Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
-    "gate_proj",
     "o_proj",
     "k_proj",
+    "up_proj",
     "q_proj",
-    "up_proj"
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3229b13aec8e554939ae868f44d11c8994096d915dc423d4a032382e98a6b0ee
+oid sha256:e8ac35ef4906846f50efeb09ce60285bb7bd4392908141f6652a48a6b1c6a0b9
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0503bd06a639e3e95ed5365c58d7e5b18832a669133c6860fb35cec1889d090b
+oid sha256:15eff17c98397db8d51379881b80b2fe8dd8d5d565f410a816fccb04d784283d
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f173470e8ba136a19bd8bd44677e1a71ba04e70d18d56cf7ed62d50a3c4e13
+oid sha256:398d202d570348cb3612bda2bd902e6cf5677d1e4c30b987f82ffe1db108cdb9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4390b71d7af64dde19645aad65c80eac1055eb78e8f66bd359bbdafb2b859881
+oid sha256:29dd67dc8ca7b699874389fb88dcedea61d68b6350d38ab9d6f7d05af33938d8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508ca0d4e54b0df7770e3d0595cf3897910348491e3ea1788e30f775dc81bc7f
+oid sha256:48a59ac1c9cc4b5b125b431bd46a56746308461e0566b60b14a91b33d539de6c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7381d74bbea5eaa1a71bf292d334218d7ccba17d90eb4ff9f68fcb6277efbeee
+oid sha256:adfac5e3716d1c6ab4ad4605e7e3344aa08b4c780d49849cba1ef00c1863042d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 1.1054987907409668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6451612903225806,
+  "best_metric": 1.0583925247192383,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2903225806451613,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025806451612903226,
-      "grad_norm": 0.8154280185699463,
+      "grad_norm": 0.8232128024101257,
       "learning_rate": 5e-05,
       "loss": 2.036,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.025806451612903226,
       "eval_loss": 1.9736554622650146,
-      "eval_runtime": 3.0347,
-      "eval_samples_per_second": 86.334,
-      "eval_steps_per_second": 10.874,
+      "eval_runtime": 3.0038,
+      "eval_samples_per_second": 87.224,
+      "eval_steps_per_second": 10.986,
       "step": 1
     },
     {
       "epoch": 0.05161290322580645,
-      "grad_norm": 0.9636016488075256,
+      "grad_norm": 0.9790971875190735,
       "learning_rate": 0.0001,
       "loss": 1.953,
       "step": 2
     },
     {
       "epoch": 0.07741935483870968,
-      "grad_norm": 1.0712406635284424,
+      "grad_norm": 1.0968680381774902,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.8551,
+      "loss": 1.8547,
       "step": 3
     },
     {
       "epoch": 0.1032258064516129,
-      "grad_norm": 0.9042462110519409,
+      "grad_norm": 0.9214650392532349,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.6841,
+      "loss": 1.6842,
       "step": 4
     },
     {
       "epoch": 0.12903225806451613,
-      "grad_norm": 0.9828581809997559,
+      "grad_norm": 0.9923097491264343,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.4698,
+      "loss": 1.4695,
       "step": 5
     },
     {
       "epoch": 0.15483870967741936,
-      "grad_norm": 1.0596216917037964,
+      "grad_norm": 1.0702646970748901,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.4499,
+      "loss": 1.4507,
       "step": 6
     },
     {
       "epoch": 0.18064516129032257,
-      "grad_norm": 1.1427077054977417,
+      "grad_norm": 1.1556005477905273,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.3559,
+      "loss": 1.3562,
       "step": 7
     },
     {
       "epoch": 0.2064516129032258,
-      "grad_norm": 1.011368751525879,
+      "grad_norm": 1.0237374305725098,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.2267,
+      "loss": 1.2262,
       "step": 8
     },
     {
       "epoch": 0.23225806451612904,
-      "grad_norm": 0.8033608794212341,
+      "grad_norm": 0.8062003254890442,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.9945,
+      "loss": 0.9942,
       "step": 9
     },
     {
       "epoch": 0.25806451612903225,
-      "grad_norm": 1.294642686843872,
+      "grad_norm": 1.275856614112854,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.661,
+      "loss": 1.6591,
