Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
     "down_proj",
     "o_proj",
     "up_proj",
-    "v_proj",
-    "q_proj"
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "v_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 sha256:2daa5bd55bedf198d1d64977bc8928cfc4ab1338646ed22b35c439ed81cc47ca
+oid sha256:b071be95eb2e1fa59e3d854e8765b01cdaa7bfe88136978cec3e9867389328f7
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011b229cf7932128024efaacc2097c7654c6fd396ad6ac1ebed40b7d7000e61
+oid sha256:41697e6396c5d85ff41eb38449bbeb93bce2966915a50942504fcf7aff33f712
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82b625db56507f447e53f457cd40a516407fb4c508f6a80ad29dded2571bb42
+oid sha256:e96084db0d88b3f6f054fd8e1ee389d8068f68911086b40d9534c6441e1738ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02632964718272775,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.000526592943654555,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 0.000526592943654555,
       "eval_loss": 10.178997039794922,
-      "eval_runtime": 21.5369,
-      "eval_samples_per_second": 37.146,
-      "eval_steps_per_second": 18.573,
+      "eval_runtime": 20.8513,
+      "eval_samples_per_second": 38.367,
+      "eval_steps_per_second": 19.183,
       "step": 1
-    },
-    {
-      "epoch": 0.0026329647182727752,
-      "grad_norm": 21.805500030517578,
-      "learning_rate": 5e-05,
-      "loss": 10.0321,
-      "step": 5
-    },
-    {
-      "epoch": 0.0052659294365455505,
-      "grad_norm": 24.200536727905273,
-      "learning_rate": 0.0001,
-      "loss": 7.6786,
-      "step": 10
-    },
-    {
-      "epoch": 0.0052659294365455505,
-      "eval_loss": 3.4688384532928467,
-      "eval_runtime": 21.6215,
-      "eval_samples_per_second": 37.0,
-      "eval_steps_per_second": 18.5,
-      "step": 10
-    },
-    {
-      "epoch": 0.007898894154818325,
-      "grad_norm": 1.099424123764038,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 1.3599,
-      "step": 15
-    },
-    {
-      "epoch": 0.010531858873091101,
-      "grad_norm": 0.0010866125812754035,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0009,
-      "step": 20
-    },
-    {
-      "epoch": 0.010531858873091101,
-      "eval_loss": 4.6386987378355116e-05,
-      "eval_runtime": 21.566,
-      "eval_samples_per_second": 37.095,
-      "eval_steps_per_second": 18.548,
-      "step": 20
-    },
-    {
-      "epoch": 0.013164823591363875,
-      "grad_norm": 0.0039704530499875546,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.01579778830963665,
-      "grad_norm": 0.00037722557317465544,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.01579778830963665,
-      "eval_loss": 3.998309239250375e-06,
-      "eval_runtime": 21.6363,
-      "eval_samples_per_second": 36.975,
-      "eval_steps_per_second": 18.487,
-      "step": 30
-    },
-    {
-      "epoch": 0.018430753027909426,
-      "grad_norm": 0.0013271215138956904,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.021063717746182202,
-      "grad_norm": 0.0011808726703748107,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.021063717746182202,
-      "eval_loss": 3.2110322081280174e-06,
-      "eval_runtime": 21.2044,
-      "eval_samples_per_second": 37.728,
-      "eval_steps_per_second": 18.864,
-      "step": 40
-    },
-    {
-      "epoch": 0.023696682464454975,
-      "grad_norm": 0.0005120717105455697,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.02632964718272775,
-      "grad_norm": 0.0004391983966343105,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.02632964718272775,
-      "eval_loss": 3.196502120772493e-06,
-      "eval_runtime": 21.1976,
-      "eval_samples_per_second": 37.74,
-      "eval_steps_per_second": 18.87,
-      "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1202727577190400.0,
+  "total_flos": 24054551543808.0,
   "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 sha256:6dbfaf21602a949fb6188f79d43407ad28956e1d0fef6098b9e75a042893d463
+oid sha256:0ed38aa868afb29637e8105f6176eccb4c2984beb09e4927af87d52267ef29a7
 size 6776