Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "shared_expert_gate",
     "gate",
-    "gate_proj",
     "v_proj",
-    "shared_expert_gate",
+    "gate_proj",
     "k_proj",
-    "q_proj",
+    "down_proj",
     "up_proj",
-    "down_proj"
+    "q_proj",
+    "o_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:c90fcc3b4b2628775508e9a5a1839959f2987e130bc41dd502291738f9fc0a1a
+oid sha256:a6e497b1ce6b627ea7da09527644c58698f3972c83d7bcfb0326006b675ed1aa
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a24f21c8fa910ea94cd9328c76a33460114593fc154be4139a2467100aa822
+oid sha256:6003483f3f5542d64f1cf902190b114e8e6af45ebec7a23330be28aa39597aaf
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
+oid sha256:2ca4e2bce515e7a88c44624c36d0bc76daf1fd306e88836f9dc2aaf5f09cd386
 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": 0.012562024998429747,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0002512404999685949,
+  "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": 0.0002512404999685949,
       "eval_loss": 11.934860229492188,
-      "eval_runtime": 40.0315,
-      "eval_samples_per_second": 41.867,
-      "eval_steps_per_second": 20.933,
+      "eval_runtime": 40.3871,
+      "eval_samples_per_second": 41.498,
+      "eval_steps_per_second": 20.749,
       "step": 1
-    },
-    {
-      "epoch": 0.0012562024998429746,
-      "grad_norm": 0.2730819582939148,
-      "learning_rate": 5e-05,
-      "loss": 11.9352,
-      "step": 5
-    },
-    {
-      "epoch": 0.0025124049996859492,
-      "grad_norm": 0.1563212126493454,
-      "learning_rate": 0.0001,
-      "loss": 11.9407,
-      "step": 10
-    },
-    {
-      "epoch": 0.0025124049996859492,
-      "eval_loss": 11.933594703674316,
-      "eval_runtime": 39.6685,
-      "eval_samples_per_second": 42.25,
-      "eval_steps_per_second": 21.125,
-      "step": 10
-    },
-    {
-      "epoch": 0.003768607499528924,
-      "grad_norm": 0.2707776725292206,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 11.93,
-      "step": 15
-    },
-    {
-      "epoch": 0.0050248099993718985,
-      "grad_norm": 0.19105862081050873,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 11.9298,
-      "step": 20
-    },
-    {
-      "epoch": 0.0050248099993718985,
-      "eval_loss": 11.930817604064941,
-      "eval_runtime": 39.8289,
-      "eval_samples_per_second": 42.08,
-      "eval_steps_per_second": 21.04,
-      "step": 20
-    },
-    {
-      "epoch": 0.006281012499214873,
-      "grad_norm": 0.17992514371871948,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 11.9294,
-      "step": 25
-    },
-    {
-      "epoch": 0.007537214999057848,
-      "grad_norm": 0.18809108436107635,
-      "learning_rate": 5e-05,
-      "loss": 11.93,
-      "step": 30
-    },
-    {
-      "epoch": 0.007537214999057848,
-      "eval_loss": 11.928617477416992,
-      "eval_runtime": 39.9206,
-      "eval_samples_per_second": 41.983,
-      "eval_steps_per_second": 20.992,
-      "step": 30
-    },
-    {
-      "epoch": 0.008793417498900823,
-      "grad_norm": 0.25860026478767395,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 11.9238,
-      "step": 35
-    },
-    {
-      "epoch": 0.010049619998743797,
-      "grad_norm": 0.2260095775127411,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 11.9298,
-      "step": 40
-    },
-    {
-      "epoch": 0.010049619998743797,
-      "eval_loss": 11.92742919921875,
-      "eval_runtime": 39.9959,
-      "eval_samples_per_second": 41.904,
-      "eval_steps_per_second": 20.952,
-      "step": 40
-    },
-    {
-      "epoch": 0.011305822498586773,
-      "grad_norm": 0.23762130737304688,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 11.933,
-      "step": 45
-    },
-    {
-      "epoch": 0.012562024998429747,
-      "grad_norm": 0.2021377682685852,
-      "learning_rate": 0.0,
-      "loss": 11.9325,
-      "step": 50
-    },
-    {
-      "epoch": 0.012562024998429747,
-      "eval_loss": 11.927210807800293,
-      "eval_runtime": 39.9491,
-      "eval_samples_per_second": 41.953,
-      "eval_steps_per_second": 20.977,
-      "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": 6257796710400.0,
+  "total_flos": 125155934208.0,
   "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 sha256:46ba157939a314bc995fb92e356a04e7137d28879658dda338900412f7796707
+oid sha256:aa1428edc12ebed704973c935480def3105f22112042b963b73574e7a6b178a1
 size 6776