Training in progress, epoch 2, checkpoint

checkpoint-7198/README.md

@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.15.2
+- PEFT 0.14.0

checkpoint-7198/adapter_config.json

@@ -3,7 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
   "bias": "none",
-  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -24,11 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

checkpoint-7198/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7944a65b4b919fbb1a6b69f266cae31eb268c510b0803928915d6d85f840ffd3
+oid sha256:874ade54f316c582f68a4fd8b58d8f4377f783b5ec69e2a743d50f4e679e523d
 size 268636736

checkpoint-7198/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc3891bddc357343b21b2a26ad3bf6ceaf59bb359625f43aff6a7686e5fc5f7
-size 12664203
+oid sha256:e858fc761ce61176961eefcf8cd7881c311da9c777de09ae9a3efb0a6a4611c6
+size 12663802

checkpoint-7198/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f631a04c193a45d77a05be2c0a997ea5ea0aa98e89ad7e6100655bef5e0a5d0c
-size 16389
+oid sha256:cda3e4f4f3a579f2ed43a35a824ea37d6c5a0bbd3109f6ad01d2f905c0549b0a
+size 15984

checkpoint-7198/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c21817d687e302c18134ec4bfd078d26d7cb9bff6bcda3f8ad0a490066a101d
-size 16389
+oid sha256:796b5fe8c978fa8993cce438df553f377a0acff0e64bb6f43357b28c2030b822
+size 15984

checkpoint-7198/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b6eca8d71531d366716331e5be72b2fda425225784d3dcf41ea7cd84c77196
-size 16389
+oid sha256:03c5b80306eb16ae0bc2c4f04f254e081b37503f947ddcd865278219551f7105
+size 15984

checkpoint-7198/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7703717b324ae7f7c45eab40ceac0da20e902d53c84d414ec596b400a2d6d6
-size 16389
+oid sha256:c138718360b2d4843b6994f78d26cd9dd4e71fd652881180f024fb00ef934d0a
+size 15984

checkpoint-7198/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94f4d81fa3bbc6990bc5fa81129fad2bd93cf3a243342b98e7c84e223e55ec5
-size 16389
+oid sha256:6fa54bcaf5f754442c8642d25df77cc12ba0695da6d82226774003b5daa63442
+size 15984

checkpoint-7198/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77f39238dae4c265c7b7bc7cc77cfc22c89b46e1fdabd0956ce262ac2e38fc8
-size 16389
+oid sha256:1897d09b0d7c961aade75a21f8733b45deb6a2c198503d78e9de03a3ccf7d0b6
+size 15984

checkpoint-7198/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e9324a60a620c354498fd7882159b57352945b73c5625a13746f5a9390d589
-size 16389
+oid sha256:4c10eb0c4913bd71bd971542978362902724e2dd4d4b63d3d7c354a085624491
+size 15984

checkpoint-7198/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0136c967ce78a0135424284d5623057b7257e23018806753b7c62b1ffc583c
-size 16389
+oid sha256:a41887a962310fa5123d4e8ff37f4bed4d5848017b56d675efb7d617c0670cfc
+size 15984

checkpoint-7198/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a6fd51fb7a23c15e5739574610fda6afbc2d8fed6f774f9160868c7ad200ee
-size 1465
+oid sha256:bf2e7644477bc493e38cdd3df5a5c7abece9a6e2c689e8592c062678b7e37747
+size 1064

