Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "o_proj",
     "k_proj",
-    "gate_proj",
     "v_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj"
+    "gate_proj",
+    "q_proj",
+    "up_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 sha256:2a0161bc9fe56eef85888e948bae90b892301b10b964e46b323368d3c2c24e6b
+oid sha256:dff1ae698a21db1a465345cb9185e26481a2df9e5fd4e498adcce0c048f4e032
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d88628bb708d2aeb4d62cbcb1a86472e50f182b9af4920faeaea688c725950
+oid sha256:8e80c32e107cc9359c2864a894d23d5f052234c0159d39c0602daf07dfc7e60e
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702dec26fe3255fca599ae4f5fbf695aff40a521b0fb582b046dbed340148d8d
-size 14960
+oid sha256:387dfd6dfe741a0b34c6f6c61040ee4a533c506b6c6d1cac9223c508941357bf
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c328dd1baeb8e509d6021039e4828dd873d8f446a32c7b0a0f1124f50a6a187
+oid sha256:aeb5382fb74fa78273273de65fd109f24d458b0ee7c8185eedd044abcc68e9c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4ff9db4bf3e9f53633885cd47615ff37af25396e668b96d6f519f738ab6edf
+oid sha256:c92a48b844813083ebe0117e4878b41bab78e8dc096dc101cde4d6a23b35852b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784d917e6ec419b422c0692bfc72aed61d2168de0df8757559c3928abc1bf30d
+oid sha256:718e7097cfe8368bf1aa1590e471b3bd734944333ff85d0482277f6a58159a9a
 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": 0.3264453411102295,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12330456226880394,
+  "best_metric": 0.3010638654232025,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2466091245376079,
   "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": 0.004932182490752158,
-      "grad_norm": 1.8534983396530151,
+      "grad_norm": 1.853391408920288,
       "learning_rate": 5e-05,
       "loss": 1.1438,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.004932182490752158,
       "eval_loss": 1.414349913597107,
-      "eval_runtime": 20.7051,
-      "eval_samples_per_second": 65.974,
-      "eval_steps_per_second": 8.259,
+      "eval_runtime": 20.1993,
+      "eval_samples_per_second": 67.626,
+      "eval_steps_per_second": 8.466,
       "step": 1
     },
     {
       "epoch": 0.009864364981504316,
-      "grad_norm": 1.8421441316604614,
+      "grad_norm": 1.838688611984253,
       "learning_rate": 0.0001,
       "loss": 1.1763,
       "step": 2
     },
     {
       "epoch": 0.014796547472256474,
-      "grad_norm": 1.5805590152740479,
+      "grad_norm": 1.5773396492004395,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.1488,
+      "loss": 1.1486,
       "step": 3
     },
     {
       "epoch": 0.01972872996300863,
-      "grad_norm": 1.2270656824111938,
+      "grad_norm": 1.2263104915618896,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 0.9757,
+      "loss": 0.9751,
       "step": 4
     },
     {
       "epoch": 0.02466091245376079,
-      "grad_norm": 1.2160286903381348,
+      "grad_norm": 1.2177971601486206,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 0.8759,
+      "loss": 0.8749,
       "step": 5
     },
     {
       "epoch": 0.029593094944512947,
-      "grad_norm": 1.2084640264511108,
+      "grad_norm": 1.2090750932693481,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.7989,
+      "loss": 0.7983,
       "step": 6
     },
     {
       "epoch": 0.0345252774352651,
-      "grad_norm": 1.0644646883010864,
+      "grad_norm": 1.0687938928604126,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.7208,
+      "loss": 0.7207,
       "step": 7
     },
     {
       "epoch": 0.03945745992601726,
-      "grad_norm": 1.1075224876403809,
+      "grad_norm": 1.105446696281433,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.6503,
+      "loss": 0.6496,
       "step": 8
     },
     {
       "epoch": 0.04438964241676942,
-      "grad_norm": 1.0241856575012207,
+      "grad_norm": 1.0916451215744019,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.604,
+      "loss": 0.6039,
       "step": 9
     },
     {
       "epoch": 0.04932182490752158,
-      "grad_norm": 1.1344308853149414,
+      "grad_norm": 1.2162078619003296,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.5534,
+      "loss": 0.5552,
