Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:503ff065ff52ba1abf2842ceca8e19c4f585d64b31efab2f46be2e365e1c918e
+oid sha256:fa04affb0975da68973ea8c546695406bd666c4181794ddcfb7d051d582a7207
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4b6cb3cec1511ee9210da76ec64fc2ba28f483f3153a76e83d8d1e4079daec
+oid sha256:1d13f83ef5507d1c7a52270409c80484c35d2fba797207ba72f4c478a8008d05
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f589cdc8adb695a9a26b669b4afed6a0acea4337ae464f7c4c015c70e1182a
+oid sha256:b34ffde75a9f5669e1c8a7e881b3110da5a1be84070f76d80f348434ba729ecf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f18fffb0e3a0ef336b47179743ab4126e50cd1f6b973081299b4ddb7dd17108
+oid sha256:b880929b96bf75acbc85f47d876c46d359fd62d1478ce33a372b0c060023cc3a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e3feeaf0cb2e18e2a639e1a4dbc0e4904c0909b9ea1c45912f8b1713d0de1d
+oid sha256:b0e4249ff6a680977c90ce618286998e69c58663c049a77e0ba9a6d23c96107e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898278affd6a9a4756a8d9bbe28e167dd71767815151ca235e3ea1cda09fa12a
+oid sha256:a2feaab34299e5d4c191dee1d96d761a6aeb502db66d24b986c68043182cfcbd
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af915b3bd1f4e2109b462a6794b6020da77edbf1d90b3213a0a05f6b1d4f617
+oid sha256:9a2759c51def6f12ecf076b0cf2571dc6049a636d579f7f0a8bd8ae37daff96c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8664895296096802,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.9047619047619047,
+  "epoch": 3.0476190476190474,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,111 @@
       "eval_samples_per_second": 51.662,
       "eval_steps_per_second": 6.966,
       "step": 25
+    },
+    {
+      "epoch": 1.980952380952381,
+      "grad_norm": 0.5163573622703552,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.8898,
+      "step": 26
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 1.372274398803711,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 1.63,
+      "step": 27
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.9707751274108887,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.8799,
+      "step": 28
+    },
+    {
+      "epoch": 2.2095238095238097,
+      "grad_norm": 0.9621633291244507,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 0.8554,
+      "step": 29
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.5492159128189087,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.8722,
+      "step": 30
+    },
+    {
+      "epoch": 2.361904761904762,
+      "grad_norm": 0.5442349314689636,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 0.8885,
+      "step": 31
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 0.5701318383216858,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.8383,
+      "step": 32
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.5509917736053467,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.8445,
+      "step": 33
+    },
+    {
+      "epoch": 2.5904761904761906,
+      "grad_norm": 0.4586718678474426,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.8689,
+      "step": 34
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.5567528009414673,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 0.8582,
+      "step": 35
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 1.0045620203018188,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.8702,
+      "step": 36
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 0.47573980689048767,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 0.8581,
+      "step": 37
+    },
+    {
+      "epoch": 2.895238095238095,
+      "grad_norm": 0.525488555431366,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.8556,
+      "step": 38
+    },
+    {
+      "epoch": 2.9714285714285715,
+      "grad_norm": 0.7117540836334229,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.857,
+      "step": 39
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 2.8340647220611572,
+      "learning_rate": 0.0,
+      "loss": 1.6132,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -221,12 +326,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.83042868150272e+16,
+  "total_flos": 1.2528685890404352e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null