Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "gate_proj",
     "q_proj",
+    "o_proj",
     "k_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
-    "up_proj"
+    "up_proj",
+    "down_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 sha256:2774a796753478dafed475f6ae03274c1ed79d5c1dea054850a91fc6c244def0
+oid sha256:311a52b716b3339c60a62267c8aa5422f7cbb319cc51e92f9393193e16a0be71
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7267e6d6a40d6f7a56890b005aedc5561255d442204033ec2901437e97ee525
+oid sha256:04e1ff5a56ff1a2121e7a6d994036ff4533b890112ba5b5dc6ff4040d96dd92c
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac727c8d1b09cb5c6714aef1e24be1f747baf4690a1f0b52b6673366565e9cf
+oid sha256:2206eceda46b84e781d40b70679282f57883db1be9922375ac5f34eb91c6e125
 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": 0.0005526648115551159,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 1.1053296231102318e-05,
+  "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": 1.1053296231102318e-05,
       "eval_loss": 3.9584224224090576,
-      "eval_runtime": 2867.572,
-      "eval_samples_per_second": 13.284,
-      "eval_steps_per_second": 6.642,
+      "eval_runtime": 2351.5782,
+      "eval_samples_per_second": 16.199,
+      "eval_steps_per_second": 8.1,
       "step": 1
-    },
-    {
-      "epoch": 5.526648115551159e-05,
-      "grad_norm": 4.578774452209473,
-      "learning_rate": 5e-05,
-      "loss": 3.6034,
-      "step": 5
-    },
-    {
-      "epoch": 0.00011053296231102318,
-      "grad_norm": 11.06997299194336,
-      "learning_rate": 0.0001,
-      "loss": 3.0673,
-      "step": 10
-    },
-    {
-      "epoch": 0.00011053296231102318,
-      "eval_loss": 2.7215049266815186,
-      "eval_runtime": 2047.2854,
-      "eval_samples_per_second": 18.607,
-      "eval_steps_per_second": 9.304,
-      "step": 10
-    },
-    {
-      "epoch": 0.00016579944346653476,
-      "grad_norm": 12.175200462341309,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 2.0786,
-      "step": 15
-    },
-    {
-      "epoch": 0.00022106592462204635,
-      "grad_norm": 9.548558235168457,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 1.3026,
-      "step": 20
-    },
-    {
-      "epoch": 0.00022106592462204635,
-      "eval_loss": 1.2258411645889282,
-      "eval_runtime": 2054.8525,
-      "eval_samples_per_second": 18.538,
-      "eval_steps_per_second": 9.269,
-      "step": 20
-    },
-    {
-      "epoch": 0.00027633240577755794,
-      "grad_norm": 7.163697242736816,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 1.161,
-      "step": 25
-    },
-    {
-      "epoch": 0.00033159888693306953,
-      "grad_norm": 7.7752156257629395,
-      "learning_rate": 5e-05,
-      "loss": 0.7917,
-      "step": 30
-    },
-    {
-      "epoch": 0.00033159888693306953,
-      "eval_loss": 0.6201350688934326,
-      "eval_runtime": 2061.1401,
-      "eval_samples_per_second": 18.482,
-      "eval_steps_per_second": 9.241,
-      "step": 30
-    },
-    {
-      "epoch": 0.0003868653680885811,
-      "grad_norm": 9.875985145568848,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.8146,
-      "step": 35
-    },
-    {
-      "epoch": 0.0004421318492440927,
-      "grad_norm": 17.325223922729492,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.2595,
-      "step": 40
-    },
-    {
-      "epoch": 0.0004421318492440927,
-      "eval_loss": 0.43640169501304626,
-      "eval_runtime": 2052.9477,
-      "eval_samples_per_second": 18.555,
-      "eval_steps_per_second": 9.278,
-      "step": 40
-    },
-    {
-      "epoch": 0.0004973983303996043,
-      "grad_norm": 4.131010055541992,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.2891,
-      "step": 45
-    },
-    {
-      "epoch": 0.0005526648115551159,
-      "grad_norm": 7.422944068908691,
-      "learning_rate": 0.0,
-      "loss": 0.4703,
-      "step": 50
-    },
-    {
-      "epoch": 0.0005526648115551159,
-      "eval_loss": 0.4152521789073944,
-      "eval_runtime": 2055.2428,
-      "eval_samples_per_second": 18.535,
-      "eval_steps_per_second": 9.268,
-      "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": 3793452898713600.0,
+  "total_flos": 85658613841920.0,
   "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 sha256:2a2a56c9314838ee773f0e2139bc7c5ee1a5a6020d47cecb8792d1c2eb45070e
+oid sha256:0a28599c7fc0a215525d73691b99f1a62e15c0977e8bca0dfdee80c494d67c83
 size 6776