       "step": 10
     },
     {
       "epoch": 0.05425400739827373,
-      "grad_norm": 1.2645190954208374,
+      "grad_norm": 1.3956806659698486,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.5682,
+      "loss": 0.5719,
       "step": 11
     },
     {
       "epoch": 0.059186189889025895,
-      "grad_norm": 1.148837685585022,
+      "grad_norm": 1.2086831331253052,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.5713,
+      "loss": 0.5734,
       "step": 12
     },
     {
       "epoch": 0.06411837237977805,
-      "grad_norm": 1.8091137409210205,
+      "grad_norm": 1.8638321161270142,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.3916,
+      "loss": 0.3938,
       "step": 13
     },
     {
       "epoch": 0.0690505548705302,
-      "grad_norm": 1.0642383098602295,
+      "grad_norm": 1.1751363277435303,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.3792,
+      "loss": 0.3828,
       "step": 14
     },
     {
       "epoch": 0.07398273736128237,
-      "grad_norm": 0.8615063428878784,
+      "grad_norm": 0.9490559697151184,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.3716,
+      "loss": 0.3741,
       "step": 15
     },
     {
       "epoch": 0.07891491985203453,
-      "grad_norm": 0.7969047427177429,
+      "grad_norm": 0.8116526007652283,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.3794,
+      "loss": 0.3803,
       "step": 16
     },
     {
       "epoch": 0.08384710234278668,
-      "grad_norm": 0.6164565682411194,
+      "grad_norm": 0.6244385838508606,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.3569,
+      "loss": 0.3585,
       "step": 17
     },
     {
       "epoch": 0.08877928483353884,
-      "grad_norm": 0.545974850654602,
+      "grad_norm": 0.5554587244987488,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.3355,
+      "loss": 0.3372,
       "step": 18
     },
     {
       "epoch": 0.093711467324291,
-      "grad_norm": 0.604865312576294,
+      "grad_norm": 0.6161372065544128,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.364,
+      "loss": 0.3646,
       "step": 19
     },
     {
       "epoch": 0.09864364981504316,
-      "grad_norm": 0.4479445517063141,
+      "grad_norm": 0.4445961117744446,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.3048,
+      "loss": 0.3057,
       "step": 20
     },
     {
       "epoch": 0.10357583230579531,
-      "grad_norm": 0.47299858927726746,
+      "grad_norm": 0.4906725287437439,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.3388,
+      "loss": 0.3403,
       "step": 21
     },
     {
       "epoch": 0.10850801479654747,
-      "grad_norm": 0.6112440228462219,
+      "grad_norm": 0.5985474586486816,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.3445,
+      "loss": 0.3451,
       "step": 22
     },
     {
       "epoch": 0.11344019728729964,
-      "grad_norm": 0.5682258605957031,
+      "grad_norm": 0.5309833884239197,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.3287,
+      "loss": 0.329,
       "step": 23
     },
     {
       "epoch": 0.11837237977805179,
-      "grad_norm": 0.6382001638412476,
+      "grad_norm": 0.7182720899581909,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.4193,
+      "loss": 0.4217,
       "step": 24
     },
     {
       "epoch": 0.12330456226880394,
-      "grad_norm": 0.9506509304046631,
+      "grad_norm": 0.9789097309112549,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.3309,
+      "loss": 0.3338,
       "step": 25
     },
     {
       "epoch": 0.12330456226880394,
-      "eval_loss": 0.3264453411102295,
-      "eval_runtime": 20.7046,
-      "eval_samples_per_second": 65.976,
-      "eval_steps_per_second": 8.259,
+      "eval_loss": 0.32859063148498535,
+      "eval_runtime": 20.2071,
+      "eval_samples_per_second": 67.6,
+      "eval_steps_per_second": 8.462,
       "step": 25
+    },
+    {
+      "epoch": 0.1282367447595561,
+      "grad_norm": 1.0022274255752563,
+      "learning_rate": 5e-05,
+      "loss": 0.3003,
+      "step": 26
+    },
+    {
+      "epoch": 0.13316892725030827,
+      "grad_norm": 0.5783088803291321,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3105,
+      "step": 27
+    },
+    {
+      "epoch": 0.1381011097410604,
