Training in progress, step 1, checkpoint

last-checkpoint/README.md

@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.12.0
+- PEFT 0.13.0

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "o_proj",
-    "v_proj",
+    "q_proj",
+    "k_proj",
     "gate_proj",
     "up_proj",
-    "q_proj"
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11d9e0657440c22e6be394f9202e4e2741a8c3272eabf4774c1b2f4c36a00df
+oid sha256:561c6b93070c73144a416e7c9cf562b25739bd09872867ce8b25d47d06cfae59
 size 41599888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c320bbc90e1c223f7c748ece3d7a59a38ba1e0238b5046962501b3679d39be
-size 21222664
+oid sha256:14d9859f7541ea622b68c259a4e2d0156f53ba5ecb43889989752a4ce661c7c6
+size 21516104

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4734489b6f69f98e667b11c78c8f32dfe8b0d85349156b640625a29e3f4f6ae
+oid sha256:24ccbf5303ad569e3f94b6a321ce0a48ac0ad4f6e84f0e6db2bb9c2814fd2f56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9b1e2fb9e3a2ea5f6eceaacc95c0f2b57f31e97e7ecc768d3f909a8763c71f
+oid sha256:8b06889bea5a35ad424b6507846078e5ec1dad6feab2691e4c09645ed7dfb43a
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
-size 17525357
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

