Training in progress, step 6, 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 sha256:1ddd0bfa337995872206a908ff6c31d7f22a65a8b352afcb3f79bb895124bf8f
+oid sha256:c1d63cf8f6ef2d576643283d509afb4bb6838a70e0ac66bec9ce82ec82760175
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f8c3c9aa5490a356e1a0bf3d542da3411c36bd7c0824d4df71dd45b464b55e
+oid sha256:23d83e937d684ae9b0f2ab436f43fe8d4cc0d454ef86c216002ada9c8554db59
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,114 +1,78 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005988023952095809,
+  "epoch": 0.001796541657309679,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 6,
   "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,
+      "epoch": 0.0011976944382064525,
+      "grad_norm": 11.335941314697266,
       "learning_rate": 2e-05,
-      "loss": 11.4872,
+      "loss": 9.5838,
       "step": 4
     },
     {
-      "epoch": 0.0029940119760479044,
-      "grad_norm": 6.535604953765869,
+      "epoch": 0.0014971180477580657,
+      "grad_norm": 12.509073257446289,
       "learning_rate": 4e-05,
-      "loss": 9.9558,
+      "loss": 11.0567,
       "step": 5
     },
     {
-      "epoch": 0.003592814371257485,
-      "grad_norm": 8.272323608398438,
+      "epoch": 0.001796541657309679,
+      "grad_norm": 13.569826126098633,
       "learning_rate": 6e-05,
-      "loss": 11.9577,
+      "loss": 12.2136,
       "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,
+      "epoch": 0.001796541657309679,
+      "eval_loss": 11.521071434020996,
+      "eval_runtime": 94.7717,
+      "eval_samples_per_second": 7.428,
+      "eval_steps_per_second": 7.428,
       "step": 6
-    },
-    {
-      "epoch": 0.004191616766467066,
-      "grad_norm": 8.094924926757812,
-      "learning_rate": 8e-05,
-      "loss": 12.3056,
-      "step": 7
-    },
-    {
-      "epoch": 0.004790419161676647,
-      "grad_norm": 9.111627578735352,
-      "learning_rate": 0.0001,
-      "loss": 9.0397,
-      "step": 8
-    },
-    {
-      "epoch": 0.005389221556886228,
-      "grad_norm": 6.980569839477539,
-      "learning_rate": 0.00012,
-      "loss": 9.2177,
-      "step": 9
-    },
-    {
-      "epoch": 0.005389221556886228,
-      "eval_loss": 10.915068626403809,
-      "eval_runtime": 47.9969,
-      "eval_samples_per_second": 14.668,
-      "eval_steps_per_second": 7.334,
-      "step": 9
-    },
-    {
-      "epoch": 0.005988023952095809,
-      "grad_norm": NaN,
-      "learning_rate": 0.00012,
-      "loss": 8.6476,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +87,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 1109738548887552.0,
   "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