Training in progress, step 12, checkpoint

checkpoint-12/adapter_config.json

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

checkpoint-12/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56000b728927322d9e86b8406ce9fad531e6c2668058306b8dde96f73edbd533
+oid sha256:dfdbb07538a47b1f579a81425d153481c6bf7e8b2b4b9e9312c4f6a93f54981a
 size 80013120

checkpoint-12/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fec7b939776120d9a838393230d787fc8c6d4ef77a0ec38f3465a1b4efca68d
+oid sha256:d4f01ff1f2816fdfff56c7f358509b2bd9937f359e8ba3e2d168334d44dfa80d
 size 160284754

checkpoint-12/trainer_state.json

@@ -10,118 +10,118 @@
   "log_history": [
     {
       "epoch": 0.0006200589055960316,
-      "grad_norm": 0.18599237501621246,
+      "grad_norm": 0.16878783702850342,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 0.9319,
+      "loss": 0.9729,
       "step": 1
     },
     {
       "epoch": 0.0012401178111920632,
-      "grad_norm": 0.09086523950099945,
+      "grad_norm": 0.0865061804652214,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.6463,
+      "loss": 0.6661,
       "step": 2
     },
     {
       "epoch": 0.0018601767167880949,
-      "grad_norm": 0.09325356036424637,
+      "grad_norm": 0.0920981764793396,
       "learning_rate": 1.2e-05,
-      "loss": 0.575,
+      "loss": 0.5954,
       "step": 3
     },
     {
       "epoch": 0.0018601767167880949,
-      "eval_loss": 0.7272388935089111,
-      "eval_runtime": 33.9288,
-      "eval_samples_per_second": 2.947,
-      "eval_steps_per_second": 2.947,
+      "eval_loss": 0.762992262840271,
+      "eval_runtime": 33.3972,
+      "eval_samples_per_second": 2.994,
+      "eval_steps_per_second": 2.994,
       "step": 3
     },
     {
       "epoch": 0.0024802356223841263,
-      "grad_norm": 0.09707680344581604,
+      "grad_norm": 0.10451442003250122,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.7038,
+      "loss": 0.7227,
       "step": 4
     },
     {
       "epoch": 0.0031002945279801583,
-      "grad_norm": 0.10810782760381699,
+      "grad_norm": 0.11351602524518967,
       "learning_rate": 2e-05,
-      "loss": 0.5471,
+      "loss": 0.5719,
       "step": 5
     },
     {
       "epoch": 0.0037203534335761897,
-      "grad_norm": 0.13030411303043365,
+      "grad_norm": 0.12484906613826752,
       "learning_rate": 1.9200000000000003e-05,
-      "loss": 0.6735,
+      "loss": 0.6972,
       "step": 6
     },
     {
       "epoch": 0.0037203534335761897,
-      "eval_loss": 0.7256982922554016,
-      "eval_runtime": 33.9528,
-      "eval_samples_per_second": 2.945,
-      "eval_steps_per_second": 2.945,
+      "eval_loss": 0.7615777850151062,
+      "eval_runtime": 33.3804,
+      "eval_samples_per_second": 2.996,
+      "eval_steps_per_second": 2.996,
       "step": 6
     },
     {
       "epoch": 0.004340412339172222,
-      "grad_norm": 0.12336976826190948,
+      "grad_norm": 0.11116621643304825,
       "learning_rate": 1.8400000000000003e-05,
-      "loss": 0.654,
+      "loss": 0.6789,
       "step": 7
     },
     {
       "epoch": 0.004960471244768253,
-      "grad_norm": 0.16046489775180817,
+      "grad_norm": 0.16013608872890472,
       "learning_rate": 1.76e-05,
-      "loss": 0.6301,
+      "loss": 0.6612,
       "step": 8
     },
     {
       "epoch": 0.005580530150364285,
-      "grad_norm": 0.11589628458023071,
+      "grad_norm": 0.1211152970790863,
       "learning_rate": 1.6800000000000002e-05,
-      "loss": 0.5326,
+      "loss": 0.5557,
       "step": 9
     },
     {
       "epoch": 0.005580530150364285,
-      "eval_loss": 0.723076343536377,
-      "eval_runtime": 34.5303,
-      "eval_samples_per_second": 2.896,
-      "eval_steps_per_second": 2.896,
+      "eval_loss": 0.7586225867271423,
+      "eval_runtime": 33.7015,
+      "eval_samples_per_second": 2.967,
+      "eval_steps_per_second": 2.967,
       "step": 9
     },
     {
       "epoch": 0.0062005890559603165,
-      "grad_norm": 0.12244553864002228,
+      "grad_norm": 0.1299518495798111,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.8055,
+      "loss": 0.8339,
       "step": 10
     },
     {
       "epoch": 0.0068206479615563476,
-      "grad_norm": 0.10270956158638,
+      "grad_norm": 0.11476285755634308,
       "learning_rate": 1.5200000000000002e-05,
-      "loss": 0.5492,
+      "loss": 0.5786,
       "step": 11
     },
     {
       "epoch": 0.0074407068671523795,
-      "grad_norm": 0.14439155161380768,
+      "grad_norm": 0.18253028392791748,
       "learning_rate": 1.4400000000000001e-05,
-      "loss": 0.8579,
+      "loss": 0.8889,
       "step": 12
     },
     {
       "epoch": 0.0074407068671523795,
-      "eval_loss": 0.7205619215965271,
-      "eval_runtime": 33.7297,
-      "eval_samples_per_second": 2.965,
-      "eval_steps_per_second": 2.965,
+      "eval_loss": 0.7548640966415405,
+      "eval_runtime": 34.763,
+      "eval_samples_per_second": 2.877,
+      "eval_steps_per_second": 2.877,
       "step": 12
     }
   ],
@@ -142,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5745185726971904e+16,
+  "total_flos": 1.5897880968413184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-12/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd165a72088a81e5441087b0ae01dd72f7f14c5dad6a2e407eebc961586b0fc2
+oid sha256:1fba20505ee5f941c5085404aed8036910f9919d2bc7b2ba5ba4186849388b0c
 size 5752