Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58637f646021f026f9948e5e5fa40b59acd733b7b70763c508fbd20ebbb6615f
+oid sha256:3d34030ebe838578e51a97e314cd4e9dd782ad7b54d15f6669ec726a912485d0
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4bc9ea0093b6e177fd7f7de87470d744c828e46fd6d8a2093429a4f9607f94
+oid sha256:dfe43ded61b12a21907fcc4c07c8230762c9c65d91bd05ba3673eb38fb119ce4
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097972ff701e3c593c36e534e5474f72cbdbdc7cb8c32dff998b7b7a5412f826
+oid sha256:d94dc85657d2f148354682eac4b8957c0c8d0714763142633a70dbbb5b92288d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ac7e857ee22a37440f01d80119e56313523694505f4305361f2953ee483b03
+oid sha256:423dcca70ad847cea2ad6f5c82f15371953e35d514ce9bcd1c3738b1175e76fc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:725f748f3209e9421acf4c4e8e99152535a904fbeb3df37330f81dfa556a7aa2
+oid sha256:82e9b73f38c4c7b3bfc1a14bc48c5615b95f6de16f6b18ac61cd58c23aaebd39
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31eeb852472f791a10ec9a4ffb7e7af065564b37a05c0d272e99bc1cba5e310e
+oid sha256:8acb2288979dcfff126632b1e12a8d6a1ea8ec8aba682d8240b94c77b6692591
 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": 1.6209503412246704,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16999575010624735,
+  "best_metric": 1.527787685394287,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3399915002124947,
   "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": 14.621,
       "eval_steps_per_second": 3.801,
       "step": 25
+    },
+    {
+      "epoch": 0.17679558011049723,
+      "grad_norm": 0.4149613082408905,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5519,
+      "step": 26
+    },
+    {
+      "epoch": 0.18359541011474714,
+      "grad_norm": 0.39556705951690674,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5136,
+      "step": 27
+    },
+    {
+      "epoch": 0.19039524011899703,
+      "grad_norm": 0.3815109431743622,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5095,
+      "step": 28
+    },
+    {
+      "epoch": 0.1971950701232469,
+      "grad_norm": 0.29904016852378845,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.4106,
+      "step": 29
+    },
+    {
+      "epoch": 0.20399490012749683,
+      "grad_norm": 0.30246588587760925,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3192,
+      "step": 30
+    },
+    {
+      "epoch": 0.2107947301317467,
+      "grad_norm": 0.301662802696228,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2347,
+      "step": 31
+    },
+    {
+      "epoch": 0.2175945601359966,
+      "grad_norm": 0.29702726006507874,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3073,
+      "step": 32
+    },
+    {
+      "epoch": 0.22439439014024648,
+      "grad_norm": 0.3229938745498657,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3189,
+      "step": 33
+    },
+    {
+      "epoch": 0.2311942201444964,
+      "grad_norm": 0.3404196500778198,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4107,
+      "step": 34
+    },
+    {
+      "epoch": 0.23799405014874628,
+      "grad_norm": 0.41550806164741516,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.3458,
+      "step": 35
+    },
+    {
+      "epoch": 0.24479388015299616,
+      "grad_norm": 0.46461188793182373,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5456,
+      "step": 36
+    },
+    {
+      "epoch": 0.2515937101572461,
+      "grad_norm": 0.6510084867477417,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5994,
+      "step": 37
+    },
+    {
+      "epoch": 0.25839354016149596,
+      "grad_norm": 0.38543900847435,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5238,
+      "step": 38
+    },
+    {
+      "epoch": 0.26519337016574585,
+      "grad_norm": 0.26357683539390564,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5447,
+      "step": 39
+    },
+    {
+      "epoch": 0.27199320016999573,
+      "grad_norm": 0.26030537486076355,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5315,
+      "step": 40
+    },
+    {
+      "epoch": 0.27879303017424567,
+      "grad_norm": 0.2664230763912201,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4162,
+      "step": 41
+    },
+    {
+      "epoch": 0.28559286017849556,
+      "grad_norm": 0.2548981308937073,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3392,
+      "step": 42
+    },
+    {
+      "epoch": 0.29239269018274544,
+      "grad_norm": 0.2501774728298187,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2559,
+      "step": 43
+    },
+    {
+      "epoch": 0.2991925201869953,
+      "grad_norm": 0.2650240957736969,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2541,
+      "step": 44
+    },
+    {
+      "epoch": 0.3059923501912452,
+      "grad_norm": 0.2973995804786682,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2218,
+      "step": 45
+    },
+    {
+      "epoch": 0.3127921801954951,
+      "grad_norm": 0.3280287981033325,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2937,
+      "step": 46
+    },
+    {
+      "epoch": 0.319592010199745,
+      "grad_norm": 0.3540947437286377,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4076,
+      "step": 47
+    },
+    {
+      "epoch": 0.3263918402039949,
+      "grad_norm": 0.4255731701850891,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4754,
+      "step": 48
+    },
+    {
+      "epoch": 0.3331916702082448,
+      "grad_norm": 0.5464865565299988,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5759,
+      "step": 49
+    },
+    {
+      "epoch": 0.3399915002124947,
+      "grad_norm": 0.886528491973877,
+      "learning_rate": 1e-05,
+      "loss": 1.7149,
+      "step": 50
+    },
+    {
+      "epoch": 0.3399915002124947,
+      "eval_loss": 1.527787685394287,
+      "eval_runtime": 3.3947,
+      "eval_samples_per_second": 14.729,
+      "eval_steps_per_second": 3.829,
+      "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": 2.7698250104858214e+17,
+  "total_flos": 5.513049055124521e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null