Training in progress, step 30, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
+    "gate_proj",
     "v_proj",
     "down_proj",
     "o_proj",
     "q_proj",
-    "k_proj",
-    "gate_proj"
+    "k_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:f00f9538b271e8d8961813afd5ab30b65fd44804ac0d2fd5fc611c77eb726d97
+oid sha256:56d434d598901331d000d69f27bf2d6a200a08071d7cddb9fcc74d618b8fdcb0
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99777225e2d875939f04d6a013d3489b5b5815c9e4ee07852ed26ee178dbede3
+oid sha256:807c2c215b63a89b54f864694bcb59b5d66e08d35c2d3cb7b85205e700e1b415
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235987cd14d2b651bd083a2045910396be0aab90ff9f738c75760d88528349a3
+oid sha256:0017d054f399ae02d66bec2e7c0b81e4c469b5e125926b0e041136c01e7debf8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed83c54ad01fcfcd8246932f708e99e17e8ef5c6e3595097b68d8c42cf78ec5
+oid sha256:409b87eefbbfc5af04df48b8cccf0428548d3efea659f10ffd25c2e2bc3de30b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0966a69a93e8ec900098984946f252e636d603335a1be19728cf108f6f5076ed
+oid sha256:b2a3eaa55c6d5537c27e4456768a8f475ec9b8f739daf816e638d7ac888011bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f556cc525b21d1e70dfd21e4724095b63d005b1d343403352d5b6e8f1a8a5b
+oid sha256:c9ed5c5b37f0763e77790b53d0f88a4fc69d787befcb63013221803055bb03c9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8b460eb34577dc31e89c5d46049a264caffc8e9f90e68fb640444126fba5f4
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 1.0479129552841187,
+  "best_metric": 1.0476467609405518,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.6369426751592355,
+  "epoch": 3.1910828025477707,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.10191082802547771,
-      "grad_norm": 0.315826952457428,
+      "grad_norm": 0.3121834695339203,
       "learning_rate": 5e-05,
       "loss": 1.2924,
       "step": 1
@@ -18,186 +18,221 @@
     {
       "epoch": 0.10191082802547771,
       "eval_loss": 1.4096554517745972,
-      "eval_runtime": 2.2855,
-      "eval_samples_per_second": 28.878,
-      "eval_steps_per_second": 3.938,
+      "eval_runtime": 2.2711,
+      "eval_samples_per_second": 29.061,
+      "eval_steps_per_second": 3.963,
       "step": 1
     },
     {
       "epoch": 0.20382165605095542,
-      "grad_norm": 0.30153176188468933,
+      "grad_norm": 0.2996855676174164,
       "learning_rate": 0.0001,
       "loss": 1.3123,
       "step": 2
     },
     {
       "epoch": 0.3057324840764331,
-      "grad_norm": 0.35216328501701355,
+      "grad_norm": 0.3492814004421234,
       "learning_rate": 9.968561049466214e-05,
-      "loss": 1.4112,
+      "loss": 1.4114,
       "step": 3
     },
     {
       "epoch": 0.40764331210191085,
-      "grad_norm": 0.27521029114723206,
+      "grad_norm": 0.2742891311645508,
       "learning_rate": 9.874639560909117e-05,
-      "loss": 1.1817,
+      "loss": 1.1823,
       "step": 4
     },
     {
       "epoch": 0.5095541401273885,
-      "grad_norm": 0.3043312728404999,
+      "grad_norm": 0.3076689541339874,
       "learning_rate": 9.719416651541839e-05,
-      "loss": 1.3587,
+      "loss": 1.3595,
       "step": 5
     },
     {
       "epoch": 0.6114649681528662,
-      "grad_norm": 0.3067076504230499,
+      "grad_norm": 0.3100813329219818,
       "learning_rate": 9.504844339512095e-05,
-      "loss": 1.2378,
+      "loss": 1.2393,
       "step": 6
     },
     {
       "epoch": 0.7133757961783439,
-      "grad_norm": 0.24411499500274658,
+      "grad_norm": 0.24378710985183716,
       "learning_rate": 9.233620996141421e-05,
-      "loss": 1.2001,
+      "loss": 1.2006,
       "step": 7
     },
     {
       "epoch": 0.8152866242038217,
-      "grad_norm": 0.31167352199554443,
+      "grad_norm": 0.30991846323013306,
       "learning_rate": 8.90915741234015e-05,
-      "loss": 1.1681,
+      "loss": 1.1693,
       "step": 8
     },
     {
       "epoch": 0.9171974522292994,
-      "grad_norm": 0.2961890995502472,
+      "grad_norm": 0.298220694065094,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.1551,
+      "loss": 1.1559,
       "step": 9
     },
     {
       "epoch": 1.0636942675159236,
-      "grad_norm": 0.5746045112609863,
+      "grad_norm": 0.5674415826797485,
       "learning_rate": 8.117449009293668e-05,
-      "loss": 1.7392,
+      "loss": 1.7409,
       "step": 10
     },
     {
       "epoch": 1.1656050955414012,
-      "grad_norm": 0.28287041187286377,
+      "grad_norm": 0.28200918436050415,
       "learning_rate": 7.660160382576683e-05,
-      "loss": 0.9983,
+      "loss": 0.9992,
       "step": 11
     },
     {
       "epoch": 1.267515923566879,
-      "grad_norm": 0.26368194818496704,
+      "grad_norm": 0.25404325127601624,
