Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "v_proj",
     "q_proj",
-    "gate_proj",
-    "k_proj",
-    "up_proj",
+    "down_proj",
     "o_proj",
-    "v_proj"
+    "up_proj",
+    "gate_proj",
+    "k_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:c32514e354b6d09fc79c674ee149cb36139ff7a0e4f49d81c13e17f27c9064d4
+oid sha256:89ebd70b7f581a26b358316551aa9125aced9ba97b19403aa7625805c97e83ba
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f35a23aa1a9990cc0a4971e7208c8803b940a85e13943c3d4bc8a4af22290b9
-size 168037178
+oid sha256:50034867d33500fcbca5f263e64df4948cb0350e33b3094632dfba4eacd405fe
+size 2216

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
 size 1064

last-checkpoint/trainer_state.json

@@ -1,78 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003592814371257485,
+  "epoch": 0.0008982708286548395,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0005988023952095808,
+      "epoch": 0.0002994236095516131,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 10.8959,
+      "loss": 10.9802,
       "step": 1
     },
     {
-      "epoch": 0.0005988023952095808,
-      "eval_loss": 11.577476501464844,
-      "eval_runtime": 47.7616,
-      "eval_samples_per_second": 14.74,
-      "eval_steps_per_second": 7.37,
+      "epoch": 0.0002994236095516131,
+      "eval_loss": 11.5775728225708,
+      "eval_runtime": 95.8713,
+      "eval_samples_per_second": 7.343,
+      "eval_steps_per_second": 7.343,
       "step": 1
     },
     {
-      "epoch": 0.0011976047904191617,
+      "epoch": 0.0005988472191032262,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 10.0136,
+      "loss": 10.7165,
       "step": 2
     },
     {
-      "epoch": 0.0017964071856287425,
+      "epoch": 0.0008982708286548395,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 11.649,
+      "loss": 10.434,
       "step": 3
     },
     {
-      "epoch": 0.0017964071856287425,
-      "eval_loss": 11.577476501464844,
-      "eval_runtime": 47.9565,
-      "eval_samples_per_second": 14.68,
-      "eval_steps_per_second": 7.34,
+      "epoch": 0.0008982708286548395,
+      "eval_loss": 11.5775728225708,
+      "eval_runtime": 94.6943,
+      "eval_samples_per_second": 7.434,
+      "eval_steps_per_second": 7.434,
       "step": 3
-    },
-    {
-      "epoch": 0.0023952095808383233,
-      "grad_norm": 9.167847633361816,
-      "learning_rate": 2e-05,
-      "loss": 11.4872,
-      "step": 4
-    },
-    {
-      "epoch": 0.0029940119760479044,
-      "grad_norm": 6.535604953765869,
-      "learning_rate": 4e-05,
-      "loss": 9.9558,
-      "step": 5
-    },
-    {
-      "epoch": 0.003592814371257485,
-      "grad_norm": 8.272323608398438,
-      "learning_rate": 6e-05,
-      "loss": 11.9577,
-      "step": 6
-    },
-    {
-      "epoch": 0.003592814371257485,
-      "eval_loss": 11.506834983825684,
-      "eval_runtime": 47.6191,
-      "eval_samples_per_second": 14.784,
-      "eval_steps_per_second": 7.392,
-      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -92,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 554869274443776.0,
   "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 sha256:6bc64a63498e1a4fd3792d98994b6d4b37c859bdb415f82833cc56bc99d4df9e
+oid sha256:ed5cf1a7f24b2f4b6ffdd137a7076d460d56660645e71b5af0068e2d73030f31
 size 6776