Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "v_proj",
     "down_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj",
+    "k_proj",
     "o_proj",
-    "q_proj"
+    "q_proj",
+    "gate_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 sha256:7bc483c0b09a8e32d774880977bee2187e7ff6c4292530b5f13b031dfdff2f42
+oid sha256:9bdf912a81a8c6f951dcf34001e5cf73bd020115bca0a3daa8584634441b76e3
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6caa98a16ba83c472144e6439622e391b9ed7c7f0ffef59ccdd4b9ed0e87f903
+oid sha256:2f1dcdd15b76db955d741278ad8d3bb95ed70ae1a383dc22f3106f81f9ee933f
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494b33d421b03d1cd28f79b8a14e3ee58ac7b56ac617857ec95c88d4246e6c4f
+oid sha256:b57c7f5d43bf7daadabf2da6f96b4632b95a7e7bde83c3e8f0cb2baea8f08d40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017287578874578616,
+  "epoch": 0.0005186273662373585,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00017287578874578615,
-      "grad_norm": 3.482372760772705,
+      "grad_norm": 3.553006649017334,
       "learning_rate": 2e-05,
       "loss": 10.147,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.00017287578874578615,
       "eval_loss": 10.197986602783203,
-      "eval_runtime": 67.4855,
-      "eval_samples_per_second": 36.097,
-      "eval_steps_per_second": 18.048,
+      "eval_runtime": 100.6946,
+      "eval_samples_per_second": 24.192,
+      "eval_steps_per_second": 12.096,
       "step": 1
     },
     {
       "epoch": 0.0003457515774915723,
-      "grad_norm": 3.57196044921875,
+      "grad_norm": 3.655125141143799,
       "learning_rate": 4e-05,
       "loss": 9.9026,
       "step": 2
     },
     {
       "epoch": 0.0005186273662373585,
-      "grad_norm": 3.3633735179901123,
+      "grad_norm": 3.4464893341064453,
       "learning_rate": 6e-05,
-      "loss": 9.9502,
+      "loss": 9.9519,
       "step": 3
     },
     {
       "epoch": 0.0005186273662373585,
-      "eval_loss": 10.191715240478516,
-      "eval_runtime": 67.4992,
-      "eval_samples_per_second": 36.089,
-      "eval_steps_per_second": 18.045,
+      "eval_loss": 10.192020416259766,
+      "eval_runtime": 100.4666,
+      "eval_samples_per_second": 24.247,
+      "eval_steps_per_second": 12.123,
       "step": 3
-    },
-    {
-      "epoch": 0.0006915031549831446,
-      "grad_norm": 3.694139242172241,
-      "learning_rate": 8e-05,
-      "loss": 10.109,
-      "step": 4
-    },
-    {
-      "epoch": 0.0008643789437289308,
-      "grad_norm": 3.5772221088409424,
-      "learning_rate": 0.0001,
-      "loss": 10.1954,
-      "step": 5
-    },
-    {
-      "epoch": 0.001037254732474717,
-      "grad_norm": 3.585089683532715,
-      "learning_rate": 0.00012,
-      "loss": 10.2633,
-      "step": 6
-    },
-    {
-      "epoch": 0.001037254732474717,
-      "eval_loss": 10.106863975524902,
-      "eval_runtime": 67.0671,
-      "eval_samples_per_second": 36.322,
-      "eval_steps_per_second": 18.161,
-      "step": 6
-    },
-    {
-      "epoch": 0.001210130521220503,
-      "grad_norm": 3.840843439102173,
-      "learning_rate": 0.00014,
-      "loss": 10.4198,
-      "step": 7
-    },
-    {
-      "epoch": 0.0013830063099662892,
-      "grad_norm": 3.3266236782073975,
-      "learning_rate": 0.00016,
-      "loss": 10.0992,
-      "step": 8
-    },
-    {
-      "epoch": 0.0015558820987120754,
-      "grad_norm": 3.247655153274536,
-      "learning_rate": 0.00018,
-      "loss": 10.0575,
-      "step": 9
-    },
-    {
-      "epoch": 0.0015558820987120754,
-      "eval_loss": 9.946037292480469,
-      "eval_runtime": 67.5398,
-      "eval_samples_per_second": 36.068,
-      "eval_steps_per_second": 18.034,
-      "step": 9
-    },
-    {
-      "epoch": 0.0017287578874578616,
-      "grad_norm": 3.7988805770874023,
-      "learning_rate": 0.0002,
-      "loss": 9.8737,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5429904015360.0,
+  "total_flos": 1628971204608.0,
   "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 sha256:56cea1ed7427faf32abdfc3138b10c51013f0290b1f91671f66db7bd1d9eb990
+oid sha256:7d643b556e215e472d5553f222bdceb7aa9fc11d85e013337c48c5f6015adcd8
 size 6712