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:e7d7fbc3bfaf68e21c78bf93f96cd54e9c4306667280b542d9ffbebb90b129d2
+oid sha256:9f33e1ccc3ab947ad91e5723bcd35b37e0e2851c6d1d0102699ba7caeb52dcc1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887344ce26fe51656955ddf95c6398f28e4bd07fdd7c820fce69042f0e38b5f5
+oid sha256:524c866e50744483539c27527bc09dacffc1a969e4add4d2685e7ee06e233c8c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d88b16c3b830b136152c4972b26076a44ff47b816a5097903f9510575e2299a
+oid sha256:0348576019facc2ffbf31c0764a282884c0ea8ae2bf33a1efadf72c9bf1981f1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de91d40674963eb3f440ae1fcf38070262203e6ab5adeec57f7d2fac3dec6fd
+oid sha256:e8c51bcf215fbf6aaf07a0302952f3593bc645bc78cbfb0b22cc55a1b840b37b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2150f069d080411529ad588be42ac3ef3830ee3f17c93ec24ea1d9b1dfa52e7b
+oid sha256:dd2be4f2486a52117e9895d2cb9366afb243f8b57fbf8003f080572c9e878465
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821ba9c125b4cbe7618b815f480b78ecf7c1aab3658838dea6dd5e351166aa7c
+oid sha256:d412a83e752ab00331865b581a09f6dd92e18f19360451ef5166c53d97525107
 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": 2.410325527191162,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.024466328215793014,
+  "best_metric": 2.396644353866577,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04893265643158603,
   "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": 14.389,
       "eval_steps_per_second": 3.741,
       "step": 25
+    },
+    {
+      "epoch": 0.025444981344424737,
+      "grad_norm": 0.19889217615127563,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1861,
+      "step": 26
+    },
+    {
+      "epoch": 0.026423634473056457,
+      "grad_norm": 0.24287927150726318,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.2757,
+      "step": 27
+    },
+    {
+      "epoch": 0.027402287601688176,
+      "grad_norm": 0.2795593738555908,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.3154,
+      "step": 28
+    },
+    {
+      "epoch": 0.0283809407303199,
+      "grad_norm": 0.307158499956131,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.3342,
+      "step": 29
+    },
+    {
+      "epoch": 0.029359593858951618,
+      "grad_norm": 0.3302345871925354,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.2589,
+      "step": 30
+    },
+    {
+      "epoch": 0.030338246987583337,
+      "grad_norm": 0.31997916102409363,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.291,
+      "step": 31
+    },
+    {
+      "epoch": 0.03131690011621506,
+      "grad_norm": 0.34045863151550293,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.2796,
+      "step": 32
+    },
+    {
+      "epoch": 0.03229555324484678,
+      "grad_norm": 0.3185667395591736,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.33,
+      "step": 33
+    },
+    {
+      "epoch": 0.0332742063734785,
+      "grad_norm": 0.3068499267101288,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.3097,
+      "step": 34
+    },
+    {
+      "epoch": 0.03425285950211022,
+      "grad_norm": 0.3778265118598938,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.3589,
+      "step": 35
+    },
+    {
+      "epoch": 0.035231512630741944,
+      "grad_norm": 0.3738100826740265,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.2939,
+      "step": 36
+    },
+    {
+      "epoch": 0.036210165759373664,
+      "grad_norm": 0.42966437339782715,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.3238,
+      "step": 37
+    },
+    {
+      "epoch": 0.03718881888800538,
+      "grad_norm": 0.18900859355926514,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.156,
+      "step": 38
+    },
+    {
+      "epoch": 0.0381674720166371,
+      "grad_norm": 0.18164923787117004,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2335,
+      "step": 39
+    },
+    {
+      "epoch": 0.03914612514526882,
+      "grad_norm": 0.2060445249080658,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.2695,
+      "step": 40
+    },
+    {
+      "epoch": 0.04012477827390054,
+      "grad_norm": 0.2239447981119156,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2437,
+      "step": 41
+    },
+    {
+      "epoch": 0.04110343140253227,
+      "grad_norm": 0.23141714930534363,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2309,
+      "step": 42
+    },
+    {
+      "epoch": 0.04208208453116399,
+      "grad_norm": 0.2500653862953186,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3043,
+      "step": 43
+    },
+    {
+      "epoch": 0.043060737659795706,
+      "grad_norm": 0.25972434878349304,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.2783,
+      "step": 44
+    },
+    {
+      "epoch": 0.044039390788427425,
+      "grad_norm": 0.2742820084095001,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.2897,
+      "step": 45
+    },
+    {
+      "epoch": 0.045018043917059145,
+      "grad_norm": 0.2878837585449219,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2736,
+      "step": 46
+    },
+    {
+      "epoch": 0.04599669704569087,
+      "grad_norm": 0.32029470801353455,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.3139,
+      "step": 47
+    },
+    {
+      "epoch": 0.04697535017432259,
+      "grad_norm": 0.37453824281692505,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.3575,
+      "step": 48
+    },
+    {
+      "epoch": 0.04795400330295431,
+      "grad_norm": 0.38911765813827515,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.2911,
+      "step": 49
+    },
+    {
+      "epoch": 0.04893265643158603,
+      "grad_norm": 0.4732091724872589,
+      "learning_rate": 1e-05,
+      "loss": 2.2883,
+      "step": 50
+    },
+    {
+      "epoch": 0.04893265643158603,
+      "eval_loss": 2.396644353866577,
+      "eval_runtime": 3.4758,
+      "eval_samples_per_second": 14.385,
+      "eval_steps_per_second": 3.74,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null