Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e72d9ca1c1de115c304b0b201b8a737631fcca1578aeb0f06e808317835e406
+oid sha256:9bd641fba65a9c92c8f8b7d7f8ea8e6e54345969f9c50899cd1fec67a7f00400
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b01ce726f47a9405ce9cd91341e6b13ae67f87a72d83dbfc0d5435b598e9a0
+oid sha256:c79026057a1e3229cde3a764a3ca4d45e23c246caad6f8191961aa57da7f0cd5
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3545d82ac4c1aabcd6f41a90a8f7e2ac28a97901270a5622cc7c605e8dc3398c
+oid sha256:41c4bc92cb659934e496f1de4d82928ffcb498759cff59710f9e0af1d01ee7d9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b56455dc5f30216de65c9509db47e9c42c32160a4f226004574e13e8a2d55fc
+oid sha256:82419b09ee2b8c6f8390405b1ee64e8acf86192e51b494f0c3137b82ae78d5df
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89eff97692e7fb1f8f985ad2a6ce5fc965c501a8cf6b7e38e1af9da1cc495208
+oid sha256:f7d937e2dd9748788700fa1b14c4384b47a19e92f816ad0ae0e8caad24972a00
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6726a0b49526fff4d0b8158c0876731c82fae441b7a84122c6eac4455d775fc2
+oid sha256:e884ca004bef459c2f54483bb6228f5639eb1d403b100d108a1b72295e409a9e
 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": 0.4245308041572571,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.042923060414207535,
+  "best_metric": 0.4081031084060669,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08584612082841507,
   "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": 34.093,
       "eval_steps_per_second": 8.864,
       "step": 25
+    },
+    {
+      "epoch": 0.04463998283077583,
+      "grad_norm": 0.21593862771987915,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3316,
+      "step": 26
+    },
+    {
+      "epoch": 0.046356905247344135,
+      "grad_norm": 0.24882915616035461,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4051,
+      "step": 27
+    },
+    {
+      "epoch": 0.04807382766391244,
+      "grad_norm": 0.25821322202682495,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4135,
+      "step": 28
+    },
+    {
+      "epoch": 0.049790750080480735,
+      "grad_norm": 0.2826606333255768,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4407,
+      "step": 29
+    },
+    {
+      "epoch": 0.05150767249704904,
+      "grad_norm": 0.2720731198787689,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4301,
+      "step": 30
+    },
+    {
+      "epoch": 0.05322459491361734,
+      "grad_norm": 0.27546319365501404,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4239,
+      "step": 31
+    },
+    {
+      "epoch": 0.054941517330185645,
+      "grad_norm": 0.28127309679985046,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.449,
+      "step": 32
+    },
+    {
+      "epoch": 0.05665843974675394,
+      "grad_norm": 0.29469725489616394,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4422,
+      "step": 33
+    },
+    {
+      "epoch": 0.058375362163322245,
+      "grad_norm": 0.32133859395980835,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4467,
+      "step": 34
+    },
+    {
+      "epoch": 0.06009228457989055,
+      "grad_norm": 0.31768831610679626,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4535,
+      "step": 35
+    },
+    {
+      "epoch": 0.061809206996458844,
+      "grad_norm": 0.3453242778778076,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4698,
+      "step": 36
+    },
+    {
+      "epoch": 0.06352612941302715,
+      "grad_norm": 0.388174831867218,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4149,
+      "step": 37
+    },
+    {
+      "epoch": 0.06524305182959544,
+      "grad_norm": 0.2139841616153717,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3314,
+      "step": 38
+    },
+    {
+      "epoch": 0.06695997424616375,
+      "grad_norm": 0.2043762505054474,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.372,
+      "step": 39
+    },
+    {
+      "epoch": 0.06867689666273205,
+      "grad_norm": 0.22525262832641602,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4039,
+      "step": 40
+    },
+    {
+      "epoch": 0.07039381907930035,
+      "grad_norm": 0.23101642727851868,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3862,
+      "step": 41
+    },
+    {
+      "epoch": 0.07211074149586866,
+      "grad_norm": 0.2495206594467163,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4331,
+      "step": 42
+    },
+    {
+      "epoch": 0.07382766391243696,
+      "grad_norm": 0.24867644906044006,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4008,
+      "step": 43
+    },
+    {
+      "epoch": 0.07554458632900526,
+      "grad_norm": 0.2708423435688019,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4429,
+      "step": 44
+    },
+    {
+      "epoch": 0.07726150874557355,
+      "grad_norm": 0.27113476395606995,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4277,
+      "step": 45
+    },
+    {
+      "epoch": 0.07897843116214186,
+      "grad_norm": 0.27955588698387146,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4675,
+      "step": 46
+    },
+    {
+      "epoch": 0.08069535357871016,
+      "grad_norm": 0.28158727288246155,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4287,
+      "step": 47
+    },
+    {
+      "epoch": 0.08241227599527846,
+      "grad_norm": 0.3091404438018799,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4544,
+      "step": 48
+    },
+    {
+      "epoch": 0.08412919841184677,
+      "grad_norm": 0.3447839319705963,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4569,
+      "step": 49
+    },
+    {
+      "epoch": 0.08584612082841507,
+      "grad_norm": 0.4188736081123352,
+      "learning_rate": 1e-05,
+      "loss": 0.4265,
+      "step": 50
+    },
+    {
+      "epoch": 0.08584612082841507,
+      "eval_loss": 0.4081031084060669,
+      "eval_runtime": 1.4601,
+      "eval_samples_per_second": 34.245,
+      "eval_steps_per_second": 8.904,
+      "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": 7.952285976808653e+16,
+  "total_flos": 1.5899604877626573e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null