       "learning_rate": 7.169418695587791e-05,
-      "loss": 1.0329,
+      "loss": 1.0336,
       "step": 12
     },
     {
       "epoch": 1.3694267515923566,
-      "grad_norm": 0.24134495854377747,
+      "grad_norm": 0.2391156703233719,
       "learning_rate": 6.651395309775837e-05,
-      "loss": 1.0751,
+      "loss": 1.0757,
       "step": 13
     },
     {
       "epoch": 1.4713375796178343,
-      "grad_norm": 0.28836143016815186,
+      "grad_norm": 0.2868117690086365,
       "learning_rate": 6.112604669781572e-05,
-      "loss": 1.022,
+      "loss": 1.0221,
       "step": 14
     },
     {
       "epoch": 1.573248407643312,
-      "grad_norm": 0.2660194933414459,
+      "grad_norm": 0.26096099615097046,
       "learning_rate": 5.559822380516539e-05,
-      "loss": 1.1208,
+      "loss": 1.1211,
       "step": 15
     },
     {
       "epoch": 1.6751592356687897,
-      "grad_norm": 0.24954141676425934,
+      "grad_norm": 0.2496553361415863,
       "learning_rate": 5e-05,
-      "loss": 1.0427,
+      "loss": 1.0423,
       "step": 16
     },
     {
       "epoch": 1.7770700636942676,
-      "grad_norm": 0.26790428161621094,
+      "grad_norm": 0.26016390323638916,
       "learning_rate": 4.4401776194834613e-05,
-      "loss": 1.0076,
+      "loss": 1.0078,
       "step": 17
     },
     {
       "epoch": 1.8789808917197452,
-      "grad_norm": 0.23538947105407715,
+      "grad_norm": 0.23476140201091766,
       "learning_rate": 3.887395330218429e-05,
-      "loss": 0.9877,
+      "loss": 0.9879,
       "step": 18
     },
     {
       "epoch": 2.0254777070063694,
-      "grad_norm": 0.346373051404953,
+      "grad_norm": 0.3431682288646698,
       "learning_rate": 3.3486046902241664e-05,
-      "loss": 1.6144,
+      "loss": 1.6151,
       "step": 19
     },
     {
       "epoch": 2.127388535031847,
-      "grad_norm": 0.21446581184864044,
+      "grad_norm": 0.21315336227416992,
       "learning_rate": 2.8305813044122097e-05,
-      "loss": 0.9596,
+      "loss": 0.9605,
       "step": 20
     },
     {
       "epoch": 2.229299363057325,
-      "grad_norm": 0.20357617735862732,
+      "grad_norm": 0.20435573160648346,
       "learning_rate": 2.3398396174233178e-05,
       "loss": 0.925,
       "step": 21
     },
     {
       "epoch": 2.3312101910828025,
-      "grad_norm": 0.2289550006389618,
+      "grad_norm": 0.2289644032716751,
       "learning_rate": 1.8825509907063327e-05,
-      "loss": 1.0315,
+      "loss": 1.032,
       "step": 22
     },
     {
       "epoch": 2.43312101910828,
-      "grad_norm": 0.22605831921100616,
+      "grad_norm": 0.22667603194713593,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.9437,
+      "loss": 0.944,
       "step": 23
     },
     {
       "epoch": 2.535031847133758,
-      "grad_norm": 0.21340759098529816,
+      "grad_norm": 0.21269646286964417,
       "learning_rate": 1.090842587659851e-05,
-      "loss": 0.9948,
+      "loss": 0.9952,
       "step": 24
     },
     {
       "epoch": 2.6369426751592355,
-      "grad_norm": 0.21240516006946564,
+      "grad_norm": 0.21037527918815613,
       "learning_rate": 7.663790038585793e-06,
-      "loss": 0.954,
+      "loss": 0.9544,
       "step": 25
     },
     {
       "epoch": 2.6369426751592355,
-      "eval_loss": 1.0479129552841187,
-      "eval_runtime": 2.2831,
-      "eval_samples_per_second": 28.908,
-      "eval_steps_per_second": 3.942,
+      "eval_loss": 1.0476467609405518,
+      "eval_runtime": 2.2679,
+      "eval_samples_per_second": 29.102,
+      "eval_steps_per_second": 3.968,
       "step": 25
+    },
+    {
+      "epoch": 2.738853503184713,
+      "grad_norm": 0.2182152420282364,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.9549,
+      "step": 26
+    },
+    {
+      "epoch": 2.840764331210191,
+      "grad_norm": 0.20187175273895264,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.9287,
+      "step": 27
+    },
+    {
+      "epoch": 2.9426751592356686,
+      "grad_norm": 0.4659386873245239,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 1.4175,
+      "step": 28
+    },
+    {
+      "epoch": 3.089171974522293,
+      "grad_norm": 0.2993531823158264,
+      "learning_rate": 3.143895053378698e-07,
+      "loss": 1.082,
+      "step": 29
+    },
+    {
+      "epoch": 3.1910828025477707,
+      "grad_norm": 0.25595200061798096,
+      "learning_rate": 0.0,
+      "loss": 0.8877,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +256,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4042109046266266e+17,
+  "total_flos": 1.68704369229824e+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 sha256:11310abb03160086896271409f285f645e098cc1d2c620a9c8e344ab93359699
+oid sha256:9feb44dd06351a4ebb3399d9273df0fe7c81cda65ffedc861c36f176fba73ef5
 size 6776