Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
-    "q_proj",
     "o_proj",
-    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
     "v_proj",
-    "gate_proj"
+    "k_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:b223e30d8c9bbebf54351b7cf7b34b0849a4652f452b06d4ef2624ec31855119
+oid sha256:b533b7117bc0e3c81f20822c894195616054d12b9a0cdcfb40e420186d215d2a
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3470004bc3d15c18ea2624c80f07ad8a5ed20b05b353785a3c2fa87f54c561
+oid sha256:6f42ed2f7db2eb0efb886fd0c06f7bbded3dbda320f1d1b8a30c808868f264a9
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bcf5ac8488b2a4c6dbe42b144f3d1d61b237d080b40d4d50265b37a38585d5
+oid sha256:e3e7f581cbfcc9ee011f6906f74fe1cae71cebb72a9de5faedb960a4a724a10b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f883fd9393081a5c2e54691be1749bef50e284275a9e7a1c589cf11727a2e22b
+oid sha256:ebe0540ed6e94d693724d0fd61916b0efd9dc6adbac83c0b0a2d35823214a0a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,38 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00013455328310010763,
+  "epoch": 6.727664155005382e-05,
   "eval_steps": 500,
-  "global_step": 2,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 6.727664155005382e-05,
-      "grad_norm": 0.13251228630542755,
+      "grad_norm": 0.1577831506729126,
       "learning_rate": 0.0001,
       "loss": 11.9692,
       "step": 1
     },
     {
-      "epoch": 0.00013455328310010763,
-      "grad_norm": 0.032421912997961044,
-      "learning_rate": 0.0002,
-      "loss": 11.931,
-      "step": 2
-    },
-    {
-      "epoch": 0.00013455328310010763,
-      "eval_loss": 11.932136535644531,
-      "eval_runtime": 0.7625,
-      "eval_samples_per_second": 198.036,
-      "eval_steps_per_second": 198.036,
-      "step": 2
+      "epoch": 6.727664155005382e-05,
+      "eval_loss": 11.932138442993164,
+      "eval_runtime": 0.7745,
+      "eval_samples_per_second": 194.959,
+      "eval_steps_per_second": 194.959,
+      "step": 1
     }
   ],
   "logging_steps": 1,
-  "max_steps": 2,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -48,7 +41,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7385088.0,
+  "total_flos": 3692544.0,
   "train_batch_size": 1,
   "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:dce5acab224b5c3a108ca0fe2f9d758fbfc0ad3d00d3c86ddb99c6b0338681e0
+oid sha256:746519a0d96e6801b9e01fd3392d353e8f9467d5d8a337d4d558559fbbc2a9f0
 size 6776