Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "down_proj",
     "k_proj",
     "gate_proj",
+    "o_proj",
     "up_proj",
     "v_proj",
-    "q_proj",
-    "down_proj"
+    "q_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:bcf8f3f81077c72b30757b447323ff03eafe77a4c7a7c16fc24907fdc8bfe29d
+oid sha256:da7a7bfa3c9e322c18f110a1dd21f7919c4e2959c2fa1b459904044f9946a0a8
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb97cff48ebb4707b5c7966da00071b163a2170a1b90811e7f23c85e3eb6df90
+oid sha256:3722569925c9a26ca6bd9d0a34b2e3cee883cb8e9cae7a6c78947c515a35018b
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6035abaef6269d017307cb69d94afde51c7a814a09f6c71bcbc401d0d2da6877
+oid sha256:81b0fa30ce7d6caf58ef5c2227062e5ee5947fe33564486703caa8d601663ea6
 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": 0.02658160552897395,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.000531632110579479,
+  "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": 0.000531632110579479,
       "eval_loss": 2.794513702392578,
-      "eval_runtime": 35.2595,
-      "eval_samples_per_second": 22.462,
-      "eval_steps_per_second": 11.231,
+      "eval_runtime": 26.5875,
+      "eval_samples_per_second": 29.788,
+      "eval_steps_per_second": 14.894,
       "step": 1
-    },
-    {
-      "epoch": 0.002658160552897395,
-      "grad_norm": 2.5087876319885254,
-      "learning_rate": 5e-05,
-      "loss": 2.9129,
-      "step": 5
-    },
-    {
-      "epoch": 0.00531632110579479,
-      "grad_norm": 3.172278881072998,
-      "learning_rate": 0.0001,
-      "loss": 2.5148,
-      "step": 10
-    },
-    {
-      "epoch": 0.00531632110579479,
-      "eval_loss": 2.32590651512146,
-      "eval_runtime": 26.5891,
-      "eval_samples_per_second": 29.787,
-      "eval_steps_per_second": 14.893,
-      "step": 10
-    },
-    {
-      "epoch": 0.007974481658692184,
-      "grad_norm": 2.6018869876861572,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 1.7981,
-      "step": 15
-    },
-    {
-      "epoch": 0.01063264221158958,
-      "grad_norm": 1.8246312141418457,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 1.145,
-      "step": 20
-    },
-    {
-      "epoch": 0.01063264221158958,
-      "eval_loss": 0.6814725399017334,
-      "eval_runtime": 27.0108,
-      "eval_samples_per_second": 29.322,
-      "eval_steps_per_second": 14.661,
-      "step": 20
-    },
-    {
-      "epoch": 0.013290802764486975,
-      "grad_norm": 2.5452466011047363,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.6943,
-      "step": 25
-    },
-    {
-      "epoch": 0.01594896331738437,
-      "grad_norm": 1.912396788597107,
-      "learning_rate": 5e-05,
-      "loss": 0.3943,
-      "step": 30
-    },
-    {
-      "epoch": 0.01594896331738437,
-      "eval_loss": 0.2496986836194992,
-      "eval_runtime": 27.3235,
-      "eval_samples_per_second": 28.986,
-      "eval_steps_per_second": 14.493,
-      "step": 30
-    },
-    {
-      "epoch": 0.018607123870281767,
-      "grad_norm": 0.5929796099662781,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.1247,
-      "step": 35
-    },
-    {
-      "epoch": 0.02126528442317916,
-      "grad_norm": 1.806302547454834,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.1757,
-      "step": 40
-    },
-    {
-      "epoch": 0.02126528442317916,
-      "eval_loss": 0.1834142655134201,
-      "eval_runtime": 27.0169,
-      "eval_samples_per_second": 29.315,
-      "eval_steps_per_second": 14.657,
-      "step": 40
-    },
-    {
-      "epoch": 0.023923444976076555,
-      "grad_norm": 2.3250198364257812,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.2178,
-      "step": 45
-    },
-    {
-      "epoch": 0.02658160552897395,
-      "grad_norm": 0.5584317445755005,
-      "learning_rate": 0.0,
-      "loss": 0.0977,
-      "step": 50
-    },
-    {
-      "epoch": 0.02658160552897395,
-      "eval_loss": 0.17906339466571808,
-      "eval_runtime": 26.7116,
-      "eval_samples_per_second": 29.65,
-      "eval_steps_per_second": 14.825,
-      "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": 1581936279552000.0,
+  "total_flos": 31638725591040.0,
   "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 sha256:4d8014bdbf365b7c80c19de9c9ffd0ae1c588b167a2374fea0ff34c2127a39f0
+oid sha256:91f112afae4e2301bbefc56d64d917f6205e0d3af916c3d8ee71db3d6b725c73
 size 6776