Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d228dd44e7411b401527998adca67534aac05412a7affae634160c9f9e3dcc
+oid sha256:7ef3336a1efd1d21d16d11234ec58229e9c5c104341e1e15955ef7239418944f
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181651d3a6e9e125e28cbd383237bf4ea15463f24bfe5be3e08a510ba27b6b10
+oid sha256:dc31523cacb60c9fcf83923d5e4619e7e555e70a39d9ac6e4834646e2ba7e2fb
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd70df1d68255e2d46c7e953275d78bbd67729b5bd254b907b675983eacc881e
+oid sha256:7d946895f5d29bac50735453d0a7b3abe1a0384ebb785d60426931b846dd3239
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3369f0b5e4e693678f391f21bf2d8f01954b5a7711b3299660489dbc8d9ceb77
+oid sha256:3fe607e5c0c967e4d7569e162ef111c4b70339edce85d416b2ef78d4950a36b7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b013257d812fcea47d5c416e8d3ef573879a87ba432f0e508e924282ad247a
+oid sha256:9641c859122f1af64563e5e054cd0ea5b0728f7171f8a8e7566a937c1ca98e9a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f5996d2818435d741a355159beefe5504c41c3af00ca430f20b2552dc6ff1a
+oid sha256:dd91781236ac1aefe6a572e80dae11d449a636b3dd693f223fb3ded6556a6a88
 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": 0.9141214489936829,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0369139904023625,
+  "best_metric": 0.8821292519569397,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.073827980804725,
   "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": 34.806,
       "eval_steps_per_second": 4.356,
       "step": 25
+    },
+    {
+      "epoch": 0.038390550018456995,
+      "grad_norm": 0.15258188545703888,
+      "learning_rate": 5e-05,
+      "loss": 1.0821,
+      "step": 26
+    },
+    {
+      "epoch": 0.03986710963455149,
+      "grad_norm": 0.16078627109527588,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9651,
+      "step": 27
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 0.16188524663448334,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.821,
+      "step": 28
+    },
+    {
+      "epoch": 0.042820228866740494,
+      "grad_norm": 0.17332187294960022,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9002,
+      "step": 29
+    },
+    {
+      "epoch": 0.044296788482835,
+      "grad_norm": 0.18269848823547363,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7494,
+      "step": 30
+    },
+    {
+      "epoch": 0.045773348098929495,
+      "grad_norm": 0.17247238755226135,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6904,
+      "step": 31
+    },
+    {
+      "epoch": 0.04724990771502399,
+      "grad_norm": 0.18827833235263824,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6211,
+      "step": 32
+    },
+    {
+      "epoch": 0.048726467331118496,
+      "grad_norm": 0.2117096185684204,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6906,
+      "step": 33
+    },
+    {
+      "epoch": 0.05020302694721299,
+      "grad_norm": 0.23306560516357422,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.678,
+      "step": 34
+    },
+    {
+      "epoch": 0.05167958656330749,
+      "grad_norm": 0.267149418592453,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7681,
+      "step": 35
+    },
+    {
+      "epoch": 0.053156146179401995,
+      "grad_norm": 0.34443435072898865,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8942,
+      "step": 36
+    },
+    {
+      "epoch": 0.05463270579549649,
+      "grad_norm": 0.545831561088562,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2254,
+      "step": 37
+    },
+    {
+      "epoch": 0.056109265411590996,
+      "grad_norm": 0.193207785487175,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1269,
+      "step": 38
+    },
+    {
+      "epoch": 0.05758582502768549,
+      "grad_norm": 0.16855843365192413,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0996,
+      "step": 39
+    },
+    {
+      "epoch": 0.05906238464377999,
+      "grad_norm": 0.14967533946037292,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9894,
+      "step": 40
+    },
+    {
+      "epoch": 0.060538944259874494,
+      "grad_norm": 0.1433860808610916,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8061,
+      "step": 41
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 0.14255517721176147,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8361,
+      "step": 42
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.14755815267562866,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6904,
+      "step": 43
+    },
+    {
+      "epoch": 0.06496862310815799,
+      "grad_norm": 0.16876764595508575,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6982,
+      "step": 44
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "grad_norm": 0.1740587055683136,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7029,
+      "step": 45
+    },
+    {
+      "epoch": 0.067921742340347,
+      "grad_norm": 0.19714155793190002,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6876,
+      "step": 46
+    },
+    {
+      "epoch": 0.06939830195644149,
+      "grad_norm": 0.21021583676338196,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6576,
+      "step": 47
+    },
+    {
+      "epoch": 0.07087486157253599,
+      "grad_norm": 0.2548488974571228,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7183,
+      "step": 48
+    },
+    {
+      "epoch": 0.07235142118863049,
+      "grad_norm": 0.34631800651550293,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8755,
+      "step": 49
+    },
+    {
+      "epoch": 0.073827980804725,
+      "grad_norm": 0.8000274896621704,
+      "learning_rate": 0.0,
+      "loss": 1.6595,
+      "step": 50
+    },
+    {
+      "epoch": 0.073827980804725,
+      "eval_loss": 0.8821292519569397,
+      "eval_runtime": 130.0288,
+      "eval_samples_per_second": 35.092,
+      "eval_steps_per_second": 4.391,
+      "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": 2.8155439495092634e+17,
+  "total_flos": 5.6328454211108864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null