Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b755921433dfe32e83ecccd6dc9950ab093a1181898d970077367505f6123a3a
+oid sha256:00cb040299ae5e8da0e42dfd28d7ed4c00a0c94f6e3cef1c51a54f086c34461c
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d9249914df3102728699c0c98fe7b17bdc0089474cccbd63b7d429fb5ef411
+oid sha256:e3c01ec97e6eb7ea09295331360fc870a0e15eda85fa04aaa1de458933f66307
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8710c8123bebff38ccc13aaf4c4006c2e29d4045c70980f284997e7ca266d45
+oid sha256:3154b8d965a998bfaf87407fb1fa491e64886e8993ccf4d5f0db53234f45a229
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83b29a4c27781859e3a450c7ee549f3b030dd83f93d97e60c5596d1ffb18df4
+oid sha256:ce6d3c9d3e8ca2671a6bbcf4bc7df1dbd3a00aa0519f1a5cc163ce0683485bc8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018665a1bb6a4ea27091053d45d06e24674dd6f061327cd94477895f351393b7
+oid sha256:a7b55ce5c587eb6c359720e4ceb07e932e887811000e3c64767a0b2a7e972ef7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d62048589179bbb6a539c3b102f8eb060de3babd551164595f6c2ec1065f837
+oid sha256:9b186065b89e44263839f3abe367a975cbd00677acd26569bc31096b2407ad16
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
+oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9449502229690552,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8493150684931505,
+  "epoch": 3.136986301369863,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 51.196,
       "eval_steps_per_second": 13.311,
       "step": 25
+    },
+    {
+      "epoch": 1.9223744292237441,
+      "grad_norm": 0.9425220489501953,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 2.0892,
+      "step": 26
+    },
+    {
+      "epoch": 2.018264840182648,
+      "grad_norm": 1.2423070669174194,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.944,
+      "step": 27
+    },
+    {
+      "epoch": 2.091324200913242,
+      "grad_norm": 0.7437182068824768,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 1.8443,
+      "step": 28
+    },
+    {
+      "epoch": 2.1643835616438354,
+      "grad_norm": 0.7723404765129089,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 1.8569,
+      "step": 29
+    },
+    {
+      "epoch": 2.237442922374429,
+      "grad_norm": 0.7458028793334961,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 1.5894,
+      "step": 30
+    },
+    {
+      "epoch": 2.3105022831050226,
+      "grad_norm": 0.8333907723426819,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 2.0206,
+      "step": 31
+    },
+    {
+      "epoch": 2.383561643835616,
+      "grad_norm": 0.7999001145362854,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.8319,
+      "step": 32
+    },
+    {
+      "epoch": 2.45662100456621,
+      "grad_norm": 0.8819563388824463,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 1.6749,
+      "step": 33
+    },
+    {
+      "epoch": 2.5296803652968034,
+      "grad_norm": 0.9369629621505737,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 1.8284,
+      "step": 34
+    },
+    {
+      "epoch": 2.602739726027397,
+      "grad_norm": 0.9049533605575562,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 1.8499,
+      "step": 35
+    },
+    {
+      "epoch": 2.6757990867579906,
+      "grad_norm": 0.8291096091270447,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 1.6656,
+      "step": 36
+    },
+    {
+      "epoch": 2.748858447488584,
+      "grad_norm": 0.933771550655365,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.7633,
+      "step": 37
+    },
+    {
+      "epoch": 2.821917808219178,
+      "grad_norm": 0.9030247330665588,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 1.8017,
+      "step": 38
+    },
+    {
+      "epoch": 2.8949771689497714,
+      "grad_norm": 0.9774025678634644,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 1.7459,
+      "step": 39
+    },
+    {
+      "epoch": 2.968036529680365,
+      "grad_norm": 1.4044599533081055,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 2.4792,
+      "step": 40
+    },
+    {
+      "epoch": 3.0639269406392695,
+      "grad_norm": 1.0370107889175415,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 1.9816,
+      "step": 41
+    },
+    {
+      "epoch": 3.136986301369863,
+      "grad_norm": 0.9146576523780823,
+      "learning_rate": 1e-05,
+      "loss": 1.7765,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.1240447254528e+16,
+  "total_flos": 1.3648395138760704e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null