       "step": 10
     },
     {
       "epoch": 0.2838709677419355,
-      "grad_norm": 1.1089555025100708,
+      "grad_norm": 1.0931450128555298,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.5621,
+      "loss": 1.5615,
       "step": 11
     },
     {
       "epoch": 0.3096774193548387,
-      "grad_norm": 0.6231883764266968,
+      "grad_norm": 0.6137867569923401,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 1.448,
+      "loss": 1.4473,
       "step": 12
     },
     {
       "epoch": 0.33548387096774196,
-      "grad_norm": 0.7332714796066284,
+      "grad_norm": 0.734936535358429,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.3044,
+      "loss": 1.3045,
       "step": 13
     },
     {
       "epoch": 0.36129032258064514,
-      "grad_norm": 0.8896142840385437,
+      "grad_norm": 0.8893285989761353,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.0781,
+      "loss": 1.0787,
       "step": 14
     },
     {
       "epoch": 0.3870967741935484,
-      "grad_norm": 0.7502830028533936,
+      "grad_norm": 0.7464378476142883,
       "learning_rate": 8.296729075500344e-05,
       "loss": 1.0254,
       "step": 15
     },
     {
       "epoch": 0.4129032258064516,
-      "grad_norm": 0.6011187434196472,
+      "grad_norm": 0.5999816656112671,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 1.0411,
+      "loss": 1.0404,
       "step": 16
     },
     {
       "epoch": 0.43870967741935485,
-      "grad_norm": 0.5312099456787109,
+      "grad_norm": 0.5284008979797363,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.0013,
+      "loss": 1.0016,
       "step": 17
     },
     {
       "epoch": 0.4645161290322581,
-      "grad_norm": 0.5888484716415405,
+      "grad_norm": 0.5968301892280579,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.9215,
+      "loss": 0.9219,
       "step": 18
     },
     {
       "epoch": 0.49032258064516127,
-      "grad_norm": 0.6311532855033875,
+      "grad_norm": 0.62823086977005,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.7885,
+      "loss": 0.7891,
       "step": 19
     },
     {
       "epoch": 0.5161290322580645,
-      "grad_norm": 0.7916381359100342,
+      "grad_norm": 0.8073842525482178,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.652,
+      "loss": 1.6532,
       "step": 20
     },
     {
       "epoch": 0.5419354838709678,
-      "grad_norm": 0.743448793888092,
+      "grad_norm": 0.7547092437744141,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.4368,
+      "loss": 1.4375,
       "step": 21
     },
     {
       "epoch": 0.567741935483871,
-      "grad_norm": 0.6138935089111328,
+      "grad_norm": 0.6148136854171753,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.2923,
+      "loss": 1.2913,
       "step": 22
     },
     {
       "epoch": 0.5935483870967742,
-      "grad_norm": 0.5238935351371765,
+      "grad_norm": 0.5285658836364746,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.1441,
+      "loss": 1.1442,
       "step": 23
     },
     {
       "epoch": 0.6193548387096774,
-      "grad_norm": 0.4640217125415802,
+      "grad_norm": 0.4618549346923828,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.0112,
+      "loss": 1.0113,
       "step": 24
     },
     {
       "epoch": 0.6451612903225806,
-      "grad_norm": 0.5122854709625244,
+      "grad_norm": 0.5254773497581482,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 1.0068,
+      "loss": 1.0067,
       "step": 25
     },
     {
       "epoch": 0.6451612903225806,
-      "eval_loss": 1.1054987907409668,
-      "eval_runtime": 3.0392,
-      "eval_samples_per_second": 86.206,
-      "eval_steps_per_second": 10.858,
+      "eval_loss": 1.1069587469100952,
+      "eval_runtime": 3.0035,
+      "eval_samples_per_second": 87.233,
+      "eval_steps_per_second": 10.987,
       "step": 25
+    },
+    {
+      "epoch": 0.6709677419354839,
+      "grad_norm": 0.5983415842056274,
+      "learning_rate": 5e-05,
+      "loss": 0.9648,
+      "step": 26
+    },
+    {
+      "epoch": 0.6967741935483871,
+      "grad_norm": 0.8184328079223633,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0181,