checkpoint-7198/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 2.0,
@@ -11,172 +10,172 @@
   "log_history": [
     {
       "epoch": 0.13892747985551543,
-      "grad_norm": 0.6735790967941284,
-      "learning_rate": 0.0007907937390015746,
-      "loss": 0.3742,
+      "grad_norm": 0.9573676586151123,
+      "learning_rate": 0.0007907566916736131,
+      "loss": 0.377,
       "step": 500
     },
     {
       "epoch": 0.2000555709919422,
-      "eval_loss": 0.2844131588935852,
-      "eval_runtime": 5.091,
-      "eval_samples_per_second": 98.212,
-      "eval_steps_per_second": 6.286,
+      "eval_loss": 0.28939542174339294,
+      "eval_runtime": 4.6518,
+      "eval_samples_per_second": 107.484,
+      "eval_steps_per_second": 6.879,
       "step": 720
     },
     {
       "epoch": 0.27785495971103086,
-      "grad_norm": 0.6214504241943359,
-      "learning_rate": 0.0007815319070112068,
-      "loss": 0.2859,
+      "grad_norm": 0.5571001768112183,
+      "learning_rate": 0.0007815133833472261,
+      "loss": 0.2824,
       "step": 1000
     },
     {
       "epoch": 0.4001111419838844,
-      "eval_loss": 0.2708466649055481,
-      "eval_runtime": 4.8349,
-      "eval_samples_per_second": 103.416,
-      "eval_steps_per_second": 6.619,
+      "eval_loss": 0.2604603171348572,
+      "eval_runtime": 4.3083,
+      "eval_samples_per_second": 116.054,
+      "eval_steps_per_second": 7.427,
       "step": 1440
     },
     {
       "epoch": 0.41678243956654626,
-      "grad_norm": 0.5057302117347717,
-      "learning_rate": 0.0007722700750208392,
-      "loss": 0.2679,
+      "grad_norm": 0.6729081273078918,
+      "learning_rate": 0.0007722515513568584,
+      "loss": 0.2627,
       "step": 1500
     },
     {
       "epoch": 0.5557099194220617,
-      "grad_norm": 0.623817503452301,
-      "learning_rate": 0.0007630082430304714,
-      "loss": 0.2527,
+      "grad_norm": 0.5200651288032532,
+      "learning_rate": 0.0007629897193664907,
+      "loss": 0.2488,
       "step": 2000
     },
     {
       "epoch": 0.6001667129758266,
-      "eval_loss": 0.24877774715423584,
-      "eval_runtime": 5.9656,
-      "eval_samples_per_second": 83.813,
-      "eval_steps_per_second": 5.364,
+      "eval_loss": 0.24864767491817474,
+      "eval_runtime": 3.8713,
+      "eval_samples_per_second": 129.157,
+      "eval_steps_per_second": 8.266,
       "step": 2160
     },
     {
       "epoch": 0.6946373992775771,
-      "grad_norm": 1.3911620378494263,
-      "learning_rate": 0.0007537649347040845,
-      "loss": 0.2441,
+      "grad_norm": 0.6645380258560181,
+      "learning_rate": 0.0007537464110401038,
+      "loss": 0.2424,
       "step": 2500
     },
     {
       "epoch": 0.8002222839677688,
-      "eval_loss": 0.2391277253627777,
-      "eval_runtime": 5.9872,
-      "eval_samples_per_second": 83.512,
-      "eval_steps_per_second": 5.345,
+      "eval_loss": 0.2434273064136505,
+      "eval_runtime": 4.2012,
+      "eval_samples_per_second": 119.013,
+      "eval_steps_per_second": 7.617,
       "step": 2880
     },
     {
       "epoch": 0.8335648791330925,
-      "grad_norm": 0.7922923564910889,
-      "learning_rate": 0.0007445216263776975,
-      "loss": 0.235,
+      "grad_norm": 0.8886778354644775,
+      "learning_rate": 0.000744484579049736,
+      "loss": 0.2332,
       "step": 3000
     },
     {
       "epoch": 0.972492358988608,
-      "grad_norm": 0.8539218902587891,
-      "learning_rate": 0.0007352597943873298,
-      "loss": 0.2331,
+      "grad_norm": 0.5990277528762817,
+      "learning_rate": 0.0007352227470593684,
+      "loss": 0.2307,
       "step": 3500
     },
     {
       "epoch": 1.000277854959711,
-      "eval_loss": 0.23887279629707336,
-      "eval_runtime": 5.6004,
-      "eval_samples_per_second": 89.279,
-      "eval_steps_per_second": 5.714,
+      "eval_loss": 0.23320984840393066,
