Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a34f46e9a78a78c3293dc87dd004ed98de61f4487f76f9d105dce2f96b081de
+oid sha256:5350d8e72b425180d98b8f5dfef792598915263fd55ce4923d0b43e19162bcbc
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97aa93a7ab9d6ccdd5886f6a5c4ff735920a8b49bbc7171e3b7ce0ddc15c7e7d
+oid sha256:52bf05ac3d9c61b34ec8f12e90972d3287097f25e00a7da72e988ca8609fc557
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3625ba24000e7f6214cc5e80875a5bdcca2c873879d471233f3c65d6d3d91706
+oid sha256:83140b979ee3fa53fe0358e62bbb225258af47af4d713ba13686c284fe6c1b16
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd2cfa5094eb6d2209d188b69f501059d751488f3f6a67d02fac45892cde294
+oid sha256:48b3546366cea1175ea566c2f847a02d7284569e9f752f76e9e34a04be918f9e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6e2e5b2927bc22b66f79d0856de10329d56f957f277c70b24384ef14074996
+oid sha256:7868df55a74f69b87bb923c58371ff9ca8bb2c69db917ecfe75f1339959b2ff9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f413d19727bbbbaa0129f523495c7af94b1e13d8f3cf9b6a6a96e118c54525c5
+oid sha256:a0b07962a90c556d75f13278a577df56a3d0dd3d5c037438711c1128bd7ea836
 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": 1.0571568012237549,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3427592116538132,
+  "best_metric": 1.0213967561721802,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6855184233076264,
   "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": 21.595,
       "eval_steps_per_second": 5.615,
       "step": 25
+    },
+    {
+      "epoch": 0.3564695801199657,
+      "grad_norm": 0.3724190294742584,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8609,
+      "step": 26
+    },
+    {
+      "epoch": 0.37017994858611825,
+      "grad_norm": 0.3975992500782013,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8236,
+      "step": 27
+    },
+    {
+      "epoch": 0.3838903170522708,
+      "grad_norm": 0.4572630226612091,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8765,
+      "step": 28
+    },
+    {
+      "epoch": 0.3976006855184233,
+      "grad_norm": 0.5107871890068054,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8768,
+      "step": 29
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.6196900606155396,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9245,
+      "step": 30
+    },
+    {
+      "epoch": 0.4250214224507284,
+      "grad_norm": 0.6747974753379822,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.978,
+      "step": 31
+    },
+    {
+      "epoch": 0.4387317909168809,
+      "grad_norm": 0.6937869191169739,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.935,
+      "step": 32
+    },
+    {
+      "epoch": 0.4524421593830334,
+      "grad_norm": 0.7304213643074036,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.9434,
+      "step": 33
+    },
+    {
+      "epoch": 0.4661525278491859,
+      "grad_norm": 0.8814483880996704,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9642,
+      "step": 34
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 1.1520628929138184,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9072,
+      "step": 35
+    },
+    {
+      "epoch": 0.493573264781491,
+      "grad_norm": 1.8298850059509277,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0162,
+      "step": 36
+    },
+    {
+      "epoch": 0.5072836332476436,
+      "grad_norm": 1.9809646606445312,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9673,
+      "step": 37
+    },
+    {
+      "epoch": 0.5209940017137961,
+      "grad_norm": 0.39740994572639465,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9083,
+      "step": 38
+    },
+    {
+      "epoch": 0.5347043701799485,
+      "grad_norm": 0.3018646240234375,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8195,
+      "step": 39
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.3188331127166748,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7938,
+      "step": 40
+    },
+    {
+      "epoch": 0.5621251071122536,
+      "grad_norm": 0.35798129439353943,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.849,
+      "step": 41
+    },
+    {
+      "epoch": 0.5758354755784062,
+      "grad_norm": 0.4261307716369629,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8968,
+      "step": 42
+    },
+    {
+      "epoch": 0.5895458440445587,
+      "grad_norm": 0.4484318792819977,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8825,
+      "step": 43
+    },
+    {
+      "epoch": 0.6032562125107113,
+      "grad_norm": 0.5180601477622986,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.91,
+      "step": 44
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.621738851070404,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9466,
+      "step": 45
+    },
+    {
+      "epoch": 0.6306769494430163,
+      "grad_norm": 0.6436194777488708,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9237,
+      "step": 46
+    },
+    {
+      "epoch": 0.6443873179091688,
+      "grad_norm": 0.837110161781311,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9483,
+      "step": 47
+    },
+    {
+      "epoch": 0.6580976863753213,
+      "grad_norm": 1.1074998378753662,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0255,
+      "step": 48
+    },
+    {
+      "epoch": 0.6718080548414739,
+      "grad_norm": 1.4551877975463867,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0155,
+      "step": 49
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 1.933646559715271,
+      "learning_rate": 1e-05,
+      "loss": 0.8422,
+      "step": 50
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "eval_loss": 1.0213967561721802,
+      "eval_runtime": 2.3124,
+      "eval_samples_per_second": 21.623,
+      "eval_steps_per_second": 5.622,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null