+      "grad_norm": 0.4817257523536682,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3177,
+      "step": 28
+    },
+    {
+      "epoch": 0.14303329223181258,
+      "grad_norm": 0.43291813135147095,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3168,
+      "step": 29
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.5325983166694641,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2996,
+      "step": 30
+    },
+    {
+      "epoch": 0.15289765721331688,
+      "grad_norm": 0.5798412561416626,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3117,
+      "step": 31
+    },
+    {
+      "epoch": 0.15782983970406905,
+      "grad_norm": 0.5370204448699951,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3033,
+      "step": 32
+    },
+    {
+      "epoch": 0.16276202219482122,
+      "grad_norm": 0.5216674208641052,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3017,
+      "step": 33
+    },
+    {
+      "epoch": 0.16769420468557336,
+      "grad_norm": 0.48683419823646545,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2976,
+      "step": 34
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.5342722535133362,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3315,
+      "step": 35
+    },
+    {
+      "epoch": 0.17755856966707767,
+      "grad_norm": 0.5742915868759155,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3254,
+      "step": 36
+    },
+    {
+      "epoch": 0.18249075215782984,
+      "grad_norm": 1.067507266998291,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3885,
+      "step": 37
+    },
+    {
+      "epoch": 0.187422934648582,
+      "grad_norm": 0.4760156571865082,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.272,
+      "step": 38
+    },
+    {
+      "epoch": 0.19235511713933415,
+      "grad_norm": 0.5933215618133545,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.284,
+      "step": 39
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.6129382848739624,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2854,
+      "step": 40
+    },
+    {
+      "epoch": 0.20221948212083848,
+      "grad_norm": 0.8225616216659546,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3068,
+      "step": 41
+    },
+    {
+      "epoch": 0.20715166461159062,
+      "grad_norm": 0.698328971862793,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2929,
+      "step": 42
+    },
+    {
+      "epoch": 0.2120838471023428,
+      "grad_norm": 0.5400214791297913,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2885,
+      "step": 43
+    },
+    {
+      "epoch": 0.21701602959309493,
+      "grad_norm": 0.636957585811615,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3086,
+      "step": 44
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.57123863697052,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2952,
+      "step": 45
+    },
+    {
+      "epoch": 0.22688039457459927,
+      "grad_norm": 0.4993796944618225,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2806,
+      "step": 46
+    },
+    {
+      "epoch": 0.2318125770653514,
+      "grad_norm": 0.6364679336547852,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.312,
+      "step": 47
+    },
+    {
+      "epoch": 0.23674475955610358,
+      "grad_norm": 0.46784254908561707,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2945,
+      "step": 48
+    },
+    {
+      "epoch": 0.24167694204685575,
+      "grad_norm": 0.5183226466178894,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3751,
+      "step": 49
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.3274175524711609,
+      "learning_rate": 0.0,
+      "loss": 0.2895,
+      "step": 50
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "eval_loss": 0.3010638654232025,
+      "eval_runtime": 20.1887,
+      "eval_samples_per_second": 67.662,
+      "eval_steps_per_second": 8.47,
+      "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": 2.898563020567347e+16,
+  "total_flos": 5.80081729709015e+16,
   "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 sha256:8e2aa80718cefc67ce40615d2504276755fefcf94b378ebe5f2b4e506d2f53e8
+oid sha256:65452aaa7d77b7da3d5e5f9773ddcb300bbf77de27efbabfcb8898e12a85973a
 size 6776