+      "step": 27
+    },
+    {
+      "epoch": 0.7225806451612903,
+      "grad_norm": 0.9854726791381836,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8841,
+      "step": 28
+    },
+    {
+      "epoch": 0.7483870967741936,
+      "grad_norm": 0.5056580305099487,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4426,
+      "step": 29
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.4871244728565216,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4657,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5702559947967529,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4197,
+      "step": 31
+    },
+    {
+      "epoch": 0.8258064516129032,
+      "grad_norm": 0.5786279439926147,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1867,
+      "step": 32
+    },
+    {
+      "epoch": 0.8516129032258064,
+      "grad_norm": 0.6143596172332764,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0965,
+      "step": 33
+    },
+    {
+      "epoch": 0.8774193548387097,
+      "grad_norm": 0.5821972489356995,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9171,
+      "step": 34
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.5039418935775757,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0049,
+      "step": 35
+    },
+    {
+      "epoch": 0.9290322580645162,
+      "grad_norm": 0.46057987213134766,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0062,
+      "step": 36
+    },
+    {
+      "epoch": 0.9548387096774194,
+      "grad_norm": 0.49549490213394165,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8983,
+      "step": 37
+    },
+    {
+      "epoch": 0.9806451612903225,
+      "grad_norm": 0.9176192283630371,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.796,
+      "step": 38
+    },
+    {
+      "epoch": 1.0064516129032257,
+      "grad_norm": 0.4929143488407135,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4949,
+      "step": 39
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.48160475492477417,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4423,
+      "step": 40
+    },
+    {
+      "epoch": 1.0580645161290323,
+      "grad_norm": 0.4517855644226074,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2639,
+      "step": 41
+    },
+    {
+      "epoch": 1.0838709677419356,
+      "grad_norm": 0.49489712715148926,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0878,
+      "step": 42
+    },
+    {
+      "epoch": 1.1096774193548387,
+      "grad_norm": 0.47455382347106934,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0512,
+      "step": 43
+    },
+    {
+      "epoch": 1.135483870967742,
+      "grad_norm": 0.4912084639072418,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9109,
+      "step": 44
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 0.4730239510536194,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8809,
+      "step": 45
+    },
+    {
+      "epoch": 1.1870967741935483,
+      "grad_norm": 0.5607527494430542,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8847,
+      "step": 46
+    },
+    {
+      "epoch": 1.2129032258064516,
+      "grad_norm": 0.5235608220100403,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9092,
+      "step": 47
+    },
+    {
+      "epoch": 1.238709677419355,
+      "grad_norm": 0.5274782776832581,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6345,
+      "step": 48
+    },
+    {
+      "epoch": 1.2645161290322582,
+      "grad_norm": 0.5025497078895569,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8134,
+      "step": 49
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.4852551817893982,
+      "learning_rate": 0.0,
+      "loss": 1.4402,
+      "step": 50
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "eval_loss": 1.0583925247192383,
+      "eval_runtime": 3.0074,
+      "eval_samples_per_second": 87.12,
+      "eval_steps_per_second": 10.973,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:920b2c7d82856e5fb7d9351929f1af6962c972e7bfe34ba7314628b82510914d
+oid sha256:cdea26617d7d2d86baab47f17a029e6354a495dec927a580227d3a5dcb021241
 size 6776