last-checkpoint/trainer_state.json

@@ -1,312 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8117154811715483,
+  "epoch": 0.025177025963808025,
   "eval_steps": 500,
-  "global_step": 42,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.06694560669456066,
-      "grad_norm": 7.278318881988525,
-      "learning_rate": 4.880952380952381e-05,
-      "loss": 0.4218,
+      "epoch": 0.025177025963808025,
+      "grad_norm": 14.77905559539795,
+      "learning_rate": 4.871794871794872e-05,
+      "loss": 0.5853,
       "step": 1
-    },
-    {
-      "epoch": 0.13389121338912133,
-      "grad_norm": 7.141674518585205,
-      "learning_rate": 4.761904761904762e-05,
-      "loss": 0.33,
-      "step": 2
-    },
-    {
-      "epoch": 0.200836820083682,
-      "grad_norm": 4.828211784362793,
-      "learning_rate": 4.642857142857143e-05,
-      "loss": 0.2474,
-      "step": 3
-    },
-    {
-      "epoch": 0.26778242677824265,
-      "grad_norm": 5.059885025024414,
-      "learning_rate": 4.523809523809524e-05,
-      "loss": 0.2322,
-      "step": 4
-    },
-    {
-      "epoch": 0.33472803347280333,
-      "grad_norm": 2.1169519424438477,
-      "learning_rate": 4.404761904761905e-05,
-      "loss": 0.0811,
-      "step": 5
-    },
-    {
-      "epoch": 0.401673640167364,
-      "grad_norm": 2.1026101112365723,
-      "learning_rate": 4.2857142857142856e-05,
-      "loss": 0.0712,
-      "step": 6
-    },
-    {
-      "epoch": 0.4686192468619247,
-      "grad_norm": 0.8095500469207764,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.0289,
-      "step": 7
-    },
-    {
-      "epoch": 0.5355648535564853,
-      "grad_norm": 0.6098321080207825,
-      "learning_rate": 4.047619047619048e-05,
-      "loss": 0.0177,
-      "step": 8
-    },
-    {
-      "epoch": 0.602510460251046,
-      "grad_norm": 0.18397152423858643,
-      "learning_rate": 3.928571428571429e-05,
-      "loss": 0.004,
-      "step": 9
-    },
-    {
-      "epoch": 0.6694560669456067,
-      "grad_norm": 0.1370420753955841,
-      "learning_rate": 3.809523809523809e-05,
-      "loss": 0.0031,
-      "step": 10
-    },
-    {
-      "epoch": 0.7364016736401674,
-      "grad_norm": 2.0491957664489746,
-      "learning_rate": 3.690476190476191e-05,
-      "loss": 0.0322,
-      "step": 11
-    },
-    {
-      "epoch": 0.803347280334728,
-      "grad_norm": 0.014418386854231358,
-      "learning_rate": 3.571428571428572e-05,
-      "loss": 0.0002,
-      "step": 12
-    },
-    {
-      "epoch": 0.8702928870292888,
-      "grad_norm": 0.9757394194602966,
-      "learning_rate": 3.4523809523809526e-05,
-      "loss": 0.0164,
-      "step": 13
-    },
-    {
-      "epoch": 0.9372384937238494,
-      "grad_norm": 0.013029157184064388,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0002,
-      "step": 14
-    },
-    {
-      "epoch": 1.00418410041841,
-      "grad_norm": 0.026524800807237625,
-      "learning_rate": 3.2142857142857144e-05,
-      "loss": 0.0003,
-      "step": 15
-    },
-    {
-      "epoch": 1.0711297071129706,
-      "grad_norm": 0.0028753578662872314,
-      "learning_rate": 3.095238095238095e-05,
-      "loss": 0.0,
-      "step": 16
-    },
-    {
-      "epoch": 1.1380753138075315,
-      "grad_norm": 0.0033568963408470154,
-      "learning_rate": 2.9761904761904762e-05,
-      "loss": 0.0,
-      "step": 17
-    },
-    {
-      "epoch": 1.205020920502092,
-      "grad_norm": 0.0005203815526328981,
-      "learning_rate": 2.857142857142857e-05,
-      "loss": 0.0,
-      "step": 18
-    },
-    {
-      "epoch": 1.2719665271966527,
-      "grad_norm": 0.1936761736869812,
-      "learning_rate": 2.7380952380952383e-05,
-      "loss": 0.0019,
-      "step": 19
-    },
-    {
-      "epoch": 1.3389121338912133,
-      "grad_norm": 0.00036436261143535376,
-      "learning_rate": 2.6190476190476192e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 1.4058577405857742,
-      "grad_norm": 0.00035023957025259733,
-      "learning_rate": 2.5e-05,
-      "loss": 0.0,
-      "step": 21
-    },
-    {
-      "epoch": 1.4728033472803348,
-      "grad_norm": 0.00016843595949467272,
-      "learning_rate": 2.380952380952381e-05,
-      "loss": 0.0,
-      "step": 22
-    },
-    {
-      "epoch": 1.5397489539748954,
-      "grad_norm": 9.115493594435975e-05,
-      "learning_rate": 2.261904761904762e-05,
-      "loss": 0.0,
-      "step": 23
-    },
-    {
-      "epoch": 1.606694560669456,
-      "grad_norm": 0.00036285529495216906,
-      "learning_rate": 2.1428571428571428e-05,
-      "loss": 0.0,
-      "step": 24
-    },
-    {
-      "epoch": 1.6736401673640167,
-      "grad_norm": 7.200593972811475e-05,
-      "learning_rate": 2.023809523809524e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 1.7405857740585775,
-      "grad_norm": 0.018788069486618042,
-      "learning_rate": 1.9047619047619046e-05,
-      "loss": 0.0001,
-      "step": 26
-    },
-    {
-      "epoch": 1.8075313807531381,
-      "grad_norm": 5.917173621128313e-05,
-      "learning_rate": 1.785714285714286e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 1.8744769874476988,
-      "grad_norm": 2.454935383866541e-05,
-      "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 1.9414225941422594,
-      "grad_norm": 0.35622039437294006,
-      "learning_rate": 1.5476190476190476e-05,
-      "loss": 0.0027,
-      "step": 29
-    },
-    {
-      "epoch": 2.00836820083682,
-      "grad_norm": 4.2320960346842185e-05,
-      "learning_rate": 1.4285714285714285e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 2.075313807531381,
-      "grad_norm": 0.00016777269775047898,
-      "learning_rate": 1.3095238095238096e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 2.1422594142259412,
-      "grad_norm": 3.271171226515435e-05,
-      "learning_rate": 1.1904761904761905e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 2.209205020920502,
-      "grad_norm": 4.509908103500493e-05,
-      "learning_rate": 1.0714285714285714e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 2.276150627615063,
-      "grad_norm": 0.0001721126027405262,
-      "learning_rate": 9.523809523809523e-06,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 2.3430962343096233,
-      "grad_norm": 3.9707927498966455e-05,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 2.410041841004184,
-      "grad_norm": 2.9311438993318006e-05,
-      "learning_rate": 7.142857142857143e-06,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 2.476987447698745,
-      "grad_norm": 1.4432046555157285e-05,
-      "learning_rate": 5.9523809523809525e-06,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 2.5439330543933054,
-      "grad_norm": 1.8700251530390233e-05,
-      "learning_rate": 4.7619047619047615e-06,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 2.6108786610878663,
-      "grad_norm": 3.1687275622971356e-05,
-      "learning_rate": 3.5714285714285714e-06,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 2.6778242677824267,
-      "grad_norm": 6.366440356941894e-05,
-      "learning_rate": 2.3809523809523808e-06,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 2.7447698744769875,
-      "grad_norm": 2.3581902496516705e-05,
-      "learning_rate": 1.1904761904761904e-06,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 2.8117154811715483,
-      "grad_norm": 0.04628070071339607,
-      "learning_rate": 0.0,
-      "loss": 0.0004,
-      "step": 42
     }
   ],
   "logging_steps": 1,
-  "max_steps": 42,
+  "max_steps": 39,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -315,7 +28,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ddfb64f72f79887e32d4e69bde9e2b6571dba4d5cc378f5f273ff94fbebb0ac
-size 5304
+oid sha256:30a2653054e0619da1c099bfd471f319db5d153cdf28d9ef1d40f203505cdca0
+size 5368