Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
     "up_proj",
+    "q_proj",
+    "o_proj",
     "v_proj",
+    "down_proj",
     "k_proj",
-    "q_proj",
-    "down_proj"
+    "gate_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 sha256:5c80f3a2378a62131102f67eb69aa98904930dfd2f1e150d8b8a19e566a72a3b
+oid sha256:992202a3c8e81c87b97a47360e2c6fc19901834658ce20ce2945945f4849a755
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a985bef33a45c9370ec847c76601858d78ec06782e5d1ccb312561b73188777c
+oid sha256:e29e706d524862f4a465358879a7fc8b718a12834cfa579ad1da94f8fb9244b1
 size 45221242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8533ac5c809e23e45fa3502773ae0eeaf07bc3c38c0faa86616fda6bd7fa0465
+oid sha256:b84d16d72b7e6ff5d6769d55df31c36b252d605a20a4c4c276e5840c32f666b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004938068392247233,
+  "epoch": 0.0007407102588370849,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 8.23011398707872e-05,
-      "grad_norm": 0.6557537913322449,
+      "grad_norm": 0.7503308057785034,
       "learning_rate": 2e-05,
       "loss": 1.5917,
       "step": 1
@@ -18,61 +18,90 @@
     {
       "epoch": 8.23011398707872e-05,
       "eval_loss": 1.959477186203003,
-      "eval_runtime": 135.3765,
-      "eval_samples_per_second": 18.895,
-      "eval_steps_per_second": 18.895,
+      "eval_runtime": 133.9988,
+      "eval_samples_per_second": 19.09,
+      "eval_steps_per_second": 19.09,
       "step": 1
     },
     {
       "epoch": 0.0001646022797415744,
-      "grad_norm": 0.7621749639511108,
+      "grad_norm": 0.8759475350379944,
       "learning_rate": 4e-05,
       "loss": 1.8288,
       "step": 2
     },
     {
       "epoch": 0.00024690341961236165,
-      "grad_norm": 0.5589603781700134,
+      "grad_norm": 0.6373544931411743,
       "learning_rate": 6e-05,
-      "loss": 1.0263,
+      "loss": 1.0265,
       "step": 3
     },
     {
       "epoch": 0.00024690341961236165,
-      "eval_loss": 1.957216739654541,
-      "eval_runtime": 161.0963,
-      "eval_samples_per_second": 15.879,
-      "eval_steps_per_second": 15.879,
+      "eval_loss": 1.9565452337265015,
+      "eval_runtime": 160.8486,
+      "eval_samples_per_second": 15.903,
+      "eval_steps_per_second": 15.903,
       "step": 3
     },
     {
       "epoch": 0.0003292045594831488,
-      "grad_norm": 0.858914315700531,
+      "grad_norm": 0.9935461282730103,
       "learning_rate": 8e-05,
-      "loss": 1.6087,
+      "loss": 1.6082,
       "step": 4
     },
     {
       "epoch": 0.00041150569935393603,
-      "grad_norm": 0.7685796618461609,
+      "grad_norm": 0.8985377550125122,
       "learning_rate": 0.0001,
-      "loss": 1.3328,
+      "loss": 1.332,
       "step": 5
     },
     {
       "epoch": 0.0004938068392247233,
-      "grad_norm": 0.6958107948303223,
+      "grad_norm": 0.804458498954773,
       "learning_rate": 0.00012,
-      "loss": 1.2796,
+      "loss": 1.2777,
       "step": 6
     },
     {
       "epoch": 0.0004938068392247233,
-      "eval_loss": 1.9416530132293701,
-      "eval_runtime": 172.4872,
-      "eval_samples_per_second": 14.83,
-      "eval_steps_per_second": 14.83,
+      "eval_loss": 1.9385048151016235,
+      "eval_runtime": 172.7761,
+      "eval_samples_per_second": 14.805,
+      "eval_steps_per_second": 14.805,
       "step": 6
+    },
+    {
+      "epoch": 0.0005761079790955105,
+      "grad_norm": 0.7060862183570862,
+      "learning_rate": 0.00014,
+      "loss": 1.3273,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006584091189662976,
+      "grad_norm": 0.9895685911178589,
+      "learning_rate": 0.00016,
+      "loss": 1.6312,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007407102588370849,
+      "grad_norm": 0.8735620975494385,
+      "learning_rate": 0.00018,
+      "loss": 1.4144,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007407102588370849,
+      "eval_loss": 1.9004994630813599,
+      "eval_runtime": 171.1439,
+      "eval_samples_per_second": 14.946,
+      "eval_steps_per_second": 14.946,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 144327309262848.0,
+  "total_flos": 216490963894272.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923ce18a73524fc48b19c36dee905217bafd6d65025d46d8a80d999e0fe09dba
+oid sha256:478a261d562ef7004d0f64e3e27b2ba59d503990d5008804b57fbc37d15611f7
 size 6776