Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7c77e73b36c7488dd0f2f935735cd178fe019e61d501323d3b9ff0f2fdda00
+oid sha256:f96377ef93e03b2317e742622c67a1fd7f77e34f61467f438f75e93670794491
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a16a51fd3b8eb645356e21062862ac98ae51139335f409c546777eefd314674
+oid sha256:71641cd0f4a94e873b8aab150d9877c32a07208a8af0d8f97f90569bb2b646d4
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a53237c0d4e72d11f0d810615e06f88f74a86d72914e9bba80627295f860aae
+oid sha256:1b634b3ce9c505a5a6ce482b0ae49120d1a6376d47493f2953da067c34559072
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b15a3c7632c5d3ee3210413f204f91ebd90d9788aac5613eb60755cd6b595b
+oid sha256:030b36924e2445d3368d4dc923d73a1a5aa7792d87b39e17c599667828cdb989
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8512f7f2240695befb047f7906dba5118d4c6e98c266d768c18dd803e76186c1
+oid sha256:17ab4ff77e2d386a9576c5adfb4869cd3bd62f629a0558906b0db072965a0a93
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488227531a416b28bd7c4bd32e2abf5c02dea1a48c2872dad6860a510a8fbf71
+oid sha256:16567f77043bc81a203e23e93beaf74122a69a62425d544aa8dafbd9c3dc18dc
 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": 11.070521354675293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15552099533437014,
+  "best_metric": 11.060905456542969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3110419906687403,
   "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": 595.63,
       "eval_steps_per_second": 154.864,
       "step": 25
+    },
+    {
+      "epoch": 0.16174183514774496,
+      "grad_norm": 2.573197364807129,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 177.1141,
+      "step": 26
+    },
+    {
+      "epoch": 0.16796267496111975,
+      "grad_norm": 2.4286153316497803,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 177.0893,
+      "step": 27
+    },
+    {
+      "epoch": 0.17418351477449456,
+      "grad_norm": 2.4644172191619873,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 177.134,
+      "step": 28
+    },
+    {
+      "epoch": 0.18040435458786935,
+      "grad_norm": 2.417313575744629,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 177.1395,
+      "step": 29
+    },
+    {
+      "epoch": 0.18662519440124417,
+      "grad_norm": 2.416379690170288,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 177.0807,
+      "step": 30
+    },
+    {
+      "epoch": 0.19284603421461896,
+      "grad_norm": 2.5380895137786865,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 177.1028,
+      "step": 31
+    },
+    {
+      "epoch": 0.19906687402799378,
+      "grad_norm": 2.898738384246826,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 177.0989,
+      "step": 32
+    },
+    {
+      "epoch": 0.2052877138413686,
+      "grad_norm": 2.7243590354919434,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 177.0639,
+      "step": 33
+    },
+    {
+      "epoch": 0.2115085536547434,
+      "grad_norm": 2.8405022621154785,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 177.0149,
+      "step": 34
+    },
+    {
+      "epoch": 0.2177293934681182,
+      "grad_norm": 3.0282528400421143,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 177.0964,
+      "step": 35
+    },
+    {
+      "epoch": 0.223950233281493,
+      "grad_norm": 3.221609354019165,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 177.0643,
+      "step": 36
+    },
+    {
+      "epoch": 0.2301710730948678,
+      "grad_norm": 3.1520352363586426,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 177.0723,
+      "step": 37
+    },
+    {
+      "epoch": 0.2363919129082426,
+      "grad_norm": 2.7963945865631104,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 177.02,
+      "step": 38
+    },
+    {
+      "epoch": 0.24261275272161742,
+      "grad_norm": 2.6416287422180176,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 177.0288,
+      "step": 39
+    },
+    {
+      "epoch": 0.24883359253499224,
+      "grad_norm": 2.5692756175994873,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 177.0617,
+      "step": 40
+    },
+    {
+      "epoch": 0.25505443234836706,
+      "grad_norm": 2.6899027824401855,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 177.0123,
+      "step": 41
+    },
+    {
+      "epoch": 0.26127527216174184,
+      "grad_norm": 2.611703634262085,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 177.0352,
+      "step": 42
+    },
+    {
+      "epoch": 0.26749611197511663,
+      "grad_norm": 2.60444712638855,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 177.0187,
+      "step": 43
+    },
+    {
+      "epoch": 0.2737169517884914,
+      "grad_norm": 2.7920703887939453,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 177.0074,
+      "step": 44
+    },
+    {
+      "epoch": 0.27993779160186627,
+      "grad_norm": 2.844726085662842,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 177.0748,
+      "step": 45
+    },
+    {
+      "epoch": 0.28615863141524106,
+      "grad_norm": 2.7402775287628174,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 176.9944,
+      "step": 46
+    },
+    {
+      "epoch": 0.29237947122861585,
+      "grad_norm": 2.834357976913452,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 176.9829,
+      "step": 47
+    },
+    {
+      "epoch": 0.2986003110419907,
+      "grad_norm": 3.010420083999634,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 177.0303,
+      "step": 48
+    },
+    {
+      "epoch": 0.3048211508553655,
+      "grad_norm": 2.935134172439575,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 176.9928,
+      "step": 49
+    },
+    {
+      "epoch": 0.3110419906687403,
+      "grad_norm": 3.591810703277588,
+      "learning_rate": 1e-05,
+      "loss": 176.9746,
+      "step": 50
+    },
+    {
+      "epoch": 0.3110419906687403,
+      "eval_loss": 11.060905456542969,
+      "eval_runtime": 0.0828,
+      "eval_samples_per_second": 603.794,
+      "eval_steps_per_second": 156.986,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null