,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2631,
+      "step": 41
+    },
+    {
+      "epoch": 0.01741609433717766,
+      "grad_norm": 0.7271828055381775,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2522,
+      "step": 42
+    },
+    {
+      "epoch": 0.017830763249967605,
+      "grad_norm": 0.7675609588623047,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2168,
+      "step": 43
+    },
+    {
+      "epoch": 0.01824543216275755,
+      "grad_norm": 0.7360167503356934,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1654,
+      "step": 44
+    },
+    {
+      "epoch": 0.018660101075547494,
+      "grad_norm": 0.7525986433029175,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2119,
+      "step": 45
+    },
+    {
+      "epoch": 0.019074769988337438,
+      "grad_norm": 0.8221715688705444,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1148,
+      "step": 46
+    },
+    {
+      "epoch": 0.019489438901127382,
+      "grad_norm": 0.8812233209609985,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.0394,
+      "step": 47
+    },
+    {
+      "epoch": 0.019904107813917327,
+      "grad_norm": 1.018441915512085,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.096,
+      "step": 48
+    },
+    {
+      "epoch": 0.02031877672670727,
+      "grad_norm": 1.3734047412872314,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1067,
+      "step": 49
+    },
+    {
+      "epoch": 0.020733445639497215,
+      "grad_norm": 2.5341591835021973,
+      "learning_rate": 0.0,
+      "loss": 2.0195,
+      "step": 50
+    },
+    {
+      "epoch": 0.020733445639497215,
+      "eval_loss": 2.1690759658813477,
+      "eval_runtime": 1096.4634,
+      "eval_samples_per_second": 14.818,
+      "eval_steps_per_second": 1.852,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null