Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
+    "dense",
     "query_key_value",
     "dense_h_to_4h",
-    "dense"
+    "dense_4h_to_h"
   ],
   "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:b0b82afae4229197820d7f65006967bd90ef20ae10fdafc2e7b8b974d3968ced
+oid sha256:dfac8e4c7fd7ff0f678d19ecb96db7f2bd4ffe865ed5744b809b78fd2dac9c76
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d7c503efc99c8dc9c0c2feb507b19d7f4a02c7d9e6e73eb85ca453a050d703
+oid sha256:c0fc53bdc480179b4eb678a72d487fb8d7741455a1ed6dec588ac1cf8eac80ee
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f60ef2192d3634423e0b411609bc5f9c4f5e662023d73fd1a3f0d934e38f842
+oid sha256:eb1228e8df97a1d799b51d461e89faa3c8b34af3eaad77d8523d93156c1e565e
 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": 0.007939343416299472,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00015878686832598943,
+  "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": 0.00015878686832598943,
       "eval_loss": 10.346136093139648,
-      "eval_runtime": 277.4907,
-      "eval_samples_per_second": 9.557,
-      "eval_steps_per_second": 4.779,
+      "eval_runtime": 280.1788,
+      "eval_samples_per_second": 9.465,
+      "eval_steps_per_second": 4.733,
       "step": 1
-    },
-    {
-      "epoch": 0.0007939343416299473,
-      "grad_norm": 15.469205856323242,
-      "learning_rate": 5e-05,
-      "loss": 41.5698,
-      "step": 5
-    },
-    {
-      "epoch": 0.0015878686832598945,
-      "grad_norm": 38.79508590698242,
-      "learning_rate": 0.0001,
-      "loss": 38.9257,
-      "step": 10
-    },
-    {
-      "epoch": 0.0015878686832598945,
-      "eval_loss": 7.56179141998291,
-      "eval_runtime": 277.4419,
-      "eval_samples_per_second": 9.559,
-      "eval_steps_per_second": 4.779,
-      "step": 10
-    },
-    {
-      "epoch": 0.0023818030248898415,
-      "grad_norm": 27.791574478149414,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 20.8014,
-      "step": 15
-    },
-    {
-      "epoch": 0.003175737366519789,
-      "grad_norm": 49.56751251220703,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 7.8074,
-      "step": 20
-    },
-    {
-      "epoch": 0.003175737366519789,
-      "eval_loss": 0.9204622507095337,
-      "eval_runtime": 276.9363,
-      "eval_samples_per_second": 9.576,
-      "eval_steps_per_second": 4.788,
-      "step": 20
-    },
-    {
-      "epoch": 0.003969671708149736,
-      "grad_norm": 56.36249923706055,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 2.338,
-      "step": 25
-    },
-    {
-      "epoch": 0.004763606049779683,
-      "grad_norm": 49.43033218383789,
-      "learning_rate": 5e-05,
-      "loss": 1.5196,
-      "step": 30
-    },
-    {
-      "epoch": 0.004763606049779683,
-      "eval_loss": 0.34085649251937866,
-      "eval_runtime": 278.0357,
-      "eval_samples_per_second": 9.538,
-      "eval_steps_per_second": 4.769,
-      "step": 30
-    },
-    {
-      "epoch": 0.00555754039140963,
-      "grad_norm": 18.811370849609375,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 1.1971,
-      "step": 35
-    },
-    {
-      "epoch": 0.006351474733039578,
-      "grad_norm": 15.046299934387207,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.8589,
-      "step": 40
-    },
-    {
-      "epoch": 0.006351474733039578,
-      "eval_loss": 0.24986527860164642,
-      "eval_runtime": 276.9621,
-      "eval_samples_per_second": 9.575,
-      "eval_steps_per_second": 4.788,
-      "step": 40
-    },
-    {
-      "epoch": 0.007145409074669525,
-      "grad_norm": 23.047611236572266,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.9236,
-      "step": 45
-    },
-    {
-      "epoch": 0.007939343416299472,
-      "grad_norm": 15.0563383102417,
-      "learning_rate": 0.0,
-      "loss": 0.9677,
-      "step": 50
-    },
-    {
-      "epoch": 0.007939343416299472,
-      "eval_loss": 0.2238224744796753,
-      "eval_runtime": 278.2518,
-      "eval_samples_per_second": 9.531,
-      "eval_steps_per_second": 4.765,
-      "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": 1.571260104572928e+16,
+  "total_flos": 326495606145024.0,
   "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 sha256:3e6b6b3dd0198fc8ffb842cc44b96bffda807040dc26380a286a84a63fe9b624
+oid sha256:a7367902910175213681c3e5a3ff786804323f7975f1881a6ea4a712d049dccc
 size 6776