Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "qkv_proj",
     "o_proj",
+    "qkv_proj",
+    "down_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a069c8ef4d87766802b4e104e45510f4e37544907c502c55f9dbcffcc733291
+oid sha256:10b8972bcf221ac32ade06daab3307654feee6542eae4967d50602f03d4ffb7a
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0c5da47714024ba4ccd75ab0e9f6c8e26e4ea424dea1b070b74f5f6881f21a
+oid sha256:de0afaace44eb727f3e02859d81945b36eac3620c9686dbeb19b95fd6460900b
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1fa59a5b80afbc921e6683688a2141f4895c30bdd2c52d1c6cab167c997be7
+oid sha256:443e4d5606026da0009399449f5ad419c10e038ad5982a08edaaafcdbd5aa67e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.14216215115924e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0010584810796507012,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 8.14216215115924e-05,
       "eval_loss": 2.5727338790893555,
-      "eval_runtime": 658.8811,
-      "eval_samples_per_second": 7.85,
-      "eval_steps_per_second": 3.925,
+      "eval_runtime": 658.2171,
+      "eval_samples_per_second": 7.858,
+      "eval_steps_per_second": 3.929,
       "step": 1
+    },
+    {
+      "epoch": 0.00040710810755796204,
+      "grad_norm": 3.0211687088012695,
+      "learning_rate": 5e-05,
+      "loss": 9.7985,
+      "step": 5
+    },
+    {
+      "epoch": 0.0008142162151159241,
+      "grad_norm": 6.464580059051514,
+      "learning_rate": 0.0001,
+      "loss": 10.5411,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008142162151159241,
+      "eval_loss": 2.4812233448028564,
+      "eval_runtime": 659.0524,
+      "eval_samples_per_second": 7.848,
+      "eval_steps_per_second": 3.924,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 183590675546112.0,
+  "total_flos": 2226036940996608.0,
   "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 sha256:35c1e488a667e502e488ec15aaeba7ae7d00f3036cd658c4eaf3a83e231e566e
+oid sha256:d31096df82bad6665abde24045196e981fab975053e68f7980a11b2e51fc5ed6
 size 6776