+      "eval_runtime": 4.3777,
+      "eval_samples_per_second": 114.216,
+      "eval_steps_per_second": 7.31,
       "step": 3600
     },
     {
       "epoch": 1.1114198388441234,
-      "grad_norm": 0.6812190413475037,
-      "learning_rate": 0.0007259979623969622,
-      "loss": 0.2201,
+      "grad_norm": 0.9014330506324768,
+      "learning_rate": 0.0007259609150690007,
+      "loss": 0.2171,
       "step": 4000
     },
     {
       "epoch": 1.2003334259516532,
-      "eval_loss": 0.2331564724445343,
-      "eval_runtime": 5.2457,
-      "eval_samples_per_second": 95.317,
-      "eval_steps_per_second": 6.1,
+      "eval_loss": 0.23165521025657654,
+      "eval_runtime": 4.5533,
+      "eval_samples_per_second": 109.81,
+      "eval_steps_per_second": 7.028,
       "step": 4320
     },
     {
       "epoch": 1.2503473186996388,
-      "grad_norm": 0.6926279067993164,
-      "learning_rate": 0.0007167361304065945,
-      "loss": 0.2199,
+      "grad_norm": 0.9070354104042053,
+      "learning_rate": 0.000716699083078633,
+      "loss": 0.2174,
       "step": 4500
     },
     {
       "epoch": 1.3892747985551543,
-      "grad_norm": 0.857128918170929,
-      "learning_rate": 0.0007074742984162268,
-      "loss": 0.2157,
+      "grad_norm": 0.9023842215538025,
+      "learning_rate": 0.000707455774752246,
+      "loss": 0.215,
       "step": 5000
     },
     {
       "epoch": 1.4003889969435954,
-      "eval_loss": 0.22209732234477997,
-      "eval_runtime": 4.9003,
-      "eval_samples_per_second": 102.035,
-      "eval_steps_per_second": 6.53,
+      "eval_loss": 0.21996016800403595,
+      "eval_runtime": 4.2649,
+      "eval_samples_per_second": 117.235,
+      "eval_steps_per_second": 7.503,
       "step": 5040
     },
     {
       "epoch": 1.5282022784106695,
-      "grad_norm": 0.8350584506988525,
-      "learning_rate": 0.000698212466425859,
-      "loss": 0.2122,
+      "grad_norm": 0.8724926710128784,
+      "learning_rate": 0.0006981939427618783,
+      "loss": 0.2101,
       "step": 5500
     },
     {
       "epoch": 1.6004445679355377,
-      "eval_loss": 0.22165100276470184,
-      "eval_runtime": 4.8879,
-      "eval_samples_per_second": 102.294,
-      "eval_steps_per_second": 6.547,
+      "eval_loss": 0.21771642565727234,
+      "eval_runtime": 4.6518,
+      "eval_samples_per_second": 107.486,
+      "eval_steps_per_second": 6.879,
       "step": 5760
     },
     {
       "epoch": 1.667129758266185,
-      "grad_norm": 0.6862344145774841,
-      "learning_rate": 0.0006889691580994721,
-      "loss": 0.2158,
+      "grad_norm": 1.1229606866836548,
+      "learning_rate": 0.0006889321107715106,
+      "loss": 0.209,
       "step": 6000
     },
     {
       "epoch": 1.8005001389274797,
-      "eval_loss": 0.21265414357185364,
-      "eval_runtime": 5.1036,
-      "eval_samples_per_second": 97.97,
-      "eval_steps_per_second": 6.27,
+      "eval_loss": 0.2162657231092453,
+      "eval_runtime": 3.9728,
+      "eval_samples_per_second": 125.857,
+      "eval_steps_per_second": 8.055,
       "step": 6480
     },
     {
       "epoch": 1.8060572381217006,
-      "grad_norm": 0.64631587266922,
-      "learning_rate": 0.0006797073261091044,
-      "loss": 0.2069,
+      "grad_norm": 0.562541127204895,
+      "learning_rate": 0.000679670278781143,
+      "loss": 0.2053,
       "step": 6500
     },
     {
       "epoch": 1.9449847179772157,
-      "grad_norm": 0.6139649748802185,
-      "learning_rate": 0.0006704454941187368,
-      "loss": 0.2063,
+      "grad_norm": 0.9058884382247925,
+      "learning_rate": 0.0006704084467907753,
+      "loss": 0.2047,
       "step": 7000
     }
   ],

checkpoint-7198/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d31253d1d9828754b954b23155d823529e2ebc7f148e5c229e9bc7b696124d
-size 6033
+oid sha256:1ac71e3cdd10165b76004d5b1c4b8cd4a183b94ec338868fce8dc9960bf7c890
+size 5496