Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "v_proj",
+    "k_proj",
     "q_proj",
-    "gate_proj",
     "down_proj",
     "up_proj",
-    "o_proj",
-    "k_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 sha256:31d35e29e57fa5bad420fb6ad53cd99fe7e1934578b2cf4c5f02c11b6dc51ad6
+oid sha256:963c365400716f0cc638d50b03e00fcd58f55d509cede070138e7cd539e365e6
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28cae85a0e7a28d9440f12cd0a5ddf8ff133db2f69de4ca2570c8818ad979ba
+oid sha256:1264b0039dfb1665021e6d451daf5b53bb93debf33ee7aa95ae29335950122a7
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037efb1585de1959202c69f662c6218305d4387c1880c29474dfba03ffd3be46
+oid sha256:3d20938fdf180abcaa5fb4311a1433c95811c7ad7a2a935c0fa2fec209987e03
 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

@@ -1,102 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2552648372686662,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00031913196106590075,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.005105296745373325,
-      "eval_loss": 0.6308530569076538,
-      "eval_runtime": 34.3499,
-      "eval_samples_per_second": 38.428,
-      "eval_steps_per_second": 4.804,
+      "epoch": 0.00031913196106590075,
+      "eval_loss": 0.6470243334770203,
+      "eval_runtime": 43.9047,
+      "eval_samples_per_second": 30.065,
+      "eval_steps_per_second": 15.033,
       "step": 1
-    },
-    {
-      "epoch": 0.05105296745373325,
-      "grad_norm": 0.10898499190807343,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 0.6061,
-      "step": 10
-    },
-    {
-      "epoch": 0.05105296745373325,
-      "eval_loss": 0.6026803851127625,
-      "eval_runtime": 34.5662,
-      "eval_samples_per_second": 38.188,
-      "eval_steps_per_second": 4.773,
-      "step": 10
-    },
-    {
-      "epoch": 0.1021059349074665,
-      "grad_norm": 0.06684104353189468,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.5841,
-      "step": 20
-    },
-    {
-      "epoch": 0.1021059349074665,
-      "eval_loss": 0.5628232359886169,
-      "eval_runtime": 34.3843,
-      "eval_samples_per_second": 38.39,
-      "eval_steps_per_second": 4.799,
-      "step": 20
-    },
-    {
-      "epoch": 0.15315890236119975,
-      "grad_norm": 0.07069219648838043,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.5459,
-      "step": 30
-    },
-    {
-      "epoch": 0.15315890236119975,
-      "eval_loss": 0.5473927855491638,
-      "eval_runtime": 34.3812,
-      "eval_samples_per_second": 38.393,
-      "eval_steps_per_second": 4.799,
-      "step": 30
-    },
-    {
-      "epoch": 0.204211869814933,
-      "grad_norm": 0.0595882311463356,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.5444,
-      "step": 40
-    },
-    {
-      "epoch": 0.204211869814933,
-      "eval_loss": 0.540993332862854,
-      "eval_runtime": 34.4989,
-      "eval_samples_per_second": 38.262,
-      "eval_steps_per_second": 4.783,
-      "step": 40
-    },
-    {
-      "epoch": 0.2552648372686662,
-      "grad_norm": 0.05125812813639641,
-      "learning_rate": 0.0,
-      "loss": 0.5309,
-      "step": 50
-    },
-    {
-      "epoch": 0.2552648372686662,
-      "eval_loss": 0.5400261282920837,
-      "eval_runtime": 34.4315,
-      "eval_samples_per_second": 38.337,
-      "eval_steps_per_second": 4.792,
-      "step": 50
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 50,
+  "logging_steps": 5,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -109,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.09267165200384e+16,
-  "train_batch_size": 8,
+  "total_flos": 51158395650048.0,
+  "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 sha256:7f2c36495ffe3b9769cca0310456430bc45e2b19be44969c7ce705fc062b4547
+oid sha256:1bba32aeaafc7ab78ebc1a8823ff2d0019269f2a5e56415f61cef1bb2eee9a69
 size 6776