Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ed488f0a937e6355e1442e36917666f0f42bd2786a7976233fc40e05c156c9
+oid sha256:4d8567c2fc430080a7024620884c41d5f5ec2c19066aa6fcae33a3465e2e729e
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd2faaa6d094734afc5b3009c6c797dc384b88db0b21ec66339bb5c199357012
+oid sha256:150db70ba763d96ac51bd8288c983fac55a9bf1f6ad3b015131544cc80f30439
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d874a7f142fa55444bed9fce0ace7a584516f772b036a7b3a402d652e03c02
+oid sha256:12e5283571d9b3f45733e5ab417726c9d8dbe9b7aeac1bc72baa511e3a691312
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3f33763d8fa920ddfcefc155c70eaf9c5fb8d8d31e02adece436d9ec47433d
+oid sha256:0970012159cf0dbcc290bc28f79381c8fbbf833075f5634838bb8e3852ef4bee
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3987c9b2e24547324adf613a494e0a5554ad70fdbf8add071209396228533a5a
+oid sha256:49f2a64efc5b63086df008d6ec1c93abe86a7b0a508acbc89f7a95ea2e9535c7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5adfad692fc9419a115615e932c232bc85a7a494b8c33cbe7764f12ad77957
+oid sha256:97a4f6cd89d46ebac6998bbd5c05becb38a46041c58f7fac99216dcc7a5d0fb9
 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": 3.2366089820861816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0906412871062769,
+  "best_metric": 3.121091365814209,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1812825742125538,
   "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": 24.552,
       "eval_steps_per_second": 3.079,
       "step": 25
+    },
+    {
+      "epoch": 0.09426693859052798,
+      "grad_norm": 5.509792327880859,
+      "learning_rate": 5e-05,
+      "loss": 3.1615,
+      "step": 26
+    },
+    {
+      "epoch": 0.09789259007477906,
+      "grad_norm": 8.197694778442383,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.0753,
+      "step": 27
+    },
+    {
+      "epoch": 0.10151824155903014,
+      "grad_norm": 1.9906346797943115,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.0005,
+      "step": 28
+    },
+    {
+      "epoch": 0.10514389304328121,
+      "grad_norm": 1.6515172719955444,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.149,
+      "step": 29
+    },
+    {
+      "epoch": 0.10876954452753229,
+      "grad_norm": 2.503220558166504,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.0762,
+      "step": 30
+    },
+    {
+      "epoch": 0.11239519601178337,
+      "grad_norm": 1.4713380336761475,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.1036,
+      "step": 31
+    },
+    {
+      "epoch": 0.11602084749603445,
+      "grad_norm": 1.6807591915130615,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.1145,
+      "step": 32
+    },
+    {
+      "epoch": 0.11964649898028552,
+      "grad_norm": 2.160545825958252,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.0805,
+      "step": 33
+    },
+    {
+      "epoch": 0.1232721504645366,
+      "grad_norm": 15.812837600708008,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.1181,
+      "step": 34
+    },
+    {
+      "epoch": 0.12689780194878766,
+      "grad_norm": 2.214811086654663,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.0835,
+      "step": 35
+    },
+    {
+      "epoch": 0.13052345343303876,
+      "grad_norm": 2.4301793575286865,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.2651,
+      "step": 36
+    },
+    {
+      "epoch": 0.13414910491728982,
+      "grad_norm": 3.295548677444458,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.2649,
+      "step": 37
+    },
+    {
+      "epoch": 0.1377747564015409,
+      "grad_norm": 2.6664798259735107,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1903,
+      "step": 38
+    },
+    {
+      "epoch": 0.14140040788579197,
+      "grad_norm": 1.2872811555862427,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.0828,
+      "step": 39
+    },
+    {
+      "epoch": 0.14502605937004306,
+      "grad_norm": 2.149052858352661,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.0371,
+      "step": 40
+    },
+    {
+      "epoch": 0.14865171085429413,
+      "grad_norm": 2.295020341873169,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.1058,
+      "step": 41
+    },
+    {
+      "epoch": 0.15227736233854522,
+      "grad_norm": 1.5253604650497437,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.099,
+      "step": 42
+    },
+    {
+      "epoch": 0.15590301382279628,
+      "grad_norm": 1.4826136827468872,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.0172,
+      "step": 43
+    },
+    {
+      "epoch": 0.15952866530704737,
+      "grad_norm": 2.7176144123077393,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.217,
+      "step": 44
+    },
+    {
+      "epoch": 0.16315431679129844,
+      "grad_norm": 1.5273343324661255,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.0648,
+      "step": 45
+    },
+    {
+      "epoch": 0.1667799682755495,
+      "grad_norm": 3.0926811695098877,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.0708,
+      "step": 46
+    },
+    {
+      "epoch": 0.1704056197598006,
+      "grad_norm": 1.7232677936553955,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.1711,
+      "step": 47
+    },
+    {
+      "epoch": 0.17403127124405166,
+      "grad_norm": 2.884068250656128,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.1643,
+      "step": 48
+    },
+    {
+      "epoch": 0.17765692272830275,
+      "grad_norm": 3.1874499320983887,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.1872,
+      "step": 49
+    },
+    {
+      "epoch": 0.1812825742125538,
+      "grad_norm": 4.788722991943359,
+      "learning_rate": 0.0,
+      "loss": 3.4839,
+      "step": 50
+    },
+    {
+      "epoch": 0.1812825742125538,
+      "eval_loss": 3.121091365814209,
+      "eval_runtime": 75.5847,
+      "eval_samples_per_second": 24.582,
+      "eval_steps_per_second": 3.083,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null